diff --git a/.mergify.yml b/.mergify.yml index 6ec28ae81a0bcede7563888f4d4e99782f6a59a8..1e306d672aa989a88aba9fd66531e618b7cb5d14 100644 --- a/.mergify.yml +++ b/.mergify.yml @@ -41,13 +41,13 @@ pull_request_rules: remove: ["conflicts"] - name: "auto add label=S2T" conditions: - - files~=^deepspeech/ + - files~=^paddlespeech/s2t/ actions: label: add: ["S2T"] - name: "auto add label=T2S" conditions: - - files~=^parakeet/ + - files~=^paddlespeech/t2s/ actions: label: add: ["T2S"] @@ -59,7 +59,7 @@ pull_request_rules: add: ["Audio"] - name: "auto add label=TextProcess" conditions: - - files~=^text_processing/ + - files~=^paddlespeech/text/ actions: label: add: ["TextProcess"] diff --git a/docs/source/asr/models_introduction.md b/docs/source/asr/models_introduction.md index c99093bd60e3f45e8cdad404b4941692ac384b66..7843a349599cb8291ea29ee633f6c8161fa1717c 100644 --- a/docs/source/asr/models_introduction.md +++ b/docs/source/asr/models_introduction.md @@ -61,7 +61,7 @@ For feature extraction, three methods are implemented, which are linear (FFT wit Currently, the released deepspeech2 online model use the linear feature extraction method. ``` The code for feature extraction -vi deepspeech/frontend/featurizer/audio_featurizer.py +vi paddlespeech/s2t/frontend/featurizer/audio_featurizer.py ``` ### Encoder @@ -69,7 +69,7 @@ The encoder is composed of two 2D convolution subsampling layers and a number of The code of Encoder is in: ``` -vi deepspeech/models/ds2_online/deepspeech2.py +vi paddlespeech/s2t/models/ds2_online/deepspeech2.py ``` ### Decoder @@ -78,9 +78,9 @@ To got the character possibilities of each frame, the feature representation of The code of the decoder is in: ``` # The code of constructing the decoder in model -vi deepspeech/models/ds2_online/deepspeech2.py +vi paddlespeech/s2t/models/ds2_online/deepspeech2.py # The code of CTC Decoder -vi deepspeech/modules/ctc.py +vi paddlespeech/s2t/modules/ctc.py ``` ### Training Process @@ -169,7 +169,7 @@ For data preparation and decoder, the deepspeech2 offline model is same with the The code of encoder and decoder for deepspeech2 offline model is in: ``` -vi deepspeech/models/ds2/deepspeech2.py +vi paddlespeech/s2t/models/ds2/deepspeech2.py ``` The training process and testing process of deepspeech2 offline model is very similary to deepspeech2 online model. diff --git a/docs/source/conf.py b/docs/source/conf.py index f2f75ce3ee630671e51ef8c8b5bae8ef6db0730f..e6431c7c49a624fe0db336116dd770f24375478a 100644 --- a/docs/source/conf.py +++ b/docs/source/conf.py @@ -28,8 +28,8 @@ autodoc_mock_imports = ["soundfile", "librosa"] # -- Project information ----------------------------------------------------- project = 'paddle speech' -copyright = '2021, Deepspeech-developers' -author = 'Deepspeech-developers' +copyright = '2021, paddlespeech-developers' +author = 'paddlespeech-developers' # The full version, including alpha/beta/rc tags release = '2.1' diff --git a/docs/source/index.rst b/docs/source/index.rst index 06bc2f3fa130e6af8e0af638375e876be6c4719f..53e5d15df5baaf307a3d0c24fce608af0d34a5e2 100644 --- a/docs/source/index.rst +++ b/docs/source/index.rst @@ -1,7 +1,7 @@ -Welcome to paddle Deepspeech documentation ! +Welcome to paddle PaddleSpeech documentation ! ============================================== -**Deepspeech** is a Speech toolkits implemented by paddlepaddle. +**PaddleSpeech** is a Speech toolkits implemented by paddlepaddle. Contents diff --git a/docs/source/tts/advanced_usage.md b/docs/source/tts/advanced_usage.md index 297f274f73a5edf079ff8af6004b3c510728e52a..0540a1c3f980c454edd99bb3fe71839bdba5cee1 100644 --- a/docs/source/tts/advanced_usage.md +++ b/docs/source/tts/advanced_usage.md @@ -67,7 +67,7 @@ There are two common ways to define a model which consists of several modules. ``` When a model is a complicated and made up of several components, each of which has a separate functionality, and can be replaced by other components with the same functionality, we prefer to define it in this way. -In the directory structure of PaddleSpeech TTS, modules with high reusability are placed in `parakeet.modules`, but models for specific tasks are placed in `parakeet.models`. When developing a new model, developers need to consider the feasibility of splitting the modules, and the degree of generality of the modules, and place them in appropriate directories. +In the directory structure of PaddleSpeech TTS, modules with high reusability are placed in `paddlespeech.t2s.modules`, but models for specific tasks are placed in `paddlespeech.t2s.models`. When developing a new model, developers need to consider the feasibility of splitting the modules, and the degree of generality of the modules, and place them in appropriate directories. ## PaddleSpeech TTS's Data Components Another critical componnet for a deep learning project is data. @@ -93,7 +93,7 @@ Then we need to select a format for saving metadata to the hard disk. There are Meanwhile, `cache` is added here, and a multi-process Manager is used to share memory between multiple processes. When `num_workers` is used, it is guaranteed that each sub process will not cache a copy. -The implementation of `DataTable` can be found in `parakeet/datasets/data_table.py`. +The implementation of `DataTable` can be found in `paddlespeech/t2s/datasets/data_table.py`. ```python class DataTable(Dataset): """Dataset to load and convert data for general purpose. @@ -179,9 +179,9 @@ We think this method is a little ugly. We prefer to return the necessary informa It takes advantage of the globality of Python's module level variables and the effect of context manager. -There is a module level variable in `parakeet/training/reporter.py` `OBSERVATIONS`，which is a `Dict` to store key-value. +There is a module level variable in `paddlespeech/t2s/training/reporter.py` `OBSERVATIONS`，which is a `Dict` to store key-value. ```python -# parakeet/training/reporter.py +# paddlespeech/t2s/training/reporter.py @contextlib.contextmanager def scope(observations): diff --git a/docs/source/tts/quick_start.md b/docs/source/tts/quick_start.md index f5d16bbfc7e29cd02d53ce01170f651d6753d46f..9fd9233886aeb869c707d540e1ee5b4c677b76dc 100644 --- a/docs/source/tts/quick_start.md +++ b/docs/source/tts/quick_start.md @@ -102,9 +102,9 @@ import numpy as np import paddle import yaml from yacs.config import CfgNode -from parakeet.models.fastspeech2 import FastSpeech2 -from parakeet.models.fastspeech2 import FastSpeech2Inference -from parakeet.modules.normalizer import ZScore +from paddlespeech.t2s.models.fastspeech2 import FastSpeech2 +from paddlespeech.t2s.models.fastspeech2 import FastSpeech2Inference +from paddlespeech.t2s.modules.normalizer import ZScore # examples/fastspeech2/baker/frontend.py from frontend import Frontend @@ -161,9 +161,9 @@ import paddle import soundfile as sf import yaml from yacs.config import CfgNode -from parakeet.models.parallel_wavegan import PWGGenerator -from parakeet.models.parallel_wavegan import PWGInference -from parakeet.modules.normalizer import ZScore +from paddlespeech.t2s.models.parallel_wavegan import PWGGenerator +from paddlespeech.t2s.models.parallel_wavegan import PWGInference +from paddlespeech.t2s.modules.normalizer import ZScore # load the pretrained model checkpoint_dir = Path("parallel_wavegan_baker_ckpt_0.4") diff --git a/examples/aishell/s0/path.sh b/examples/aishell/s0/path.sh index a066676e1d61c5117e9c08d279a2164d73d1c0b8..867cfb5da64e35dc86c3349a8d892403bdc1d5a6 100644 --- a/examples/aishell/s0/path.sh +++ b/examples/aishell/s0/path.sh @@ -11,4 +11,4 @@ export PYTHONPATH=${MAIN_ROOT}:${PYTHONPATH} export LD_LIBRARY_PATH=${LD_LIBRARY_PATH}:/usr/local/lib/ MODEL=deepspeech2 -export BIN_DIR=${MAIN_ROOT}/deepspeech/exps/${MODEL}/bin +export BIN_DIR=${MAIN_ROOT}/paddlespeech/s2t/exps/${MODEL}/bin diff --git a/examples/aishell/s1/path.sh b/examples/aishell/s1/path.sh index 0b9b0f8fc9bfc4cb533fc1dcf88bc9adbbec8be4..449829109e4cc276d1b8e1a32b15c2209a4498be 100644 --- a/examples/aishell/s1/path.sh +++ b/examples/aishell/s1/path.sh @@ -12,7 +12,7 @@ export LD_LIBRARY_PATH=${LD_LIBRARY_PATH}:/usr/local/lib/ # model exp MODEL=u2 -export BIN_DIR=${MAIN_ROOT}/deepspeech/exps/${MODEL}/bin +export BIN_DIR=${MAIN_ROOT}/paddlespeech/s2t/exps/${MODEL}/bin # srilm diff --git a/examples/aishell3/tts3/path.sh b/examples/aishell3/tts3/path.sh index 561d01632ba4b63b582ef07e460d31842823f07c..fb7e8411c80cc8cbf1c65dffaaf771bda961e10e 100755 --- a/examples/aishell3/tts3/path.sh +++ b/examples/aishell3/tts3/path.sh @@ -10,4 +10,4 @@ export PYTHONIOENCODING=UTF-8 export PYTHONPATH=${MAIN_ROOT}:${PYTHONPATH} MODEL=fastspeech2 -export BIN_DIR=${MAIN_ROOT}/parakeet/exps/${MODEL} +export BIN_DIR=${MAIN_ROOT}/paddlespeech/t2s/exps/${MODEL} diff --git a/examples/aishell3/vc0/README.md b/examples/aishell3/vc0/README.md index 9364cf00fd6155d012edafda9cfe4c2738abbc47..9a269ed5c738eac07592f07de4878db616a47d4e 100644 --- a/examples/aishell3/vc0/README.md +++ b/examples/aishell3/vc0/README.md @@ -39,7 +39,7 @@ There are silence in the edge of AISHELL-3's wavs, and the audio amplitude is ve We use Montreal Force Aligner 1.0. The label in aishell3 include pinyin，so the lexicon we provided to MFA is pinyin rather than Chinese characters. And the prosody marks(`$` and `%`) need to be removed. You shoud preprocess the dataset into the format which MFA needs, the texts have the same name with wavs and have the suffix `.lab`. -We use [lexicon.txt](https://github.com/PaddlePaddle/DeepSpeech/blob/develop/parakeet/exps/voice_cloning/tacotron2_ge2e/lexicon.txt) as the lexicon. +We use [lexicon.txt](https://github.com/PaddlePaddle/DeepSpeech/blob/develop/paddlespeech/t2s/exps/voice_cloning/tacotron2_ge2e/lexicon.txt) as the lexicon. You can download the alignment results from here [alignment_aishell3.tar.gz](https://paddlespeech.bj.bcebos.com/Parakeet/alignment_aishell3.tar.gz), or train your own MFA model reference to [use_mfa example](https://github.com/PaddlePaddle/DeepSpeech/tree/develop/examples/other/use_mfa) (use MFA1.x now) of our repo. diff --git a/examples/aishell3/vc0/path.sh b/examples/aishell3/vc0/path.sh index 485d73bf7bc2d0541c6d29976cffe64282efd8cf..dfae49afe31b475d1916729732146b9469f4b5f1 100755 --- a/examples/aishell3/vc0/path.sh +++ b/examples/aishell3/vc0/path.sh @@ -10,4 +10,4 @@ export PYTHONIOENCODING=UTF-8 export PYTHONPATH=${MAIN_ROOT}:${PYTHONPATH} MODEL=voice_cloning/tacotron2_ge2e -export BIN_DIR=${MAIN_ROOT}/parakeet/exps/${MODEL} +export BIN_DIR=${MAIN_ROOT}/paddlespeech/t2s/exps/${MODEL} diff --git a/examples/callcenter/s1/path.sh b/examples/callcenter/s1/path.sh index e4e278da4f6ba99ca06f39b60ade6529d0e9ebfa..6d95864bb27c5b7f9fea685b402ba9a9146d2d61 100644 --- a/examples/callcenter/s1/path.sh +++ b/examples/callcenter/s1/path.sh @@ -12,4 +12,4 @@ export LD_LIBRARY_PATH=${LD_LIBRARY_PATH}:/usr/local/lib/ MODEL=u2 -export BIN_DIR=${MAIN_ROOT}/deepspeech/exps/${MODEL}/bin +export BIN_DIR=${MAIN_ROOT}/paddlespeech/s2t/exps/${MODEL}/bin diff --git a/examples/csmsc/tts2/path.sh b/examples/csmsc/tts2/path.sh index 1a9519f37aaa50fc809effd2bea23383908b95f1..ad0dd552164658090ebd29a3ff93959c5e795d01 100755 --- a/examples/csmsc/tts2/path.sh +++ b/examples/csmsc/tts2/path.sh @@ -10,4 +10,4 @@ export PYTHONIOENCODING=UTF-8 export PYTHONPATH=${MAIN_ROOT}:${PYTHONPATH} MODEL=speedyspeech -export BIN_DIR=${MAIN_ROOT}/parakeet/exps/${MODEL} \ No newline at end of file +export BIN_DIR=${MAIN_ROOT}/paddlespeech/t2s/exps/${MODEL} \ No newline at end of file diff --git a/examples/csmsc/tts3/path.sh b/examples/csmsc/tts3/path.sh index 561d01632ba4b63b582ef07e460d31842823f07c..fb7e8411c80cc8cbf1c65dffaaf771bda961e10e 100755 --- a/examples/csmsc/tts3/path.sh +++ b/examples/csmsc/tts3/path.sh @@ -10,4 +10,4 @@ export PYTHONIOENCODING=UTF-8 export PYTHONPATH=${MAIN_ROOT}:${PYTHONPATH} MODEL=fastspeech2 -export BIN_DIR=${MAIN_ROOT}/parakeet/exps/${MODEL} +export BIN_DIR=${MAIN_ROOT}/paddlespeech/t2s/exps/${MODEL} diff --git a/examples/csmsc/voc1/path.sh b/examples/csmsc/voc1/path.sh index 28d39ae0078daefa770c0b9c27c4bafe6e40f254..1e6647b86e1dc27707ddfbf54fe34da9a9e5d04b 100755 --- a/examples/csmsc/voc1/path.sh +++ b/examples/csmsc/voc1/path.sh @@ -10,4 +10,4 @@ export PYTHONIOENCODING=UTF-8 export PYTHONPATH=${MAIN_ROOT}:${PYTHONPATH} MODEL=parallelwave_gan -export BIN_DIR=${MAIN_ROOT}/parakeet/exps/gan_vocoder/${MODEL} \ No newline at end of file +export BIN_DIR=${MAIN_ROOT}/paddlespeech/t2s/exps/gan_vocoder/${MODEL} \ No newline at end of file diff --git a/examples/csmsc/voc3/path.sh b/examples/csmsc/voc3/path.sh index f6b9fe61a918a75ed2438719c236a7c2be4645c8..86c8784a9d7dd7bc5631ef368c2738f9ab013e92 100755 --- a/examples/csmsc/voc3/path.sh +++ b/examples/csmsc/voc3/path.sh @@ -10,4 +10,4 @@ export PYTHONIOENCODING=UTF-8 export PYTHONPATH=${MAIN_ROOT}:${PYTHONPATH} MODEL=multi_band_melgan -export BIN_DIR=${MAIN_ROOT}/parakeet/exps/gan_vocoder/${MODEL} \ No newline at end of file +export BIN_DIR=${MAIN_ROOT}/paddlespeech/t2s/exps/gan_vocoder/${MODEL} \ No newline at end of file diff --git a/examples/librispeech/s0/path.sh b/examples/librispeech/s0/path.sh index 5ec461d743ef41fa8479f94bcec7f1b96a17b89d..0538d6f1f0dfc1d911ef6e1415b7924b557f37b2 100644 --- a/examples/librispeech/s0/path.sh +++ b/examples/librispeech/s0/path.sh @@ -12,4 +12,4 @@ export LD_LIBRARY_PATH=${LD_LIBRARY_PATH}:/usr/local/lib/ MODEL=deepspeech2 -export BIN_DIR=${MAIN_ROOT}/deepspeech/exps/${MODEL}/bin +export BIN_DIR=${MAIN_ROOT}/paddlespeech/s2t/exps/${MODEL}/bin diff --git a/examples/librispeech/s1/path.sh b/examples/librispeech/s1/path.sh index 581a350a532a482ecd3aef54835ab73b8a68353e..e825979c471f0266c183720ceb410ae30c4ede27 100644 --- a/examples/librispeech/s1/path.sh +++ b/examples/librispeech/s1/path.sh @@ -12,4 +12,4 @@ export LD_LIBRARY_PATH=${LD_LIBRARY_PATH}:/usr/local/lib/ MODEL=u2 -export BIN_DIR=${MAIN_ROOT}/deepspeech/exps/${MODEL}/bin +export BIN_DIR=${MAIN_ROOT}/paddlespeech/s2t/exps/${MODEL}/bin diff --git a/examples/librispeech/s2/path.sh b/examples/librispeech/s2/path.sh index 32ff28c1024e8a9b2f13c259d38108efc65dfa55..ad6b6913904821a43b039dbbf325c684e8b57649 100644 --- a/examples/librispeech/s2/path.sh +++ b/examples/librispeech/s2/path.sh @@ -12,7 +12,7 @@ export LD_LIBRARY_PATH=${LD_LIBRARY_PATH}:/usr/local/lib/ MODEL=u2_kaldi -export BIN_DIR=${MAIN_ROOT}/deepspeech/exps/${MODEL}/bin +export BIN_DIR=${MAIN_ROOT}/paddlespeech/s2t/exps/${MODEL}/bin # srilm export LIBLBFGS=${MAIN_ROOT}/tools/liblbfgs-1.10 diff --git a/examples/ljspeech/tts0/path.sh b/examples/ljspeech/tts0/path.sh index 590e7a9c97f7d5baf59d2c8ca9a2ffed6df820ed..a37cd21e3210967415d6842067f9294bfbce7b5e 100755 --- a/examples/ljspeech/tts0/path.sh +++ b/examples/ljspeech/tts0/path.sh @@ -10,4 +10,4 @@ export PYTHONIOENCODING=UTF-8 export PYTHONPATH=${MAIN_ROOT}:${PYTHONPATH} MODEL=tacotron2 -export BIN_DIR=${MAIN_ROOT}/parakeet/exps/${MODEL} +export BIN_DIR=${MAIN_ROOT}/paddlespeech/t2s/exps/${MODEL} diff --git a/examples/ljspeech/tts1/path.sh b/examples/ljspeech/tts1/path.sh index 201261b168f2932ffd64c842aa5140d554715195..32eecd857a92e7ceb7d98d2434b3e8978c7c75f7 100755 --- a/examples/ljspeech/tts1/path.sh +++ b/examples/ljspeech/tts1/path.sh @@ -10,4 +10,4 @@ export PYTHONIOENCODING=UTF-8 export PYTHONPATH=${MAIN_ROOT}:${PYTHONPATH} MODEL=transformer_tts -export BIN_DIR=${MAIN_ROOT}/parakeet/exps/${MODEL} +export BIN_DIR=${MAIN_ROOT}/paddlespeech/t2s/exps/${MODEL} diff --git a/examples/ljspeech/tts3/path.sh b/examples/ljspeech/tts3/path.sh index 561d01632ba4b63b582ef07e460d31842823f07c..fb7e8411c80cc8cbf1c65dffaaf771bda961e10e 100755 --- a/examples/ljspeech/tts3/path.sh +++ b/examples/ljspeech/tts3/path.sh @@ -10,4 +10,4 @@ export PYTHONIOENCODING=UTF-8 export PYTHONPATH=${MAIN_ROOT}:${PYTHONPATH} MODEL=fastspeech2 -export BIN_DIR=${MAIN_ROOT}/parakeet/exps/${MODEL} +export BIN_DIR=${MAIN_ROOT}/paddlespeech/t2s/exps/${MODEL} diff --git a/examples/ljspeech/voc0/path.sh b/examples/ljspeech/voc0/path.sh index b9fe83ecc96368cbc948f1265cb204b68b276c31..4705c9e159002095fffcdb2cf18fa0f6daada957 100755 --- a/examples/ljspeech/voc0/path.sh +++ b/examples/ljspeech/voc0/path.sh @@ -10,4 +10,4 @@ export PYTHONIOENCODING=UTF-8 export PYTHONPATH=${MAIN_ROOT}:${PYTHONPATH} MODEL=waveflow -export BIN_DIR=${MAIN_ROOT}/parakeet/exps/${MODEL} \ No newline at end of file +export BIN_DIR=${MAIN_ROOT}/paddlespeech/t2s/exps/${MODEL} \ No newline at end of file diff --git a/examples/ljspeech/voc1/path.sh b/examples/ljspeech/voc1/path.sh index 28d39ae0078daefa770c0b9c27c4bafe6e40f254..1e6647b86e1dc27707ddfbf54fe34da9a9e5d04b 100755 --- a/examples/ljspeech/voc1/path.sh +++ b/examples/ljspeech/voc1/path.sh @@ -10,4 +10,4 @@ export PYTHONIOENCODING=UTF-8 export PYTHONPATH=${MAIN_ROOT}:${PYTHONPATH} MODEL=parallelwave_gan -export BIN_DIR=${MAIN_ROOT}/parakeet/exps/gan_vocoder/${MODEL} \ No newline at end of file +export BIN_DIR=${MAIN_ROOT}/paddlespeech/t2s/exps/gan_vocoder/${MODEL} \ No newline at end of file diff --git a/examples/other/1xt2x/src_deepspeech2x/__init__.py b/examples/other/1xt2x/src_deepspeech2x/__init__.py index d85a3dde7d44a388878a0b0f411f4a2bd594800d..62f3eee3e9113f246616dd2afd7634d4c363a45c 100644 --- a/examples/other/1xt2x/src_deepspeech2x/__init__.py +++ b/examples/other/1xt2x/src_deepspeech2x/__init__.py @@ -21,7 +21,7 @@ from paddle import nn from paddle.fluid import core from paddle.nn import functional as F -from deepspeech.utils.log import Log +from paddlespeech.s2t.utils.log import Log #TODO(Hui Zhang): remove fluid import logger = Log(__name__).getlog() diff --git a/examples/other/1xt2x/src_deepspeech2x/bin/test.py b/examples/other/1xt2x/src_deepspeech2x/bin/test.py index be3f9822f6507c9dc8e7305eb1da81ab2eff4d58..b4f9cdf9dab02422818ee39f030515d917b2b343 100644 --- a/examples/other/1xt2x/src_deepspeech2x/bin/test.py +++ b/examples/other/1xt2x/src_deepspeech2x/bin/test.py @@ -14,9 +14,9 @@ """Evaluation for DeepSpeech2 model.""" from src_deepspeech2x.test_model import DeepSpeech2Tester as Tester -from deepspeech.exps.deepspeech2.config import get_cfg_defaults -from deepspeech.training.cli import default_argument_parser -from deepspeech.utils.utility import print_arguments +from paddlespeech.s2t.exps.deepspeech2.config import get_cfg_defaults +from paddlespeech.s2t.training.cli import default_argument_parser +from paddlespeech.s2t.utils.utility import print_arguments def main_sp(config, args): diff --git a/examples/other/1xt2x/src_deepspeech2x/models/ds2/deepspeech2.py b/examples/other/1xt2x/src_deepspeech2x/models/ds2/deepspeech2.py index ce123743af5c56268c0ec1e03fc390c11fd39541..ad83a41db48c460db66700b33b5dff5f2aa805a6 100644 --- a/examples/other/1xt2x/src_deepspeech2x/models/ds2/deepspeech2.py +++ b/examples/other/1xt2x/src_deepspeech2x/models/ds2/deepspeech2.py @@ -19,11 +19,11 @@ from paddle import nn from src_deepspeech2x.models.ds2.rnn import RNNStack from yacs.config import CfgNode -from deepspeech.models.ds2.conv import ConvStack -from deepspeech.modules.ctc import CTCDecoder -from deepspeech.utils import layer_tools -from deepspeech.utils.checkpoint import Checkpoint -from deepspeech.utils.log import Log +from paddlespeech.s2t.models.ds2.conv import ConvStack +from paddlespeech.s2t.modules.ctc import CTCDecoder +from paddlespeech.s2t.utils import layer_tools +from paddlespeech.s2t.utils.checkpoint import Checkpoint +from paddlespeech.s2t.utils.log import Log logger = Log(__name__).getlog() __all__ = ['DeepSpeech2Model', 'DeepSpeech2InferModel'] diff --git a/examples/other/1xt2x/src_deepspeech2x/models/ds2/rnn.py b/examples/other/1xt2x/src_deepspeech2x/models/ds2/rnn.py index e45db7c053d4128bf51ed1787af3a4f78c9081e4..383a07467027194062108733d780a77f0483155d 100644 --- a/examples/other/1xt2x/src_deepspeech2x/models/ds2/rnn.py +++ b/examples/other/1xt2x/src_deepspeech2x/models/ds2/rnn.py @@ -18,9 +18,9 @@ from paddle import nn from paddle.nn import functional as F from paddle.nn import initializer as I -from deepspeech.modules.activation import brelu -from deepspeech.modules.mask import make_non_pad_mask -from deepspeech.utils.log import Log +from paddlespeech.s2t.modules.activation import brelu +from paddlespeech.s2t.modules.mask import make_non_pad_mask +from paddlespeech.s2t.utils.log import Log logger = Log(__name__).getlog() __all__ = ['RNNStack'] diff --git a/examples/other/1xt2x/src_deepspeech2x/test_model.py b/examples/other/1xt2x/src_deepspeech2x/test_model.py index 203a3bace6362ef426a6f091ac1e8226d19bd423..a9afc6313f705fd5e04a792048323457d39cab5e 100644 --- a/examples/other/1xt2x/src_deepspeech2x/test_model.py +++ b/examples/other/1xt2x/src_deepspeech2x/test_model.py @@ -26,19 +26,19 @@ from src_deepspeech2x.models.ds2 import DeepSpeech2InferModel from src_deepspeech2x.models.ds2 import DeepSpeech2Model from yacs.config import CfgNode -from deepspeech.frontend.featurizer.text_featurizer import TextFeaturizer -from deepspeech.io.collator import SpeechCollator -from deepspeech.io.dataset import ManifestDataset -from deepspeech.io.sampler import SortagradBatchSampler -from deepspeech.io.sampler import SortagradDistributedBatchSampler -from deepspeech.models.ds2_online import DeepSpeech2InferModelOnline -from deepspeech.models.ds2_online import DeepSpeech2ModelOnline -from deepspeech.training.gradclip import ClipGradByGlobalNormWithLog -from deepspeech.training.trainer import Trainer -from deepspeech.utils import error_rate -from deepspeech.utils import layer_tools -from deepspeech.utils import mp_tools -from deepspeech.utils.log import Log +from paddlespeech.s2t.frontend.featurizer.text_featurizer import TextFeaturizer +from paddlespeech.s2t.io.collator import SpeechCollator +from paddlespeech.s2t.io.dataset import ManifestDataset +from paddlespeech.s2t.io.sampler import SortagradBatchSampler +from paddlespeech.s2t.io.sampler import SortagradDistributedBatchSampler +from paddlespeech.s2t.models.ds2_online import DeepSpeech2InferModelOnline +from paddlespeech.s2t.models.ds2_online import DeepSpeech2ModelOnline +from paddlespeech.s2t.training.gradclip import ClipGradByGlobalNormWithLog +from paddlespeech.s2t.training.trainer import Trainer +from paddlespeech.s2t.utils import error_rate +from paddlespeech.s2t.utils import layer_tools +from paddlespeech.s2t.utils import mp_tools +from paddlespeech.s2t.utils.log import Log logger = Log(__name__).getlog() diff --git a/examples/other/ge2e/path.sh b/examples/other/ge2e/path.sh index 4333199cb917b31f49886c3fd81324249383661d..b4f77985908fafacfa9fada5a7e120a52a621832 100755 --- a/examples/other/ge2e/path.sh +++ b/examples/other/ge2e/path.sh @@ -10,4 +10,4 @@ export PYTHONIOENCODING=UTF-8 export PYTHONPATH=${MAIN_ROOT}:${PYTHONPATH} MODEL=ge2e -export BIN_DIR=${MAIN_ROOT}/parakeet/exps/${MODEL} +export BIN_DIR=${MAIN_ROOT}/paddlespeech/t2s/exps/${MODEL} diff --git a/examples/other/text_frontend/test_g2p.py b/examples/other/text_frontend/test_g2p.py index 15005a003729bb6329d26f74028fc03fd8df4427..2f09208607de3bc5315e6dea7f3bcb9bdd2f3f65 100644 --- a/examples/other/text_frontend/test_g2p.py +++ b/examples/other/text_frontend/test_g2p.py @@ -15,8 +15,8 @@ import argparse import re from pathlib import Path -from parakeet.frontend.zh_frontend import Frontend as zhFrontend -from parakeet.utils.error_rate import word_errors +from paddlespeech.t2s.frontend.zh_frontend import Frontend as zhFrontend +from paddlespeech.t2s.utils.error_rate import word_errors SILENCE_TOKENS = {"sp", "sil", "sp1", "spl"} diff --git a/examples/other/text_frontend/test_textnorm.py b/examples/other/text_frontend/test_textnorm.py index 22f90f8748d9136e4d5fb6788bd7c72144cc971c..503f959e9cf85424f4325589c2e55402072c0ed9 100644 --- a/examples/other/text_frontend/test_textnorm.py +++ b/examples/other/text_frontend/test_textnorm.py @@ -15,8 +15,8 @@ import argparse import re from pathlib import Path -from parakeet.frontend.zh_normalization.text_normlization import TextNormalizer -from parakeet.utils.error_rate import char_errors +from paddlespeech.t2s.frontend.zh_normalization.text_normlization import TextNormalizer +from paddlespeech.t2s.utils.error_rate import char_errors # delete english characters diff --git a/examples/ted_en_zh/t0/path.sh b/examples/ted_en_zh/t0/path.sh index f6801e436b10f12cd57ca77663a8ccac76527dd7..fd537917a8204848957a6cf14268da5d3dbc4b35 100644 --- a/examples/ted_en_zh/t0/path.sh +++ b/examples/ted_en_zh/t0/path.sh @@ -12,4 +12,4 @@ export LD_LIBRARY_PATH=${LD_LIBRARY_PATH}:/usr/local/lib/ MODEL=u2_st -export BIN_DIR=${MAIN_ROOT}/deepspeech/exps/${MODEL}/bin +export BIN_DIR=${MAIN_ROOT}/paddlespeech/s2t/exps/${MODEL}/bin diff --git a/examples/timit/s1/path.sh b/examples/timit/s1/path.sh index e4e278da4f6ba99ca06f39b60ade6529d0e9ebfa..6d95864bb27c5b7f9fea685b402ba9a9146d2d61 100644 --- a/examples/timit/s1/path.sh +++ b/examples/timit/s1/path.sh @@ -12,4 +12,4 @@ export LD_LIBRARY_PATH=${LD_LIBRARY_PATH}:/usr/local/lib/ MODEL=u2 -export BIN_DIR=${MAIN_ROOT}/deepspeech/exps/${MODEL}/bin +export BIN_DIR=${MAIN_ROOT}/paddlespeech/s2t/exps/${MODEL}/bin diff --git a/examples/tiny/s0/path.sh b/examples/tiny/s0/path.sh index 8a9345f2ec18e0bb5fc77906d068cbf6087ead04..f43a623e1c2d7559f3e0e458f9e0c8a50f6666f0 100644 --- a/examples/tiny/s0/path.sh +++ b/examples/tiny/s0/path.sh @@ -11,4 +11,4 @@ export LD_LIBRARY_PATH=${LD_LIBRARY_PATH}:/usr/local/lib/ MODEL=deepspeech2 -export BIN_DIR=${MAIN_ROOT}/deepspeech/exps/${MODEL}/bin +export BIN_DIR=${MAIN_ROOT}/paddlespeech/s2t/exps/${MODEL}/bin diff --git a/examples/tiny/s1/path.sh b/examples/tiny/s1/path.sh index 29841bc10130a012d5d5eb92855a0394e9acff93..900156a61321cf8187922a00f54b631c70c48ba4 100644 --- a/examples/tiny/s1/path.sh +++ b/examples/tiny/s1/path.sh @@ -11,4 +11,4 @@ export LD_LIBRARY_PATH=${LD_LIBRARY_PATH}:/usr/local/lib/ MODEL=u2 -export BIN_DIR=${MAIN_ROOT}/deepspeech/exps/${MODEL}/bin +export BIN_DIR=${MAIN_ROOT}/paddlespeech/s2t/exps/${MODEL}/bin diff --git a/examples/vctk/tts3/path.sh b/examples/vctk/tts3/path.sh index 561d01632ba4b63b582ef07e460d31842823f07c..fb7e8411c80cc8cbf1c65dffaaf771bda961e10e 100755 --- a/examples/vctk/tts3/path.sh +++ b/examples/vctk/tts3/path.sh @@ -10,4 +10,4 @@ export PYTHONIOENCODING=UTF-8 export PYTHONPATH=${MAIN_ROOT}:${PYTHONPATH} MODEL=fastspeech2 -export BIN_DIR=${MAIN_ROOT}/parakeet/exps/${MODEL} +export BIN_DIR=${MAIN_ROOT}/paddlespeech/t2s/exps/${MODEL} diff --git a/examples/vctk/voc1/path.sh b/examples/vctk/voc1/path.sh index 28d39ae0078daefa770c0b9c27c4bafe6e40f254..1e6647b86e1dc27707ddfbf54fe34da9a9e5d04b 100755 --- a/examples/vctk/voc1/path.sh +++ b/examples/vctk/voc1/path.sh @@ -10,4 +10,4 @@ export PYTHONIOENCODING=UTF-8 export PYTHONPATH=${MAIN_ROOT}:${PYTHONPATH} MODEL=parallelwave_gan -export BIN_DIR=${MAIN_ROOT}/parakeet/exps/gan_vocoder/${MODEL} \ No newline at end of file +export BIN_DIR=${MAIN_ROOT}/paddlespeech/t2s/exps/gan_vocoder/${MODEL} \ No newline at end of file diff --git a/hub/setup_hub.sh b/hub/setup_hub.sh index f2d43ad105fe6be2951f846dc7e529ce5069e3e3..25c89f2b269cc6f464c259d409ef05f8de05b3b2 100644 --- a/hub/setup_hub.sh +++ b/hub/setup_hub.sh @@ -52,7 +52,7 @@ fi # install decoders python3 -c "import pkg_resources; pkg_resources.require(\"swig_decoders==1.1\")" if [ $? != 0 ]; then - cd deepspeech/decoders/swig > /dev/null + cd paddlespeech/s2t/decoders/swig > /dev/null sh setup.sh cd - > /dev/null fi diff --git a/paddlespeech/__init__.py b/paddlespeech/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/deepspeech/__init__.py b/paddlespeech/s2t/__init__.py similarity index 99% rename from deepspeech/__init__.py rename to paddlespeech/s2t/__init__.py index 5762e6359404580ca229d4218afe6b08851371d5..855ceef96f5fced0bb2f1299bc011fe1fa663ec3 100644 --- a/deepspeech/__init__.py +++ b/paddlespeech/s2t/__init__.py @@ -21,7 +21,7 @@ from paddle import nn from paddle.fluid import core from paddle.nn import functional as F -from deepspeech.utils.log import Log +from paddlespeech.s2t.utils.log import Log #TODO(Hui Zhang): remove fluid import logger = Log(__name__).getlog() diff --git a/deepspeech/decoders/README.md b/paddlespeech/s2t/decoders/README.md similarity index 100% rename from deepspeech/decoders/README.md rename to paddlespeech/s2t/decoders/README.md diff --git a/deepspeech/decoders/__init__.py b/paddlespeech/s2t/decoders/__init__.py similarity index 100% rename from deepspeech/decoders/__init__.py rename to paddlespeech/s2t/decoders/__init__.py diff --git a/deepspeech/decoders/beam_search/__init__.py b/paddlespeech/s2t/decoders/beam_search/__init__.py similarity index 100% rename from deepspeech/decoders/beam_search/__init__.py rename to paddlespeech/s2t/decoders/beam_search/__init__.py diff --git a/deepspeech/decoders/beam_search/batch_beam_search.py b/paddlespeech/s2t/decoders/beam_search/batch_beam_search.py similarity index 100% rename from deepspeech/decoders/beam_search/batch_beam_search.py rename to paddlespeech/s2t/decoders/beam_search/batch_beam_search.py diff --git a/deepspeech/decoders/beam_search/beam_search.py b/paddlespeech/s2t/decoders/beam_search/beam_search.py similarity index 99% rename from deepspeech/decoders/beam_search/beam_search.py rename to paddlespeech/s2t/decoders/beam_search/beam_search.py index 8fd8f9b8fa6f6a80dabf92749d1a939bd747b304..6c4f069d855dfb8ad4bbc7025867be278d3ff4fb 100644 --- a/deepspeech/decoders/beam_search/beam_search.py +++ b/paddlespeech/s2t/decoders/beam_search/beam_search.py @@ -25,7 +25,7 @@ import paddle from ..scorers.scorer_interface import PartialScorerInterface from ..scorers.scorer_interface import ScorerInterface from ..utils import end_detect -from deepspeech.utils.log import Log +from paddlespeech.s2t.utils.log import Log logger = Log(__name__).getlog() diff --git a/deepspeech/decoders/ctcdecoder/__init__.py b/paddlespeech/s2t/decoders/ctcdecoder/__init__.py similarity index 100% rename from deepspeech/decoders/ctcdecoder/__init__.py rename to paddlespeech/s2t/decoders/ctcdecoder/__init__.py diff --git a/deepspeech/decoders/ctcdecoder/decoders_deprecated.py b/paddlespeech/s2t/decoders/ctcdecoder/decoders_deprecated.py similarity index 100% rename from deepspeech/decoders/ctcdecoder/decoders_deprecated.py rename to paddlespeech/s2t/decoders/ctcdecoder/decoders_deprecated.py diff --git a/deepspeech/decoders/ctcdecoder/scorer_deprecated.py b/paddlespeech/s2t/decoders/ctcdecoder/scorer_deprecated.py similarity index 100% rename from deepspeech/decoders/ctcdecoder/scorer_deprecated.py rename to paddlespeech/s2t/decoders/ctcdecoder/scorer_deprecated.py diff --git a/deepspeech/decoders/ctcdecoder/swig/.gitignore b/paddlespeech/s2t/decoders/ctcdecoder/swig/.gitignore similarity index 100% rename from deepspeech/decoders/ctcdecoder/swig/.gitignore rename to paddlespeech/s2t/decoders/ctcdecoder/swig/.gitignore diff --git a/deepspeech/decoders/ctcdecoder/swig/__init__.py b/paddlespeech/s2t/decoders/ctcdecoder/swig/__init__.py similarity index 100% rename from deepspeech/decoders/ctcdecoder/swig/__init__.py rename to paddlespeech/s2t/decoders/ctcdecoder/swig/__init__.py diff --git a/deepspeech/decoders/ctcdecoder/swig/ctc_beam_search_decoder.cpp b/paddlespeech/s2t/decoders/ctcdecoder/swig/ctc_beam_search_decoder.cpp similarity index 100% rename from deepspeech/decoders/ctcdecoder/swig/ctc_beam_search_decoder.cpp rename to paddlespeech/s2t/decoders/ctcdecoder/swig/ctc_beam_search_decoder.cpp diff --git a/deepspeech/decoders/ctcdecoder/swig/ctc_beam_search_decoder.h b/paddlespeech/s2t/decoders/ctcdecoder/swig/ctc_beam_search_decoder.h similarity index 100% rename from deepspeech/decoders/ctcdecoder/swig/ctc_beam_search_decoder.h rename to paddlespeech/s2t/decoders/ctcdecoder/swig/ctc_beam_search_decoder.h diff --git a/deepspeech/decoders/ctcdecoder/swig/ctc_greedy_decoder.cpp b/paddlespeech/s2t/decoders/ctcdecoder/swig/ctc_greedy_decoder.cpp similarity index 100% rename from deepspeech/decoders/ctcdecoder/swig/ctc_greedy_decoder.cpp rename to paddlespeech/s2t/decoders/ctcdecoder/swig/ctc_greedy_decoder.cpp diff --git a/deepspeech/decoders/ctcdecoder/swig/ctc_greedy_decoder.h b/paddlespeech/s2t/decoders/ctcdecoder/swig/ctc_greedy_decoder.h similarity index 100% rename from deepspeech/decoders/ctcdecoder/swig/ctc_greedy_decoder.h rename to paddlespeech/s2t/decoders/ctcdecoder/swig/ctc_greedy_decoder.h diff --git a/deepspeech/decoders/ctcdecoder/swig/decoder_utils.cpp b/paddlespeech/s2t/decoders/ctcdecoder/swig/decoder_utils.cpp similarity index 100% rename from deepspeech/decoders/ctcdecoder/swig/decoder_utils.cpp rename to paddlespeech/s2t/decoders/ctcdecoder/swig/decoder_utils.cpp diff --git a/deepspeech/decoders/ctcdecoder/swig/decoder_utils.h b/paddlespeech/s2t/decoders/ctcdecoder/swig/decoder_utils.h similarity index 100% rename from deepspeech/decoders/ctcdecoder/swig/decoder_utils.h rename to paddlespeech/s2t/decoders/ctcdecoder/swig/decoder_utils.h diff --git a/deepspeech/decoders/ctcdecoder/swig/decoders.i b/paddlespeech/s2t/decoders/ctcdecoder/swig/decoders.i similarity index 100% rename from deepspeech/decoders/ctcdecoder/swig/decoders.i rename to paddlespeech/s2t/decoders/ctcdecoder/swig/decoders.i diff --git a/deepspeech/decoders/ctcdecoder/swig/path_trie.cpp b/paddlespeech/s2t/decoders/ctcdecoder/swig/path_trie.cpp similarity index 100% rename from deepspeech/decoders/ctcdecoder/swig/path_trie.cpp rename to paddlespeech/s2t/decoders/ctcdecoder/swig/path_trie.cpp diff --git a/deepspeech/decoders/ctcdecoder/swig/path_trie.h b/paddlespeech/s2t/decoders/ctcdecoder/swig/path_trie.h similarity index 100% rename from deepspeech/decoders/ctcdecoder/swig/path_trie.h rename to paddlespeech/s2t/decoders/ctcdecoder/swig/path_trie.h diff --git a/deepspeech/decoders/ctcdecoder/swig/scorer.cpp b/paddlespeech/s2t/decoders/ctcdecoder/swig/scorer.cpp similarity index 100% rename from deepspeech/decoders/ctcdecoder/swig/scorer.cpp rename to paddlespeech/s2t/decoders/ctcdecoder/swig/scorer.cpp diff --git a/deepspeech/decoders/ctcdecoder/swig/scorer.h b/paddlespeech/s2t/decoders/ctcdecoder/swig/scorer.h similarity index 100% rename from deepspeech/decoders/ctcdecoder/swig/scorer.h rename to paddlespeech/s2t/decoders/ctcdecoder/swig/scorer.h diff --git a/deepspeech/decoders/ctcdecoder/swig/setup.py b/paddlespeech/s2t/decoders/ctcdecoder/swig/setup.py similarity index 100% rename from deepspeech/decoders/ctcdecoder/swig/setup.py rename to paddlespeech/s2t/decoders/ctcdecoder/swig/setup.py diff --git a/deepspeech/decoders/ctcdecoder/swig/setup.sh b/paddlespeech/s2t/decoders/ctcdecoder/swig/setup.sh similarity index 100% rename from deepspeech/decoders/ctcdecoder/swig/setup.sh rename to paddlespeech/s2t/decoders/ctcdecoder/swig/setup.sh diff --git a/deepspeech/decoders/ctcdecoder/swig_wrapper.py b/paddlespeech/s2t/decoders/ctcdecoder/swig_wrapper.py similarity index 100% rename from deepspeech/decoders/ctcdecoder/swig_wrapper.py rename to paddlespeech/s2t/decoders/ctcdecoder/swig_wrapper.py diff --git a/deepspeech/decoders/ctcdecoder/tests/test_decoders.py b/paddlespeech/s2t/decoders/ctcdecoder/tests/test_decoders.py similarity index 98% rename from deepspeech/decoders/ctcdecoder/tests/test_decoders.py rename to paddlespeech/s2t/decoders/ctcdecoder/tests/test_decoders.py index 6e6265ef4848e362215c3b908af026241ccb6aed..a284890d6a45728efed01a0915a1069ca68154b1 100644 --- a/deepspeech/decoders/ctcdecoder/tests/test_decoders.py +++ b/paddlespeech/s2t/decoders/ctcdecoder/tests/test_decoders.py @@ -14,7 +14,7 @@ """Test decoders.""" import unittest -from deepspeech.decoders import decoders_deprecated as decoder +from paddlespeech.s2t.decoders import decoders_deprecated as decoder class TestDecoders(unittest.TestCase): diff --git a/deepspeech/decoders/recog.py b/paddlespeech/s2t/decoders/recog.py similarity index 95% rename from deepspeech/decoders/recog.py rename to paddlespeech/s2t/decoders/recog.py index bc48e692c9bf40fe0ea89debbcba10f79cfe56b0..d0710f9c40d1ad547484a86c9b0ba54ee38abbb0 100644 --- a/deepspeech/decoders/recog.py +++ b/paddlespeech/s2t/decoders/recog.py @@ -21,11 +21,11 @@ from .beam_search import BeamSearch from .scorers.length_bonus import LengthBonus from .scorers.scorer_interface import BatchScorerInterface from .utils import add_results_to_json -from deepspeech.exps import dynamic_import_tester -from deepspeech.io.reader import LoadInputsAndTargets -from deepspeech.models.asr_interface import ASRInterface -from deepspeech.models.lm_interface import dynamic_import_lm -from deepspeech.utils.log import Log +from paddlespeech.s2t.exps import dynamic_import_tester +from paddlespeech.s2t.io.reader import LoadInputsAndTargets +from paddlespeech.s2t.models.asr_interface import ASRInterface +from paddlespeech.s2t.models.lm_interface import dynamic_import_lm +from paddlespeech.s2t.utils.log import Log logger = Log(__name__).getlog() diff --git a/deepspeech/decoders/recog_bin.py b/paddlespeech/s2t/decoders/recog_bin.py similarity index 99% rename from deepspeech/decoders/recog_bin.py rename to paddlespeech/s2t/decoders/recog_bin.py index 7c86664839479c83f96767367d08472e32c574a3..e4d81f40916306933ee5ae7e060cc7bfa61f72d9 100644 --- a/deepspeech/decoders/recog_bin.py +++ b/paddlespeech/s2t/decoders/recog_bin.py @@ -357,7 +357,7 @@ def main(args): if args.num_encs == 1: # Experimental API that supports custom LMs if args.api == "v2": - from deepspeech.decoders.recog import recog_v2 + from paddlespeech.s2t.decoders.recog import recog_v2 recog_v2(args) else: raise ValueError("Only support --api v2") diff --git a/deepspeech/decoders/scorers/__init__.py b/paddlespeech/s2t/decoders/scorers/__init__.py similarity index 100% rename from deepspeech/decoders/scorers/__init__.py rename to paddlespeech/s2t/decoders/scorers/__init__.py diff --git a/deepspeech/decoders/scorers/ctc.py b/paddlespeech/s2t/decoders/scorers/ctc.py similarity index 98% rename from deepspeech/decoders/scorers/ctc.py rename to paddlespeech/s2t/decoders/scorers/ctc.py index 4871d6e12e0bfa86fc157c76829763ed96c4c523..74a5f578dd8d7feb8229a850b458c6b13e12f263 100644 --- a/deepspeech/decoders/scorers/ctc.py +++ b/paddlespeech/s2t/decoders/scorers/ctc.py @@ -28,7 +28,7 @@ class CTCPrefixScorer(BatchPartialScorerInterface): Args: ctc (paddle.nn.Layer): The CTC implementation. - For example, :class:`deepspeech.modules.ctc.CTC` + For example, :class:`paddlespeech.s2t.modules.ctc.CTC` eos (int): The end-of-sequence id. """ diff --git a/deepspeech/decoders/scorers/ctc_prefix_score.py b/paddlespeech/s2t/decoders/scorers/ctc_prefix_score.py similarity index 100% rename from deepspeech/decoders/scorers/ctc_prefix_score.py rename to paddlespeech/s2t/decoders/scorers/ctc_prefix_score.py diff --git a/deepspeech/decoders/scorers/length_bonus.py b/paddlespeech/s2t/decoders/scorers/length_bonus.py similarity index 100% rename from deepspeech/decoders/scorers/length_bonus.py rename to paddlespeech/s2t/decoders/scorers/length_bonus.py diff --git a/deepspeech/decoders/scorers/ngram.py b/paddlespeech/s2t/decoders/scorers/ngram.py similarity index 100% rename from deepspeech/decoders/scorers/ngram.py rename to paddlespeech/s2t/decoders/scorers/ngram.py diff --git a/deepspeech/decoders/scorers/scorer_interface.py b/paddlespeech/s2t/decoders/scorers/scorer_interface.py similarity index 100% rename from deepspeech/decoders/scorers/scorer_interface.py rename to paddlespeech/s2t/decoders/scorers/scorer_interface.py diff --git a/deepspeech/decoders/utils.py b/paddlespeech/s2t/decoders/utils.py similarity index 98% rename from deepspeech/decoders/utils.py rename to paddlespeech/s2t/decoders/utils.py index 3ed9c5da562892ccd52220d9e12d167f693e9226..7dff14c11199d7de05f5c246d9d845aafaf13c68 100644 --- a/deepspeech/decoders/utils.py +++ b/paddlespeech/s2t/decoders/utils.py @@ -13,7 +13,7 @@ # limitations under the License. import numpy as np -from deepspeech.utils.log import Log +from paddlespeech.s2t.utils.log import Log logger = Log(__name__).getlog() __all__ = ["end_detect", "parse_hypothesis", "add_results_to_json"] diff --git a/deepspeech/exps/__init__.py b/paddlespeech/s2t/exps/__init__.py similarity index 69% rename from deepspeech/exps/__init__.py rename to paddlespeech/s2t/exps/__init__.py index 2995301469a051db1185cf430bcd6d77af4609fb..b4d03066fb14bc00a02e6c1fa89d44165ba32145 100644 --- a/deepspeech/exps/__init__.py +++ b/paddlespeech/s2t/exps/__init__.py @@ -11,14 +11,14 @@ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. -from deepspeech.training.trainer import Trainer -from deepspeech.utils.dynamic_import import dynamic_import +from paddlespeech.s2t.training.trainer import Trainer +from paddlespeech.s2t.utils.dynamic_import import dynamic_import model_trainer_alias = { - "ds2": "deepspeech.exp.deepspeech2.model:DeepSpeech2Trainer", - "u2": "deepspeech.exps.u2.model:U2Trainer", - "u2_kaldi": "deepspeech.exps.u2_kaldi.model:U2Trainer", - "u2_st": "deepspeech.exps.u2_st.model:U2STTrainer", + "ds2": "paddlespeech.s2t.exp.deepspeech2.model:DeepSpeech2Trainer", + "u2": "paddlespeech.s2t.exps.u2.model:U2Trainer", + "u2_kaldi": "paddlespeech.s2t.exps.u2_kaldi.model:U2Trainer", + "u2_st": "paddlespeech.s2t.exps.u2_st.model:U2STTrainer", } @@ -39,10 +39,10 @@ def dynamic_import_trainer(module): model_tester_alias = { - "ds2": "deepspeech.exp.deepspeech2.model:DeepSpeech2Tester", - "u2": "deepspeech.exps.u2.model:U2Tester", - "u2_kaldi": "deepspeech.exps.u2_kaldi.model:U2Tester", - "u2_st": "deepspeech.exps.u2_st.model:U2STTester", + "ds2": "paddlespeech.s2t.exp.deepspeech2.model:DeepSpeech2Tester", + "u2": "paddlespeech.s2t.exps.u2.model:U2Tester", + "u2_kaldi": "paddlespeech.s2t.exps.u2_kaldi.model:U2Tester", + "u2_st": "paddlespeech.s2t.exps.u2_st.model:U2STTester", } diff --git a/deepspeech/exps/deepspeech2/__init__.py b/paddlespeech/s2t/exps/deepspeech2/__init__.py similarity index 100% rename from deepspeech/exps/deepspeech2/__init__.py rename to paddlespeech/s2t/exps/deepspeech2/__init__.py diff --git a/deepspeech/exps/deepspeech2/bin/deploy/client.py b/paddlespeech/s2t/exps/deepspeech2/bin/deploy/client.py similarity index 97% rename from deepspeech/exps/deepspeech2/bin/deploy/client.py rename to paddlespeech/s2t/exps/deepspeech2/bin/deploy/client.py index 0a83f8a58d5e7adc65899d3ce90e5220603648f8..f7ed8429b20b8dd717bf1c741a709168d0d5c2c7 100644 --- a/deepspeech/exps/deepspeech2/bin/deploy/client.py +++ b/paddlespeech/s2t/exps/deepspeech2/bin/deploy/client.py @@ -18,7 +18,7 @@ import sys import keyboard import pyaudio -from deepspeech.utils.socket_server import socket_send +from paddlespeech.s2t.utils.socket_server import socket_send parser = argparse.ArgumentParser(description=__doc__) parser.add_argument( diff --git a/deepspeech/exps/deepspeech2/bin/deploy/record.py b/paddlespeech/s2t/exps/deepspeech2/bin/deploy/record.py similarity index 100% rename from deepspeech/exps/deepspeech2/bin/deploy/record.py rename to paddlespeech/s2t/exps/deepspeech2/bin/deploy/record.py diff --git a/deepspeech/exps/deepspeech2/bin/deploy/runtime.py b/paddlespeech/s2t/exps/deepspeech2/bin/deploy/runtime.py similarity index 90% rename from deepspeech/exps/deepspeech2/bin/deploy/runtime.py rename to paddlespeech/s2t/exps/deepspeech2/bin/deploy/runtime.py index 21ffa6bf40cb5fe556a15de87e08848687f7c2fd..7ccb3a6c23f0bfad874bc7720fafc4514c1b971a 100644 --- a/deepspeech/exps/deepspeech2/bin/deploy/runtime.py +++ b/paddlespeech/s2t/exps/deepspeech2/bin/deploy/runtime.py @@ -20,16 +20,16 @@ from paddle.inference import Config from paddle.inference import create_predictor from paddle.io import DataLoader -from deepspeech.exps.deepspeech2.config import get_cfg_defaults -from deepspeech.io.collator import SpeechCollator -from deepspeech.io.dataset import ManifestDataset -from deepspeech.models.ds2 import DeepSpeech2Model -from deepspeech.training.cli import default_argument_parser -from deepspeech.utils.socket_server import AsrRequestHandler -from deepspeech.utils.socket_server import AsrTCPServer -from deepspeech.utils.socket_server import warm_up_test -from deepspeech.utils.utility import add_arguments -from deepspeech.utils.utility import print_arguments +from paddlespeech.s2t.exps.deepspeech2.config import get_cfg_defaults +from paddlespeech.s2t.io.collator import SpeechCollator +from paddlespeech.s2t.io.dataset import ManifestDataset +from paddlespeech.s2t.models.ds2 import DeepSpeech2Model +from paddlespeech.s2t.training.cli import default_argument_parser +from paddlespeech.s2t.utils.socket_server import AsrRequestHandler +from paddlespeech.s2t.utils.socket_server import AsrTCPServer +from paddlespeech.s2t.utils.socket_server import warm_up_test +from paddlespeech.s2t.utils.utility import add_arguments +from paddlespeech.s2t.utils.utility import print_arguments def init_predictor(args): diff --git a/deepspeech/exps/deepspeech2/bin/deploy/send.py b/paddlespeech/s2t/exps/deepspeech2/bin/deploy/send.py similarity index 96% rename from deepspeech/exps/deepspeech2/bin/deploy/send.py rename to paddlespeech/s2t/exps/deepspeech2/bin/deploy/send.py index ce6c7c8451f366b933aa12e3f2cb658877f9edb1..596e701027c03276f153babdf710b361eb34b882 100644 --- a/deepspeech/exps/deepspeech2/bin/deploy/send.py +++ b/paddlespeech/s2t/exps/deepspeech2/bin/deploy/send.py @@ -15,7 +15,7 @@ import argparse import wave -from deepspeech.utils.socket_server import socket_send +from paddlespeech.s2t.utils.socket_server import socket_send parser = argparse.ArgumentParser(description=__doc__) parser.add_argument( diff --git a/deepspeech/exps/deepspeech2/bin/deploy/server.py b/paddlespeech/s2t/exps/deepspeech2/bin/deploy/server.py similarity index 87% rename from deepspeech/exps/deepspeech2/bin/deploy/server.py rename to paddlespeech/s2t/exps/deepspeech2/bin/deploy/server.py index 583e909502d03c11e1cf843ea5df48f35ff730b9..5c6eee3f6cf647bda222fc92442dec9d40ae0b0d 100644 --- a/deepspeech/exps/deepspeech2/bin/deploy/server.py +++ b/paddlespeech/s2t/exps/deepspeech2/bin/deploy/server.py @@ -18,16 +18,16 @@ import numpy as np import paddle from paddle.io import DataLoader -from deepspeech.exps.deepspeech2.config import get_cfg_defaults -from deepspeech.io.collator import SpeechCollator -from deepspeech.io.dataset import ManifestDataset -from deepspeech.models.ds2 import DeepSpeech2Model -from deepspeech.training.cli import default_argument_parser -from deepspeech.utils.socket_server import AsrRequestHandler -from deepspeech.utils.socket_server import AsrTCPServer -from deepspeech.utils.socket_server import warm_up_test -from deepspeech.utils.utility import add_arguments -from deepspeech.utils.utility import print_arguments +from paddlespeech.s2t.exps.deepspeech2.config import get_cfg_defaults +from paddlespeech.s2t.io.collator import SpeechCollator +from paddlespeech.s2t.io.dataset import ManifestDataset +from paddlespeech.s2t.models.ds2 import DeepSpeech2Model +from paddlespeech.s2t.training.cli import default_argument_parser +from paddlespeech.s2t.utils.socket_server import AsrRequestHandler +from paddlespeech.s2t.utils.socket_server import AsrTCPServer +from paddlespeech.s2t.utils.socket_server import warm_up_test +from paddlespeech.s2t.utils.utility import add_arguments +from paddlespeech.s2t.utils.utility import print_arguments def start_server(config, args): diff --git a/deepspeech/exps/deepspeech2/bin/export.py b/paddlespeech/s2t/exps/deepspeech2/bin/export.py similarity index 85% rename from deepspeech/exps/deepspeech2/bin/export.py rename to paddlespeech/s2t/exps/deepspeech2/bin/export.py index 5f89e9042a7cd26aac32871159f25753e4f5248d..66042e8431c0079c8ca630c6eeb2ea83435a0210 100644 --- a/deepspeech/exps/deepspeech2/bin/export.py +++ b/paddlespeech/s2t/exps/deepspeech2/bin/export.py @@ -12,10 +12,10 @@ # See the License for the specific language governing permissions and # limitations under the License. """Export for DeepSpeech2 model.""" -from deepspeech.exps.deepspeech2.config import get_cfg_defaults -from deepspeech.exps.deepspeech2.model import DeepSpeech2Tester as Tester -from deepspeech.training.cli import default_argument_parser -from deepspeech.utils.utility import print_arguments +from paddlespeech.s2t.exps.deepspeech2.config import get_cfg_defaults +from paddlespeech.s2t.exps.deepspeech2.model import DeepSpeech2Tester as Tester +from paddlespeech.s2t.training.cli import default_argument_parser +from paddlespeech.s2t.utils.utility import print_arguments def main_sp(config, args): diff --git a/deepspeech/exps/deepspeech2/bin/test.py b/paddlespeech/s2t/exps/deepspeech2/bin/test.py similarity index 85% rename from deepspeech/exps/deepspeech2/bin/test.py rename to paddlespeech/s2t/exps/deepspeech2/bin/test.py index 6181ff902943c8d10378aac12082a48e8f9f61f1..f52615faefedbef1b40abf1b94ab840f23907fe3 100644 --- a/deepspeech/exps/deepspeech2/bin/test.py +++ b/paddlespeech/s2t/exps/deepspeech2/bin/test.py @@ -12,10 +12,10 @@ # See the License for the specific language governing permissions and # limitations under the License. """Evaluation for DeepSpeech2 model.""" -from deepspeech.exps.deepspeech2.config import get_cfg_defaults -from deepspeech.exps.deepspeech2.model import DeepSpeech2Tester as Tester -from deepspeech.training.cli import default_argument_parser -from deepspeech.utils.utility import print_arguments +from paddlespeech.s2t.exps.deepspeech2.config import get_cfg_defaults +from paddlespeech.s2t.exps.deepspeech2.model import DeepSpeech2Tester as Tester +from paddlespeech.s2t.training.cli import default_argument_parser +from paddlespeech.s2t.utils.utility import print_arguments def main_sp(config, args): diff --git a/deepspeech/exps/deepspeech2/bin/test_export.py b/paddlespeech/s2t/exps/deepspeech2/bin/test_export.py similarity index 85% rename from deepspeech/exps/deepspeech2/bin/test_export.py rename to paddlespeech/s2t/exps/deepspeech2/bin/test_export.py index 77bb0025afd12e287a6f5f63d22d0a7a4c5f08dd..b6b34d0835808d9e8e9692ed238980956263bb2c 100644 --- a/deepspeech/exps/deepspeech2/bin/test_export.py +++ b/paddlespeech/s2t/exps/deepspeech2/bin/test_export.py @@ -12,10 +12,10 @@ # See the License for the specific language governing permissions and # limitations under the License. """Evaluation for DeepSpeech2 model.""" -from deepspeech.exps.deepspeech2.config import get_cfg_defaults -from deepspeech.exps.deepspeech2.model import DeepSpeech2ExportTester as ExportTester -from deepspeech.training.cli import default_argument_parser -from deepspeech.utils.utility import print_arguments +from paddlespeech.s2t.exps.deepspeech2.config import get_cfg_defaults +from paddlespeech.s2t.exps.deepspeech2.model import DeepSpeech2ExportTester as ExportTester +from paddlespeech.s2t.training.cli import default_argument_parser +from paddlespeech.s2t.utils.utility import print_arguments def main_sp(config, args): diff --git a/deepspeech/exps/deepspeech2/bin/test_hub.py b/paddlespeech/s2t/exps/deepspeech2/bin/test_hub.py similarity index 90% rename from deepspeech/exps/deepspeech2/bin/test_hub.py rename to paddlespeech/s2t/exps/deepspeech2/bin/test_hub.py index 1203991de8254920321669350e1fae1530952acb..8ab8fea2fc41422e38c8c4decb961120b0e2f6cc 100644 --- a/deepspeech/exps/deepspeech2/bin/test_hub.py +++ b/paddlespeech/s2t/exps/deepspeech2/bin/test_hub.py @@ -19,17 +19,17 @@ from pathlib import Path import paddle import soundfile -from deepspeech.exps.deepspeech2.config import get_cfg_defaults -from deepspeech.frontend.featurizer.text_featurizer import TextFeaturizer -from deepspeech.io.collator import SpeechCollator -from deepspeech.models.ds2 import DeepSpeech2Model -from deepspeech.models.ds2_online import DeepSpeech2ModelOnline -from deepspeech.training.cli import default_argument_parser -from deepspeech.utils import mp_tools -from deepspeech.utils.checkpoint import Checkpoint -from deepspeech.utils.log import Log -from deepspeech.utils.utility import print_arguments -from deepspeech.utils.utility import UpdateConfig +from paddlespeech.s2t.exps.deepspeech2.config import get_cfg_defaults +from paddlespeech.s2t.frontend.featurizer.text_featurizer import TextFeaturizer +from paddlespeech.s2t.io.collator import SpeechCollator +from paddlespeech.s2t.models.ds2 import DeepSpeech2Model +from paddlespeech.s2t.models.ds2_online import DeepSpeech2ModelOnline +from paddlespeech.s2t.training.cli import default_argument_parser +from paddlespeech.s2t.utils import mp_tools +from paddlespeech.s2t.utils.checkpoint import Checkpoint +from paddlespeech.s2t.utils.log import Log +from paddlespeech.s2t.utils.utility import print_arguments +from paddlespeech.s2t.utils.utility import UpdateConfig logger = Log(__name__).getlog() diff --git a/deepspeech/exps/deepspeech2/bin/train.py b/paddlespeech/s2t/exps/deepspeech2/bin/train.py similarity index 85% rename from deepspeech/exps/deepspeech2/bin/train.py rename to paddlespeech/s2t/exps/deepspeech2/bin/train.py index 02aefe3df29dee8036466e50a299117e08464015..d9b610a06f787b197003f1ecd774753f518662ab 100644 --- a/deepspeech/exps/deepspeech2/bin/train.py +++ b/paddlespeech/s2t/exps/deepspeech2/bin/train.py @@ -14,10 +14,10 @@ """Trainer for DeepSpeech2 model.""" from paddle import distributed as dist -from deepspeech.exps.deepspeech2.config import get_cfg_defaults -from deepspeech.exps.deepspeech2.model import DeepSpeech2Trainer as Trainer -from deepspeech.training.cli import default_argument_parser -from deepspeech.utils.utility import print_arguments +from paddlespeech.s2t.exps.deepspeech2.config import get_cfg_defaults +from paddlespeech.s2t.exps.deepspeech2.model import DeepSpeech2Trainer as Trainer +from paddlespeech.s2t.training.cli import default_argument_parser +from paddlespeech.s2t.utils.utility import print_arguments def main_sp(config, args): diff --git a/deepspeech/exps/deepspeech2/config.py b/paddlespeech/s2t/exps/deepspeech2/config.py similarity index 77% rename from deepspeech/exps/deepspeech2/config.py rename to paddlespeech/s2t/exps/deepspeech2/config.py index 38b7d0e4d9e499ad7f6bfd3a7a13c66b253d3be6..58dc05ff6cbb5dbb1bcc0c89c22dad85b0dfe654 100644 --- a/deepspeech/exps/deepspeech2/config.py +++ b/paddlespeech/s2t/exps/deepspeech2/config.py @@ -13,12 +13,12 @@ # limitations under the License. from yacs.config import CfgNode -from deepspeech.exps.deepspeech2.model import DeepSpeech2Tester -from deepspeech.exps.deepspeech2.model import DeepSpeech2Trainer -from deepspeech.io.collator import SpeechCollator -from deepspeech.io.dataset import ManifestDataset -from deepspeech.models.ds2 import DeepSpeech2Model -from deepspeech.models.ds2_online import DeepSpeech2ModelOnline +from paddlespeech.s2t.exps.deepspeech2.model import DeepSpeech2Tester +from paddlespeech.s2t.exps.deepspeech2.model import DeepSpeech2Trainer +from paddlespeech.s2t.io.collator import SpeechCollator +from paddlespeech.s2t.io.dataset import ManifestDataset +from paddlespeech.s2t.models.ds2 import DeepSpeech2Model +from paddlespeech.s2t.models.ds2_online import DeepSpeech2ModelOnline def get_cfg_defaults(model_type='offline'): diff --git a/deepspeech/exps/deepspeech2/model.py b/paddlespeech/s2t/exps/deepspeech2/model.py similarity index 95% rename from deepspeech/exps/deepspeech2/model.py rename to paddlespeech/s2t/exps/deepspeech2/model.py index 152811773aa8ef926706c0f7889d6dab5dba1243..683fab146748009b3011c0d30d0c77ec1a36b8c7 100644 --- a/deepspeech/exps/deepspeech2/model.py +++ b/paddlespeech/s2t/exps/deepspeech2/model.py @@ -26,25 +26,25 @@ from paddle import inference from paddle.io import DataLoader from yacs.config import CfgNode -from deepspeech.frontend.featurizer.text_featurizer import TextFeaturizer -from deepspeech.io.collator import SpeechCollator -from deepspeech.io.dataset import ManifestDataset -from deepspeech.io.sampler import SortagradBatchSampler -from deepspeech.io.sampler import SortagradDistributedBatchSampler -from deepspeech.models.ds2 import DeepSpeech2InferModel -from deepspeech.models.ds2 import DeepSpeech2Model -from deepspeech.models.ds2_online import DeepSpeech2InferModelOnline -from deepspeech.models.ds2_online import DeepSpeech2ModelOnline -from deepspeech.training.gradclip import ClipGradByGlobalNormWithLog -from deepspeech.training.reporter import report -from deepspeech.training.timer import Timer -from deepspeech.training.trainer import Trainer -from deepspeech.utils import error_rate -from deepspeech.utils import layer_tools -from deepspeech.utils import mp_tools -from deepspeech.utils.log import Autolog -from deepspeech.utils.log import Log -from deepspeech.utils.utility import UpdateConfig +from paddlespeech.s2t.frontend.featurizer.text_featurizer import TextFeaturizer +from paddlespeech.s2t.io.collator import SpeechCollator +from paddlespeech.s2t.io.dataset import ManifestDataset +from paddlespeech.s2t.io.sampler import SortagradBatchSampler +from paddlespeech.s2t.io.sampler import SortagradDistributedBatchSampler +from paddlespeech.s2t.models.ds2 import DeepSpeech2InferModel +from paddlespeech.s2t.models.ds2 import DeepSpeech2Model +from paddlespeech.s2t.models.ds2_online import DeepSpeech2InferModelOnline +from paddlespeech.s2t.models.ds2_online import DeepSpeech2ModelOnline +from paddlespeech.s2t.training.gradclip import ClipGradByGlobalNormWithLog +from paddlespeech.s2t.training.reporter import report +from paddlespeech.s2t.training.timer import Timer +from paddlespeech.s2t.training.trainer import Trainer +from paddlespeech.s2t.utils import error_rate +from paddlespeech.s2t.utils import layer_tools +from paddlespeech.s2t.utils import mp_tools +from paddlespeech.s2t.utils.log import Autolog +from paddlespeech.s2t.utils.log import Log +from paddlespeech.s2t.utils.utility import UpdateConfig logger = Log(__name__).getlog() diff --git a/deepspeech/exps/lm/transformer/__init__.py b/paddlespeech/s2t/exps/lm/transformer/__init__.py similarity index 100% rename from deepspeech/exps/lm/transformer/__init__.py rename to paddlespeech/s2t/exps/lm/transformer/__init__.py diff --git a/deepspeech/exps/lm/transformer/bin/cacu_perplexity.py b/paddlespeech/s2t/exps/lm/transformer/bin/cacu_perplexity.py similarity index 96% rename from deepspeech/exps/lm/transformer/bin/cacu_perplexity.py rename to paddlespeech/s2t/exps/lm/transformer/bin/cacu_perplexity.py index 29a880f88fb308888a406d09623b65d6298ec68f..f3e4d2099f31f30ca30adbd9b37cb93e4f7b965e 100644 --- a/deepspeech/exps/lm/transformer/bin/cacu_perplexity.py +++ b/paddlespeech/s2t/exps/lm/transformer/bin/cacu_perplexity.py @@ -74,7 +74,7 @@ def get_parser(): def main(args): parser = get_parser() args = parser.parse_args(args) - from deepspeech.exps.lm.transformer.lm_cacu_perplexity import run_get_perplexity + from paddlespeech.s2t.exps.lm.transformer.lm_cacu_perplexity import run_get_perplexity run_get_perplexity(args) diff --git a/deepspeech/exps/lm/transformer/lm_cacu_perplexity.py b/paddlespeech/s2t/exps/lm/transformer/lm_cacu_perplexity.py similarity index 94% rename from deepspeech/exps/lm/transformer/lm_cacu_perplexity.py rename to paddlespeech/s2t/exps/lm/transformer/lm_cacu_perplexity.py index b63bcd08b9aff1944d759b6afc099abfbc532b8e..ab0ec8f0e899516d56e8a4847315efe428a01df5 100644 --- a/deepspeech/exps/lm/transformer/lm_cacu_perplexity.py +++ b/paddlespeech/s2t/exps/lm/transformer/lm_cacu_perplexity.py @@ -19,10 +19,10 @@ import paddle from paddle.io import DataLoader from yacs.config import CfgNode -from deepspeech.io.collator import TextCollatorSpm -from deepspeech.io.dataset import TextDataset -from deepspeech.models.lm_interface import dynamic_import_lm -from deepspeech.utils.log import Log +from paddlespeech.s2t.io.collator import TextCollatorSpm +from paddlespeech.s2t.io.dataset import TextDataset +from paddlespeech.s2t.models.lm_interface import dynamic_import_lm +from paddlespeech.s2t.utils.log import Log logger = Log(__name__).getlog() diff --git a/deepspeech/exps/u2/__init__.py b/paddlespeech/s2t/exps/u2/__init__.py similarity index 100% rename from deepspeech/exps/u2/__init__.py rename to paddlespeech/s2t/exps/u2/__init__.py diff --git a/deepspeech/exps/u2/bin/alignment.py b/paddlespeech/s2t/exps/u2/bin/alignment.py similarity index 85% rename from deepspeech/exps/u2/bin/alignment.py rename to paddlespeech/s2t/exps/u2/bin/alignment.py index 91aac1a8c57bfca2d3d9d4d8066c7e4574f3b4d9..df95baeb9982ecacc9c249f7c9528b8193e24428 100644 --- a/deepspeech/exps/u2/bin/alignment.py +++ b/paddlespeech/s2t/exps/u2/bin/alignment.py @@ -12,10 +12,10 @@ # See the License for the specific language governing permissions and # limitations under the License. """Alignment for U2 model.""" -from deepspeech.exps.u2.config import get_cfg_defaults -from deepspeech.exps.u2.model import U2Tester as Tester -from deepspeech.training.cli import default_argument_parser -from deepspeech.utils.utility import print_arguments +from paddlespeech.s2t.exps.u2.config import get_cfg_defaults +from paddlespeech.s2t.exps.u2.model import U2Tester as Tester +from paddlespeech.s2t.training.cli import default_argument_parser +from paddlespeech.s2t.utils.utility import print_arguments def main_sp(config, args): diff --git a/deepspeech/exps/u2/bin/export.py b/paddlespeech/s2t/exps/u2/bin/export.py similarity index 85% rename from deepspeech/exps/u2/bin/export.py rename to paddlespeech/s2t/exps/u2/bin/export.py index 89acbf70d84afa69f0c9d9961f9c352c2ce38ebf..44fc7c3e56a1107e09154f2646576d20065b908a 100644 --- a/deepspeech/exps/u2/bin/export.py +++ b/paddlespeech/s2t/exps/u2/bin/export.py @@ -12,10 +12,10 @@ # See the License for the specific language governing permissions and # limitations under the License. """Export for U2 model.""" -from deepspeech.exps.u2.config import get_cfg_defaults -from deepspeech.exps.u2.model import U2Tester as Tester -from deepspeech.training.cli import default_argument_parser -from deepspeech.utils.utility import print_arguments +from paddlespeech.s2t.exps.u2.config import get_cfg_defaults +from paddlespeech.s2t.exps.u2.model import U2Tester as Tester +from paddlespeech.s2t.training.cli import default_argument_parser +from paddlespeech.s2t.utils.utility import print_arguments def main_sp(config, args): diff --git a/deepspeech/exps/u2/bin/test.py b/paddlespeech/s2t/exps/u2/bin/test.py similarity index 86% rename from deepspeech/exps/u2/bin/test.py rename to paddlespeech/s2t/exps/u2/bin/test.py index 3068f1c7aed9c107fe1c3b0800ddacf95a0064a6..48b0670d5fe6d6ceeff594bcb979afe97d9de57e 100644 --- a/deepspeech/exps/u2/bin/test.py +++ b/paddlespeech/s2t/exps/u2/bin/test.py @@ -14,10 +14,10 @@ """Evaluation for U2 model.""" import cProfile -from deepspeech.exps.u2.config import get_cfg_defaults -from deepspeech.exps.u2.model import U2Tester as Tester -from deepspeech.training.cli import default_argument_parser -from deepspeech.utils.utility import print_arguments +from paddlespeech.s2t.exps.u2.config import get_cfg_defaults +from paddlespeech.s2t.exps.u2.model import U2Tester as Tester +from paddlespeech.s2t.training.cli import default_argument_parser +from paddlespeech.s2t.utils.utility import print_arguments # TODO(hui zhang): dynamic load diff --git a/deepspeech/exps/u2/bin/test_hub.py b/paddlespeech/s2t/exps/u2/bin/test_hub.py similarity index 90% rename from deepspeech/exps/u2/bin/test_hub.py rename to paddlespeech/s2t/exps/u2/bin/test_hub.py index 8c006ebea8b5d2915260b5ba53eacd51258cb545..55a61d5c5b5868c46c91c8becc586edcf35906c9 100644 --- a/deepspeech/exps/u2/bin/test_hub.py +++ b/paddlespeech/s2t/exps/u2/bin/test_hub.py @@ -19,17 +19,17 @@ import sys import paddle import soundfile -from deepspeech.exps.u2.config import get_cfg_defaults -from deepspeech.frontend.featurizer.text_featurizer import TextFeaturizer -from deepspeech.io.collator import SpeechCollator -from deepspeech.models.u2 import U2Model -from deepspeech.training.cli import default_argument_parser -from deepspeech.training.trainer import Trainer -from deepspeech.utils import layer_tools -from deepspeech.utils import mp_tools -from deepspeech.utils.log import Log -from deepspeech.utils.utility import print_arguments -from deepspeech.utils.utility import UpdateConfig +from paddlespeech.s2t.exps.u2.config import get_cfg_defaults +from paddlespeech.s2t.frontend.featurizer.text_featurizer import TextFeaturizer +from paddlespeech.s2t.io.collator import SpeechCollator +from paddlespeech.s2t.models.u2 import U2Model +from paddlespeech.s2t.training.cli import default_argument_parser +from paddlespeech.s2t.training.trainer import Trainer +from paddlespeech.s2t.utils import layer_tools +from paddlespeech.s2t.utils import mp_tools +from paddlespeech.s2t.utils.log import Log +from paddlespeech.s2t.utils.utility import print_arguments +from paddlespeech.s2t.utils.utility import UpdateConfig logger = Log(__name__).getlog() # TODO(hui zhang): dynamic load diff --git a/deepspeech/exps/u2/bin/train.py b/paddlespeech/s2t/exps/u2/bin/train.py similarity index 83% rename from deepspeech/exps/u2/bin/train.py rename to paddlespeech/s2t/exps/u2/bin/train.py index 17fb08a6c41202da97fec48911ba714942cf29c7..127db521addddc55f362510a47dcdced3cce3367 100644 --- a/deepspeech/exps/u2/bin/train.py +++ b/paddlespeech/s2t/exps/u2/bin/train.py @@ -17,12 +17,12 @@ import os from paddle import distributed as dist -from deepspeech.exps.u2.config import get_cfg_defaults -from deepspeech.exps.u2.model import U2Trainer as Trainer -from deepspeech.training.cli import default_argument_parser -from deepspeech.utils.utility import print_arguments +from paddlespeech.s2t.exps.u2.config import get_cfg_defaults +from paddlespeech.s2t.exps.u2.model import U2Trainer as Trainer +from paddlespeech.s2t.training.cli import default_argument_parser +from paddlespeech.s2t.utils.utility import print_arguments -# from deepspeech.exps.u2.trainer import U2Trainer as Trainer +# from paddlespeech.s2t.exps.u2.trainer import U2Trainer as Trainer def main_sp(config, args): diff --git a/deepspeech/exps/u2/config.py b/paddlespeech/s2t/exps/u2/config.py similarity index 80% rename from deepspeech/exps/u2/config.py rename to paddlespeech/s2t/exps/u2/config.py index 4ec7bd1908715bb583987bd1e2aae2165eadc683..898b0bb2504b96d7a9cdb89f8383ba4961a0247f 100644 --- a/deepspeech/exps/u2/config.py +++ b/paddlespeech/s2t/exps/u2/config.py @@ -13,11 +13,11 @@ # limitations under the License. from yacs.config import CfgNode -from deepspeech.exps.u2.model import U2Tester -from deepspeech.exps.u2.model import U2Trainer -from deepspeech.io.collator import SpeechCollator -from deepspeech.io.dataset import ManifestDataset -from deepspeech.models.u2 import U2Model +from paddlespeech.s2t.exps.u2.model import U2Tester +from paddlespeech.s2t.exps.u2.model import U2Trainer +from paddlespeech.s2t.io.collator import SpeechCollator +from paddlespeech.s2t.io.dataset import ManifestDataset +from paddlespeech.s2t.models.u2 import U2Model _C = CfgNode() diff --git a/deepspeech/exps/u2/model.py b/paddlespeech/s2t/exps/u2/model.py similarity index 96% rename from deepspeech/exps/u2/model.py rename to paddlespeech/s2t/exps/u2/model.py index e47a59edaf0435578b57edfc37222acca7df2de2..67441fae55068fd2a2d5288de82d9e2aad40b47c 100644 --- a/deepspeech/exps/u2/model.py +++ b/paddlespeech/s2t/exps/u2/model.py @@ -27,23 +27,23 @@ from paddle import distributed as dist from paddle.io import DataLoader from yacs.config import CfgNode -from deepspeech.io.collator import SpeechCollator -from deepspeech.io.dataset import ManifestDataset -from deepspeech.io.sampler import SortagradBatchSampler -from deepspeech.io.sampler import SortagradDistributedBatchSampler -from deepspeech.models.u2 import U2Model -from deepspeech.training.optimizer import OptimizerFactory -from deepspeech.training.reporter import ObsScope -from deepspeech.training.reporter import report -from deepspeech.training.scheduler import LRSchedulerFactory -from deepspeech.training.timer import Timer -from deepspeech.training.trainer import Trainer -from deepspeech.utils import ctc_utils -from deepspeech.utils import error_rate -from deepspeech.utils import layer_tools -from deepspeech.utils import mp_tools -from deepspeech.utils.log import Log -from deepspeech.utils.utility import UpdateConfig +from paddlespeech.s2t.io.collator import SpeechCollator +from paddlespeech.s2t.io.dataset import ManifestDataset +from paddlespeech.s2t.io.sampler import SortagradBatchSampler +from paddlespeech.s2t.io.sampler import SortagradDistributedBatchSampler +from paddlespeech.s2t.models.u2 import U2Model +from paddlespeech.s2t.training.optimizer import OptimizerFactory +from paddlespeech.s2t.training.reporter import ObsScope +from paddlespeech.s2t.training.reporter import report +from paddlespeech.s2t.training.scheduler import LRSchedulerFactory +from paddlespeech.s2t.training.timer import Timer +from paddlespeech.s2t.training.trainer import Trainer +from paddlespeech.s2t.utils import ctc_utils +from paddlespeech.s2t.utils import error_rate +from paddlespeech.s2t.utils import layer_tools +from paddlespeech.s2t.utils import mp_tools +from paddlespeech.s2t.utils.log import Log +from paddlespeech.s2t.utils.utility import UpdateConfig logger = Log(__name__).getlog() @@ -566,7 +566,7 @@ class U2Tester(U2Trainer): nn.Layer: inference model List[paddle.static.InputSpec]: input spec. """ - from deepspeech.models.u2 import U2InferModel + from paddlespeech.s2t.models.u2 import U2InferModel infer_model = U2InferModel.from_pretrained(self.test_loader, self.config.model.clone(), self.args.checkpoint_path) diff --git a/deepspeech/exps/u2/trainer.py b/paddlespeech/s2t/exps/u2/trainer.py similarity index 88% rename from deepspeech/exps/u2/trainer.py rename to paddlespeech/s2t/exps/u2/trainer.py index 1cb3eccda981019f3d8223449de4c77ac4e5f9e4..22a0a3c58e44fdc55d2269c724d3ebdf898016b3 100644 --- a/deepspeech/exps/u2/trainer.py +++ b/paddlespeech/s2t/exps/u2/trainer.py @@ -16,23 +16,23 @@ import paddle from paddle import distributed as dist from paddle.io import DataLoader -from deepspeech.io.collator import SpeechCollator -from deepspeech.io.dataset import ManifestDataset -from deepspeech.io.sampler import SortagradBatchSampler -from deepspeech.io.sampler import SortagradDistributedBatchSampler -from deepspeech.models.u2 import U2Evaluator -from deepspeech.models.u2 import U2Model -from deepspeech.models.u2 import U2Updater -from deepspeech.training.extensions.snapshot import Snapshot -from deepspeech.training.extensions.visualizer import VisualDL -from deepspeech.training.optimizer import OptimizerFactory -from deepspeech.training.scheduler import LRSchedulerFactory -from deepspeech.training.timer import Timer -from deepspeech.training.trainer import Trainer -from deepspeech.training.updaters.trainer import Trainer as NewTrainer -from deepspeech.utils import layer_tools -from deepspeech.utils.log import Log -from deepspeech.utils.utility import UpdateConfig +from paddlespeech.s2t.io.collator import SpeechCollator +from paddlespeech.s2t.io.dataset import ManifestDataset +from paddlespeech.s2t.io.sampler import SortagradBatchSampler +from paddlespeech.s2t.io.sampler import SortagradDistributedBatchSampler +from paddlespeech.s2t.models.u2 import U2Evaluator +from paddlespeech.s2t.models.u2 import U2Model +from paddlespeech.s2t.models.u2 import U2Updater +from paddlespeech.s2t.training.extensions.snapshot import Snapshot +from paddlespeech.s2t.training.extensions.visualizer import VisualDL +from paddlespeech.s2t.training.optimizer import OptimizerFactory +from paddlespeech.s2t.training.scheduler import LRSchedulerFactory +from paddlespeech.s2t.training.timer import Timer +from paddlespeech.s2t.training.trainer import Trainer +from paddlespeech.s2t.training.updaters.trainer import Trainer as NewTrainer +from paddlespeech.s2t.utils import layer_tools +from paddlespeech.s2t.utils.log import Log +from paddlespeech.s2t.utils.utility import UpdateConfig logger = Log(__name__).getlog() diff --git a/deepspeech/exps/u2_kaldi/__init__.py b/paddlespeech/s2t/exps/u2_kaldi/__init__.py similarity index 100% rename from deepspeech/exps/u2_kaldi/__init__.py rename to paddlespeech/s2t/exps/u2_kaldi/__init__.py diff --git a/deepspeech/exps/u2_kaldi/bin/recog.py b/paddlespeech/s2t/exps/u2_kaldi/bin/recog.py similarity index 92% rename from deepspeech/exps/u2_kaldi/bin/recog.py rename to paddlespeech/s2t/exps/u2_kaldi/bin/recog.py index e94a1ab186e9f57fdc9b8383f0c22dad3c6564a4..37ddd229e43b65d6c8e00ff7c9d5a1262ccbd97a 100644 --- a/deepspeech/exps/u2_kaldi/bin/recog.py +++ b/paddlespeech/s2t/exps/u2_kaldi/bin/recog.py @@ -13,7 +13,7 @@ # limitations under the License. import sys -from deepspeech.decoders.recog_bin import main +from paddlespeech.s2t.decoders.recog_bin import main if __name__ == "__main__": main(sys.argv[1:]) diff --git a/deepspeech/exps/u2_kaldi/bin/test.py b/paddlespeech/s2t/exps/u2_kaldi/bin/test.py similarity index 88% rename from deepspeech/exps/u2_kaldi/bin/test.py rename to paddlespeech/s2t/exps/u2_kaldi/bin/test.py index eb7b0280ba7090e61831f4dce739cf94febd1b2b..67bed349792930a0ae90180650e6de8d1e47502e 100644 --- a/deepspeech/exps/u2_kaldi/bin/test.py +++ b/paddlespeech/s2t/exps/u2_kaldi/bin/test.py @@ -16,13 +16,13 @@ import cProfile from yacs.config import CfgNode -from deepspeech.training.cli import default_argument_parser -from deepspeech.utils.dynamic_import import dynamic_import -from deepspeech.utils.utility import print_arguments +from paddlespeech.s2t.training.cli import default_argument_parser +from paddlespeech.s2t.utils.dynamic_import import dynamic_import +from paddlespeech.s2t.utils.utility import print_arguments model_test_alias = { - "u2": "deepspeech.exps.u2.model:U2Tester", - "u2_kaldi": "deepspeech.exps.u2_kaldi.model:U2Tester", + "u2": "paddlespeech.s2t.exps.u2.model:U2Tester", + "u2_kaldi": "paddlespeech.s2t.exps.u2_kaldi.model:U2Tester", } diff --git a/deepspeech/exps/u2_kaldi/bin/train.py b/paddlespeech/s2t/exps/u2_kaldi/bin/train.py similarity index 85% rename from deepspeech/exps/u2_kaldi/bin/train.py rename to paddlespeech/s2t/exps/u2_kaldi/bin/train.py index d909727f3a5a637f977b2f5569d553db5ff382d1..d3427eec1d08e4a000352949b56b211d96bbb11c 100644 --- a/deepspeech/exps/u2_kaldi/bin/train.py +++ b/paddlespeech/s2t/exps/u2_kaldi/bin/train.py @@ -18,13 +18,13 @@ import os from paddle import distributed as dist from yacs.config import CfgNode -from deepspeech.training.cli import default_argument_parser -from deepspeech.utils.dynamic_import import dynamic_import -from deepspeech.utils.utility import print_arguments +from paddlespeech.s2t.training.cli import default_argument_parser +from paddlespeech.s2t.utils.dynamic_import import dynamic_import +from paddlespeech.s2t.utils.utility import print_arguments model_train_alias = { - "u2": "deepspeech.exps.u2.model:U2Trainer", - "u2_kaldi": "deepspeech.exps.u2_kaldi.model:U2Trainer", + "u2": "paddlespeech.s2t.exps.u2.model:U2Trainer", + "u2_kaldi": "paddlespeech.s2t.exps.u2_kaldi.model:U2Trainer", } diff --git a/deepspeech/exps/u2_kaldi/model.py b/paddlespeech/s2t/exps/u2_kaldi/model.py similarity index 96% rename from deepspeech/exps/u2_kaldi/model.py rename to paddlespeech/s2t/exps/u2_kaldi/model.py index 663c36d8b41f01d73cac5f9cabfee3fe99021144..e37784aa1b1b8fb797cf1a50d1fa2464d065284b 100644 --- a/deepspeech/exps/u2_kaldi/model.py +++ b/paddlespeech/s2t/exps/u2_kaldi/model.py @@ -25,20 +25,20 @@ import paddle from paddle import distributed as dist from yacs.config import CfgNode -from deepspeech.frontend.featurizer import TextFeaturizer -from deepspeech.frontend.utility import load_dict -from deepspeech.io.dataloader import BatchDataLoader -from deepspeech.models.u2 import U2Model -from deepspeech.training.optimizer import OptimizerFactory -from deepspeech.training.scheduler import LRSchedulerFactory -from deepspeech.training.timer import Timer -from deepspeech.training.trainer import Trainer -from deepspeech.utils import ctc_utils -from deepspeech.utils import error_rate -from deepspeech.utils import layer_tools -from deepspeech.utils import mp_tools -from deepspeech.utils.log import Log -from deepspeech.utils.utility import UpdateConfig +from paddlespeech.s2t.frontend.featurizer import TextFeaturizer +from paddlespeech.s2t.frontend.utility import load_dict +from paddlespeech.s2t.io.dataloader import BatchDataLoader +from paddlespeech.s2t.models.u2 import U2Model +from paddlespeech.s2t.training.optimizer import OptimizerFactory +from paddlespeech.s2t.training.scheduler import LRSchedulerFactory +from paddlespeech.s2t.training.timer import Timer +from paddlespeech.s2t.training.trainer import Trainer +from paddlespeech.s2t.utils import ctc_utils +from paddlespeech.s2t.utils import error_rate +from paddlespeech.s2t.utils import layer_tools +from paddlespeech.s2t.utils import mp_tools +from paddlespeech.s2t.utils.log import Log +from paddlespeech.s2t.utils.utility import UpdateConfig logger = Log(__name__).getlog() @@ -539,7 +539,7 @@ class U2Tester(U2Trainer): nn.Layer: inference model List[paddle.static.InputSpec]: input spec. """ - from deepspeech.models.u2 import U2InferModel + from paddlespeech.s2t.models.u2 import U2InferModel infer_model = U2InferModel.from_pretrained(self.test_loader, self.config.model.clone(), self.args.checkpoint_path) diff --git a/deepspeech/exps/u2_st/__init__.py b/paddlespeech/s2t/exps/u2_st/__init__.py similarity index 100% rename from deepspeech/exps/u2_st/__init__.py rename to paddlespeech/s2t/exps/u2_st/__init__.py diff --git a/deepspeech/exps/u2_st/bin/export.py b/paddlespeech/s2t/exps/u2_st/bin/export.py similarity index 84% rename from deepspeech/exps/u2_st/bin/export.py rename to paddlespeech/s2t/exps/u2_st/bin/export.py index 2486f4c22aba29dac09156b28a537ca50db1baeb..69d9718f89e1c15354419f4f7f4e102cad6d30d0 100644 --- a/deepspeech/exps/u2_st/bin/export.py +++ b/paddlespeech/s2t/exps/u2_st/bin/export.py @@ -12,10 +12,10 @@ # See the License for the specific language governing permissions and # limitations under the License. """Export for U2 model.""" -from deepspeech.exps.u2_st.config import get_cfg_defaults -from deepspeech.exps.u2_st.model import U2STTester as Tester -from deepspeech.training.cli import default_argument_parser -from deepspeech.utils.utility import print_arguments +from paddlespeech.s2t.exps.u2_st.config import get_cfg_defaults +from paddlespeech.s2t.exps.u2_st.model import U2STTester as Tester +from paddlespeech.s2t.training.cli import default_argument_parser +from paddlespeech.s2t.utils.utility import print_arguments def main_sp(config, args): diff --git a/deepspeech/exps/u2_st/bin/test.py b/paddlespeech/s2t/exps/u2_st/bin/test.py similarity index 86% rename from deepspeech/exps/u2_st/bin/test.py rename to paddlespeech/s2t/exps/u2_st/bin/test.py index 3d51b60e0d31646804e614c18d930a91d823edbc..93c2fee0acf5caef52914f6fcaaba735a88afaf7 100644 --- a/deepspeech/exps/u2_st/bin/test.py +++ b/paddlespeech/s2t/exps/u2_st/bin/test.py @@ -14,10 +14,10 @@ """Evaluation for U2 model.""" import cProfile -from deepspeech.exps.u2_st.config import get_cfg_defaults -from deepspeech.exps.u2_st.model import U2STTester as Tester -from deepspeech.training.cli import default_argument_parser -from deepspeech.utils.utility import print_arguments +from paddlespeech.s2t.exps.u2_st.config import get_cfg_defaults +from paddlespeech.s2t.exps.u2_st.model import U2STTester as Tester +from paddlespeech.s2t.training.cli import default_argument_parser +from paddlespeech.s2t.utils.utility import print_arguments # TODO(hui zhang): dynamic load diff --git a/deepspeech/exps/u2_st/bin/train.py b/paddlespeech/s2t/exps/u2_st/bin/train.py similarity index 86% rename from deepspeech/exps/u2_st/bin/train.py rename to paddlespeech/s2t/exps/u2_st/bin/train.py index 1e6a746b848ed7e387aec91217c96640e628a39e..3d823cc44d4a5c790ed60f85d90dfc8ca0460409 100644 --- a/deepspeech/exps/u2_st/bin/train.py +++ b/paddlespeech/s2t/exps/u2_st/bin/train.py @@ -17,10 +17,10 @@ import os from paddle import distributed as dist -from deepspeech.exps.u2_st.config import get_cfg_defaults -from deepspeech.exps.u2_st.model import U2STTrainer as Trainer -from deepspeech.training.cli import default_argument_parser -from deepspeech.utils.utility import print_arguments +from paddlespeech.s2t.exps.u2_st.config import get_cfg_defaults +from paddlespeech.s2t.exps.u2_st.model import U2STTrainer as Trainer +from paddlespeech.s2t.training.cli import default_argument_parser +from paddlespeech.s2t.utils.utility import print_arguments def main_sp(config, args): diff --git a/deepspeech/exps/u2_st/config.py b/paddlespeech/s2t/exps/u2_st/config.py similarity index 80% rename from deepspeech/exps/u2_st/config.py rename to paddlespeech/s2t/exps/u2_st/config.py index 818b0e25e11f1cad83975d67f320b73d65cdec54..a48f9106a8ddaa14c85e1f0c8ed450d27e931d11 100644 --- a/deepspeech/exps/u2_st/config.py +++ b/paddlespeech/s2t/exps/u2_st/config.py @@ -13,11 +13,11 @@ # limitations under the License. from yacs.config import CfgNode -from deepspeech.exps.u2_st.model import U2STTester -from deepspeech.exps.u2_st.model import U2STTrainer -from deepspeech.io.collator import SpeechCollator -from deepspeech.io.dataset import ManifestDataset -from deepspeech.models.u2_st import U2STModel +from paddlespeech.s2t.exps.u2_st.model import U2STTester +from paddlespeech.s2t.exps.u2_st.model import U2STTrainer +from paddlespeech.s2t.io.collator import SpeechCollator +from paddlespeech.s2t.io.dataset import ManifestDataset +from paddlespeech.s2t.models.u2_st import U2STModel _C = CfgNode() diff --git a/deepspeech/exps/u2_st/model.py b/paddlespeech/s2t/exps/u2_st/model.py similarity index 96% rename from deepspeech/exps/u2_st/model.py rename to paddlespeech/s2t/exps/u2_st/model.py index 1f638e64c082f8e8bb7bd9fc8c4be7a2b53f529d..f458216e387411ff151bda4ff326834eef7ac1b7 100644 --- a/deepspeech/exps/u2_st/model.py +++ b/paddlespeech/s2t/exps/u2_st/model.py @@ -26,22 +26,22 @@ from paddle import distributed as dist from paddle.io import DataLoader from yacs.config import CfgNode -from deepspeech.io.collator import SpeechCollator -from deepspeech.io.collator import TripletSpeechCollator -from deepspeech.io.dataset import ManifestDataset -from deepspeech.io.sampler import SortagradBatchSampler -from deepspeech.io.sampler import SortagradDistributedBatchSampler -from deepspeech.models.u2_st import U2STModel -from deepspeech.training.gradclip import ClipGradByGlobalNormWithLog -from deepspeech.training.scheduler import WarmupLR -from deepspeech.training.timer import Timer -from deepspeech.training.trainer import Trainer -from deepspeech.utils import bleu_score -from deepspeech.utils import ctc_utils -from deepspeech.utils import layer_tools -from deepspeech.utils import mp_tools -from deepspeech.utils.log import Log -from deepspeech.utils.utility import UpdateConfig +from paddlespeech.s2t.io.collator import SpeechCollator +from paddlespeech.s2t.io.collator import TripletSpeechCollator +from paddlespeech.s2t.io.dataset import ManifestDataset +from paddlespeech.s2t.io.sampler import SortagradBatchSampler +from paddlespeech.s2t.io.sampler import SortagradDistributedBatchSampler +from paddlespeech.s2t.models.u2_st import U2STModel +from paddlespeech.s2t.training.gradclip import ClipGradByGlobalNormWithLog +from paddlespeech.s2t.training.scheduler import WarmupLR +from paddlespeech.s2t.training.timer import Timer +from paddlespeech.s2t.training.trainer import Trainer +from paddlespeech.s2t.utils import bleu_score +from paddlespeech.s2t.utils import ctc_utils +from paddlespeech.s2t.utils import layer_tools +from paddlespeech.s2t.utils import mp_tools +from paddlespeech.s2t.utils.log import Log +from paddlespeech.s2t.utils.utility import UpdateConfig logger = Log(__name__).getlog() @@ -555,7 +555,7 @@ class U2STTester(U2STTrainer): nn.Layer: inference model List[paddle.static.InputSpec]: input spec. """ - from deepspeech.models.u2 import U2InferModel + from paddlespeech.s2t.models.u2 import U2InferModel infer_model = U2InferModel.from_pretrained(self.test_loader, self.config.model.clone(), self.args.checkpoint_path) diff --git a/deepspeech/frontend/__init__.py b/paddlespeech/s2t/frontend/__init__.py similarity index 100% rename from deepspeech/frontend/__init__.py rename to paddlespeech/s2t/frontend/__init__.py diff --git a/deepspeech/frontend/audio.py b/paddlespeech/s2t/frontend/audio.py similarity index 100% rename from deepspeech/frontend/audio.py rename to paddlespeech/s2t/frontend/audio.py diff --git a/deepspeech/frontend/augmentor/__init__.py b/paddlespeech/s2t/frontend/augmentor/__init__.py similarity index 100% rename from deepspeech/frontend/augmentor/__init__.py rename to paddlespeech/s2t/frontend/augmentor/__init__.py diff --git a/deepspeech/frontend/augmentor/augmentation.py b/paddlespeech/s2t/frontend/augmentor/augmentation.py similarity index 89% rename from deepspeech/frontend/augmentor/augmentation.py rename to paddlespeech/s2t/frontend/augmentor/augmentation.py index d2316ab17ef6af9d1706b27431d45a36d1a8cb1e..4c5ca4fe630bcccbe4f41b869b9039f219857e89 100644 --- a/deepspeech/frontend/augmentor/augmentation.py +++ b/paddlespeech/s2t/frontend/augmentor/augmentation.py @@ -20,23 +20,23 @@ from pprint import pformat import numpy as np -from deepspeech.frontend.augmentor.base import AugmentorBase -from deepspeech.utils.dynamic_import import dynamic_import -from deepspeech.utils.log import Log +from paddlespeech.s2t.frontend.augmentor.base import AugmentorBase +from paddlespeech.s2t.utils.dynamic_import import dynamic_import +from paddlespeech.s2t.utils.log import Log logger = Log(__name__).getlog() __all__ = ["AugmentationPipeline"] import_alias = dict( - volume="deepspeech.frontend.augmentor.impulse_response:VolumePerturbAugmentor", - shift="deepspeech.frontend.augmentor.shift_perturb:ShiftPerturbAugmentor", - speed="deepspeech.frontend.augmentor.speed_perturb:SpeedPerturbAugmentor", - resample="deepspeech.frontend.augmentor.resample:ResampleAugmentor", - bayesian_normal="deepspeech.frontend.augmentor.online_bayesian_normalization:OnlineBayesianNormalizationAugmentor", - noise="deepspeech.frontend.augmentor.noise_perturb:NoisePerturbAugmentor", - impulse="deepspeech.frontend.augmentor.impulse_response:ImpulseResponseAugmentor", - specaug="deepspeech.frontend.augmentor.spec_augment:SpecAugmentor", ) + volume="paddlespeech.s2t.frontend.augmentor.impulse_response:VolumePerturbAugmentor", + shift="paddlespeech.s2t.frontend.augmentor.shift_perturb:ShiftPerturbAugmentor", + speed="paddlespeech.s2t.frontend.augmentor.speed_perturb:SpeedPerturbAugmentor", + resample="paddlespeech.s2t.frontend.augmentor.resample:ResampleAugmentor", + bayesian_normal="paddlespeech.s2t.frontend.augmentor.online_bayesian_normalization:OnlineBayesianNormalizationAugmentor", + noise="paddlespeech.s2t.frontend.augmentor.noise_perturb:NoisePerturbAugmentor", + impulse="paddlespeech.s2t.frontend.augmentor.impulse_response:ImpulseResponseAugmentor", + specaug="paddlespeech.s2t.frontend.augmentor.spec_augment:SpecAugmentor", ) class AugmentationPipeline(): diff --git a/deepspeech/frontend/augmentor/base.py b/paddlespeech/s2t/frontend/augmentor/base.py similarity index 100% rename from deepspeech/frontend/augmentor/base.py rename to paddlespeech/s2t/frontend/augmentor/base.py diff --git a/deepspeech/frontend/augmentor/impulse_response.py b/paddlespeech/s2t/frontend/augmentor/impulse_response.py similarity index 90% rename from deepspeech/frontend/augmentor/impulse_response.py rename to paddlespeech/s2t/frontend/augmentor/impulse_response.py index 818251ed8c82dfc21547fea06ae21ee05c7c8d38..6cc9c0d43991cd3f6141916ca5778485ce49dec5 100644 --- a/deepspeech/frontend/augmentor/impulse_response.py +++ b/paddlespeech/s2t/frontend/augmentor/impulse_response.py @@ -12,9 +12,9 @@ # See the License for the specific language governing permissions and # limitations under the License. """Contains the impulse response augmentation model.""" -from deepspeech.frontend.audio import AudioSegment -from deepspeech.frontend.augmentor.base import AugmentorBase -from deepspeech.frontend.utility import read_manifest +from paddlespeech.s2t.frontend.audio import AudioSegment +from paddlespeech.s2t.frontend.augmentor.base import AugmentorBase +from paddlespeech.s2t.frontend.utility import read_manifest class ImpulseResponseAugmentor(AugmentorBase): diff --git a/deepspeech/frontend/augmentor/noise_perturb.py b/paddlespeech/s2t/frontend/augmentor/noise_perturb.py similarity index 93% rename from deepspeech/frontend/augmentor/noise_perturb.py rename to paddlespeech/s2t/frontend/augmentor/noise_perturb.py index 790b0c39682933c1feb2c6fab90ea0c2e8d189c6..9d6da1a8f34818546ebc579efb4cb7a49cb559e5 100644 --- a/deepspeech/frontend/augmentor/noise_perturb.py +++ b/paddlespeech/s2t/frontend/augmentor/noise_perturb.py @@ -12,9 +12,9 @@ # See the License for the specific language governing permissions and # limitations under the License. """Contains the noise perturb augmentation model.""" -from deepspeech.frontend.audio import AudioSegment -from deepspeech.frontend.augmentor.base import AugmentorBase -from deepspeech.frontend.utility import read_manifest +from paddlespeech.s2t.frontend.audio import AudioSegment +from paddlespeech.s2t.frontend.augmentor.base import AugmentorBase +from paddlespeech.s2t.frontend.utility import read_manifest class NoisePerturbAugmentor(AugmentorBase): diff --git a/deepspeech/frontend/augmentor/online_bayesian_normalization.py b/paddlespeech/s2t/frontend/augmentor/online_bayesian_normalization.py similarity index 97% rename from deepspeech/frontend/augmentor/online_bayesian_normalization.py rename to paddlespeech/s2t/frontend/augmentor/online_bayesian_normalization.py index 0f9d3ef6fbfba1b4c6895996d180ce33d0c18891..f9d1530f0a3b5d90bc5c57c494d9c4ef1849c7b6 100644 --- a/deepspeech/frontend/augmentor/online_bayesian_normalization.py +++ b/paddlespeech/s2t/frontend/augmentor/online_bayesian_normalization.py @@ -12,7 +12,7 @@ # See the License for the specific language governing permissions and # limitations under the License. """Contain the online bayesian normalization augmentation model.""" -from deepspeech.frontend.augmentor.base import AugmentorBase +from paddlespeech.s2t.frontend.augmentor.base import AugmentorBase class OnlineBayesianNormalizationAugmentor(AugmentorBase): diff --git a/deepspeech/frontend/augmentor/resample.py b/paddlespeech/s2t/frontend/augmentor/resample.py similarity index 95% rename from deepspeech/frontend/augmentor/resample.py rename to paddlespeech/s2t/frontend/augmentor/resample.py index 509fe003df11503d88403bfd0afd870665a87397..4e6402ff71da982400a482e8de479878d8eb8a46 100644 --- a/deepspeech/frontend/augmentor/resample.py +++ b/paddlespeech/s2t/frontend/augmentor/resample.py @@ -12,7 +12,7 @@ # See the License for the specific language governing permissions and # limitations under the License. """Contain the resample augmentation model.""" -from deepspeech.frontend.augmentor.base import AugmentorBase +from paddlespeech.s2t.frontend.augmentor.base import AugmentorBase class ResampleAugmentor(AugmentorBase): diff --git a/deepspeech/frontend/augmentor/shift_perturb.py b/paddlespeech/s2t/frontend/augmentor/shift_perturb.py similarity index 96% rename from deepspeech/frontend/augmentor/shift_perturb.py rename to paddlespeech/s2t/frontend/augmentor/shift_perturb.py index 8b7439fe58aa6626d4b7873bb1511f1c59a8dd16..ed6f162b99010e8b8e38522ea3a89e57ecd3dced 100644 --- a/deepspeech/frontend/augmentor/shift_perturb.py +++ b/paddlespeech/s2t/frontend/augmentor/shift_perturb.py @@ -12,7 +12,7 @@ # See the License for the specific language governing permissions and # limitations under the License. """Contains the volume perturb augmentation model.""" -from deepspeech.frontend.augmentor.base import AugmentorBase +from paddlespeech.s2t.frontend.augmentor.base import AugmentorBase class ShiftPerturbAugmentor(AugmentorBase): diff --git a/deepspeech/frontend/augmentor/spec_augment.py b/paddlespeech/s2t/frontend/augmentor/spec_augment.py similarity index 98% rename from deepspeech/frontend/augmentor/spec_augment.py rename to paddlespeech/s2t/frontend/augmentor/spec_augment.py index e78f6f6adac57bdcb683bf93f5a8fe6a557af3ec..e91cfdce42b621934fa25b69cc629ad03c7fec34 100644 --- a/deepspeech/frontend/augmentor/spec_augment.py +++ b/paddlespeech/s2t/frontend/augmentor/spec_augment.py @@ -18,8 +18,8 @@ import numpy as np from PIL import Image from PIL.Image import BICUBIC -from deepspeech.frontend.augmentor.base import AugmentorBase -from deepspeech.utils.log import Log +from paddlespeech.s2t.frontend.augmentor.base import AugmentorBase +from paddlespeech.s2t.utils.log import Log logger = Log(__name__).getlog() diff --git a/deepspeech/frontend/augmentor/speed_perturb.py b/paddlespeech/s2t/frontend/augmentor/speed_perturb.py similarity index 98% rename from deepspeech/frontend/augmentor/speed_perturb.py rename to paddlespeech/s2t/frontend/augmentor/speed_perturb.py index ce8dfde0a674f39459bec31169aeb614e842052b..af0b23ee40ae810fc52710702ac50c5803b77b57 100644 --- a/deepspeech/frontend/augmentor/speed_perturb.py +++ b/paddlespeech/s2t/frontend/augmentor/speed_perturb.py @@ -14,7 +14,7 @@ """Contain the speech perturbation augmentation model.""" import numpy as np -from deepspeech.frontend.augmentor.base import AugmentorBase +from paddlespeech.s2t.frontend.augmentor.base import AugmentorBase class SpeedPerturbAugmentor(AugmentorBase): diff --git a/deepspeech/frontend/augmentor/volume_perturb.py b/paddlespeech/s2t/frontend/augmentor/volume_perturb.py similarity index 96% rename from deepspeech/frontend/augmentor/volume_perturb.py rename to paddlespeech/s2t/frontend/augmentor/volume_perturb.py index 70cb2889706c355048db1df5e18f1bb155c3ffd1..8cd2dc0a81f6f3be843efd7b2711c78c3a441487 100644 --- a/deepspeech/frontend/augmentor/volume_perturb.py +++ b/paddlespeech/s2t/frontend/augmentor/volume_perturb.py @@ -12,7 +12,7 @@ # See the License for the specific language governing permissions and # limitations under the License. """Contains the volume perturb augmentation model.""" -from deepspeech.frontend.augmentor.base import AugmentorBase +from paddlespeech.s2t.frontend.augmentor.base import AugmentorBase class VolumePerturbAugmentor(AugmentorBase): diff --git a/deepspeech/frontend/featurizer/__init__.py b/paddlespeech/s2t/frontend/featurizer/__init__.py similarity index 100% rename from deepspeech/frontend/featurizer/__init__.py rename to paddlespeech/s2t/frontend/featurizer/__init__.py diff --git a/deepspeech/frontend/featurizer/audio_featurizer.py b/paddlespeech/s2t/frontend/featurizer/audio_featurizer.py similarity index 100% rename from deepspeech/frontend/featurizer/audio_featurizer.py rename to paddlespeech/s2t/frontend/featurizer/audio_featurizer.py diff --git a/deepspeech/frontend/featurizer/speech_featurizer.py b/paddlespeech/s2t/frontend/featurizer/speech_featurizer.py similarity index 95% rename from deepspeech/frontend/featurizer/speech_featurizer.py rename to paddlespeech/s2t/frontend/featurizer/speech_featurizer.py index 2568714080f276fae6aa06dfef76d57df78fc41b..591df96e1f23067ae1645f0690de119f3b85bd73 100644 --- a/deepspeech/frontend/featurizer/speech_featurizer.py +++ b/paddlespeech/s2t/frontend/featurizer/speech_featurizer.py @@ -12,8 +12,8 @@ # See the License for the specific language governing permissions and # limitations under the License. """Contains the speech featurizer class.""" -from deepspeech.frontend.featurizer.audio_featurizer import AudioFeaturizer -from deepspeech.frontend.featurizer.text_featurizer import TextFeaturizer +from paddlespeech.s2t.frontend.featurizer.audio_featurizer import AudioFeaturizer +from paddlespeech.s2t.frontend.featurizer.text_featurizer import TextFeaturizer class SpeechFeaturizer(): diff --git a/deepspeech/frontend/featurizer/text_featurizer.py b/paddlespeech/s2t/frontend/featurizer/text_featurizer.py similarity index 99% rename from deepspeech/frontend/featurizer/text_featurizer.py rename to paddlespeech/s2t/frontend/featurizer/text_featurizer.py index c596bd43b1fe003e00ba04ca9604771a4dd572c9..7f3bd9e1253fbcf491743ba912472b22b4d8f0e9 100644 --- a/deepspeech/frontend/featurizer/text_featurizer.py +++ b/paddlespeech/s2t/frontend/featurizer/text_featurizer.py @@ -23,7 +23,7 @@ from ..utility import MASKCTC from ..utility import SOS from ..utility import SPACE from ..utility import UNK -from deepspeech.utils.log import Log +from paddlespeech.s2t.utils.log import Log logger = Log(__name__).getlog() diff --git a/deepspeech/frontend/normalizer.py b/paddlespeech/s2t/frontend/normalizer.py similarity index 96% rename from deepspeech/frontend/normalizer.py rename to paddlespeech/s2t/frontend/normalizer.py index 6ace4fc6ddcaccd75436c1a528e7f6b512ba8292..a29cddc387c8c8336a09a6b2792bcd73a72b0908 100644 --- a/deepspeech/frontend/normalizer.py +++ b/paddlespeech/s2t/frontend/normalizer.py @@ -19,10 +19,10 @@ import paddle from paddle.io import DataLoader from paddle.io import Dataset -from deepspeech.frontend.audio import AudioSegment -from deepspeech.frontend.utility import load_cmvn -from deepspeech.frontend.utility import read_manifest -from deepspeech.utils.log import Log +from paddlespeech.s2t.frontend.audio import AudioSegment +from paddlespeech.s2t.frontend.utility import load_cmvn +from paddlespeech.s2t.frontend.utility import read_manifest +from paddlespeech.s2t.utils.log import Log __all__ = ["FeatureNormalizer"] diff --git a/deepspeech/frontend/speech.py b/paddlespeech/s2t/frontend/speech.py similarity index 99% rename from deepspeech/frontend/speech.py rename to paddlespeech/s2t/frontend/speech.py index 9eed9725ad2c9b7a8efeac82ad3b5609f154bbbc..8fd661c9246cbe973102d348d074a2ba3c1b20cc 100644 --- a/deepspeech/frontend/speech.py +++ b/paddlespeech/s2t/frontend/speech.py @@ -14,7 +14,7 @@ """Contains the speech segment class.""" import numpy as np -from deepspeech.frontend.audio import AudioSegment +from paddlespeech.s2t.frontend.audio import AudioSegment class SpeechSegment(AudioSegment): diff --git a/deepspeech/frontend/utility.py b/paddlespeech/s2t/frontend/utility.py similarity index 99% rename from deepspeech/frontend/utility.py rename to paddlespeech/s2t/frontend/utility.py index f83f1d4e1262e3cec0527ba80476917d41cc3b81..089890d2a2b5f2f5e024fcfb29667b23a0da232b 100644 --- a/deepspeech/frontend/utility.py +++ b/paddlespeech/s2t/frontend/utility.py @@ -23,7 +23,7 @@ from typing import Text import jsonlines import numpy as np -from deepspeech.utils.log import Log +from paddlespeech.s2t.utils.log import Log logger = Log(__name__).getlog() diff --git a/deepspeech/io/__init__.py b/paddlespeech/s2t/io/__init__.py similarity index 100% rename from deepspeech/io/__init__.py rename to paddlespeech/s2t/io/__init__.py diff --git a/deepspeech/io/batchfy.py b/paddlespeech/s2t/io/batchfy.py similarity index 99% rename from deepspeech/io/batchfy.py rename to paddlespeech/s2t/io/batchfy.py index 06cb3c9d4cd1f6a3cd3f3653d3c2ea323a0f9f82..3517f059af3d52b6bb3fc285864be9f15fc0a194 100644 --- a/deepspeech/io/batchfy.py +++ b/paddlespeech/s2t/io/batchfy.py @@ -15,7 +15,7 @@ import itertools import numpy as np -from deepspeech.utils.log import Log +from paddlespeech.s2t.utils.log import Log __all__ = ["make_batchset"] diff --git a/deepspeech/io/collator.py b/paddlespeech/s2t/io/collator.py similarity index 96% rename from deepspeech/io/collator.py rename to paddlespeech/s2t/io/collator.py index 5391260eeab8deb6eae2124bf3f30cc993df849e..a500f10c9c3af3bbf5f4ce53190f601b1030cf94 100644 --- a/deepspeech/io/collator.py +++ b/paddlespeech/s2t/io/collator.py @@ -17,16 +17,16 @@ from typing import Optional import numpy as np from yacs.config import CfgNode -from deepspeech.frontend.augmentor.augmentation import AugmentationPipeline -from deepspeech.frontend.featurizer.speech_featurizer import SpeechFeaturizer -from deepspeech.frontend.featurizer.text_featurizer import TextFeaturizer -from deepspeech.frontend.normalizer import FeatureNormalizer -from deepspeech.frontend.speech import SpeechSegment -from deepspeech.frontend.utility import IGNORE_ID -from deepspeech.frontend.utility import TarLocalData -from deepspeech.io.reader import LoadInputsAndTargets -from deepspeech.io.utility import pad_list -from deepspeech.utils.log import Log +from paddlespeech.s2t.frontend.augmentor.augmentation import AugmentationPipeline +from paddlespeech.s2t.frontend.featurizer.speech_featurizer import SpeechFeaturizer +from paddlespeech.s2t.frontend.featurizer.text_featurizer import TextFeaturizer +from paddlespeech.s2t.frontend.normalizer import FeatureNormalizer +from paddlespeech.s2t.frontend.speech import SpeechSegment +from paddlespeech.s2t.frontend.utility import IGNORE_ID +from paddlespeech.s2t.frontend.utility import TarLocalData +from paddlespeech.s2t.io.reader import LoadInputsAndTargets +from paddlespeech.s2t.io.utility import pad_list +from paddlespeech.s2t.utils.log import Log __all__ = ["SpeechCollator", "TripletSpeechCollator"] diff --git a/deepspeech/io/converter.py b/paddlespeech/s2t/io/converter.py similarity index 96% rename from deepspeech/io/converter.py rename to paddlespeech/s2t/io/converter.py index b80c7b20447b26d1c62bd1868526631903afae56..94634360c41100f9f518c065570b4a93d4e3f9ce 100644 --- a/deepspeech/io/converter.py +++ b/paddlespeech/s2t/io/converter.py @@ -13,8 +13,8 @@ # limitations under the License. import numpy as np -from deepspeech.io.utility import pad_list -from deepspeech.utils.log import Log +from paddlespeech.s2t.io.utility import pad_list +from paddlespeech.s2t.utils.log import Log __all__ = ["CustomConverter"] diff --git a/deepspeech/io/dataloader.py b/paddlespeech/s2t/io/dataloader.py similarity index 94% rename from deepspeech/io/dataloader.py rename to paddlespeech/s2t/io/dataloader.py index d8ef9ba6be7e57d9f7b3185cffcb7a2634ce955d..3b5000a280621502a6b20ca2bf71b43789912ab8 100644 --- a/deepspeech/io/dataloader.py +++ b/paddlespeech/s2t/io/dataloader.py @@ -19,12 +19,12 @@ from typing import Text import numpy as np from paddle.io import DataLoader -from deepspeech.frontend.utility import read_manifest -from deepspeech.io.batchfy import make_batchset -from deepspeech.io.converter import CustomConverter -from deepspeech.io.dataset import TransformDataset -from deepspeech.io.reader import LoadInputsAndTargets -from deepspeech.utils.log import Log +from paddlespeech.s2t.frontend.utility import read_manifest +from paddlespeech.s2t.io.batchfy import make_batchset +from paddlespeech.s2t.io.converter import CustomConverter +from paddlespeech.s2t.io.dataset import TransformDataset +from paddlespeech.s2t.io.reader import LoadInputsAndTargets +from paddlespeech.s2t.utils.log import Log __all__ = ["BatchDataLoader"] diff --git a/deepspeech/io/dataset.py b/paddlespeech/s2t/io/dataset.py similarity index 99% rename from deepspeech/io/dataset.py rename to paddlespeech/s2t/io/dataset.py index 7c1010025551e76a072f68447ecc59006cc6e310..121410c8b383f381e255fa9f718204fb68059d5f 100644 --- a/deepspeech/io/dataset.py +++ b/paddlespeech/s2t/io/dataset.py @@ -16,8 +16,8 @@ from typing import Optional from paddle.io import Dataset from yacs.config import CfgNode -from deepspeech.frontend.utility import read_manifest -from deepspeech.utils.log import Log +from paddlespeech.s2t.frontend.utility import read_manifest +from paddlespeech.s2t.utils.log import Log __all__ = ["ManifestDataset", "TransformDataset"] diff --git a/deepspeech/io/reader.py b/paddlespeech/s2t/io/reader.py similarity index 99% rename from deepspeech/io/reader.py rename to paddlespeech/s2t/io/reader.py index 590987522e6025839ecfa995b2fc013ffdd8fa8c..faf2f600bcb3e8d7ae3ccc12b8f7c2146654b9b4 100644 --- a/deepspeech/io/reader.py +++ b/paddlespeech/s2t/io/reader.py @@ -17,8 +17,8 @@ import kaldiio import numpy as np import soundfile -from deepspeech.frontend.augmentor.augmentation import AugmentationPipeline as Transformation -from deepspeech.utils.log import Log +from paddlespeech.s2t.frontend.augmentor.augmentation import AugmentationPipeline as Transformation +from paddlespeech.s2t.utils.log import Log __all__ = ["LoadInputsAndTargets"] diff --git a/deepspeech/io/sampler.py b/paddlespeech/s2t/io/sampler.py similarity index 99% rename from deepspeech/io/sampler.py rename to paddlespeech/s2t/io/sampler.py index 763a3781e474e1de2e1ae94dd4200dedcb82d253..35b57524b5906d53366ebc1c8d4b36322129bba2 100644 --- a/deepspeech/io/sampler.py +++ b/paddlespeech/s2t/io/sampler.py @@ -18,7 +18,7 @@ from paddle import distributed as dist from paddle.io import BatchSampler from paddle.io import DistributedBatchSampler -from deepspeech.utils.log import Log +from paddlespeech.s2t.utils.log import Log __all__ = [ "SortagradDistributedBatchSampler", diff --git a/deepspeech/io/utility.py b/paddlespeech/s2t/io/utility.py similarity index 98% rename from deepspeech/io/utility.py rename to paddlespeech/s2t/io/utility.py index 99487a0afeac13f5449575682caec3f74672bb14..392031ba81c5b6e641538891b81b36767805d2ff 100644 --- a/deepspeech/io/utility.py +++ b/paddlespeech/s2t/io/utility.py @@ -15,7 +15,7 @@ from typing import List import numpy as np -from deepspeech.utils.log import Log +from paddlespeech.s2t.utils.log import Log __all__ = ["pad_list", "pad_sequence"] diff --git a/deepspeech/models/__init__.py b/paddlespeech/s2t/models/__init__.py similarity index 100% rename from deepspeech/models/__init__.py rename to paddlespeech/s2t/models/__init__.py diff --git a/deepspeech/models/asr_interface.py b/paddlespeech/s2t/models/asr_interface.py similarity index 94% rename from deepspeech/models/asr_interface.py rename to paddlespeech/s2t/models/asr_interface.py index d86daa0b6e27245fbdd9845d1821d21648c59100..ece83e516b15470d31122cfc3eadf8d9346c5f66 100644 --- a/deepspeech/models/asr_interface.py +++ b/paddlespeech/s2t/models/asr_interface.py @@ -14,7 +14,7 @@ """ASR Interface module.""" import argparse -from deepspeech.utils.dynamic_import import dynamic_import +from paddlespeech.s2t.utils.dynamic_import import dynamic_import class ASRInterface: @@ -103,14 +103,14 @@ class ASRInterface: @property def attention_plot_class(self): """Get attention plot class.""" - from deepspeech.training.extensions.plot import PlotAttentionReport + from paddlespeech.s2t.training.extensions.plot import PlotAttentionReport return PlotAttentionReport @property def ctc_plot_class(self): """Get CTC plot class.""" - from deepspeech.training.extensions.plot import PlotCTCReport + from paddlespeech.s2t.training.extensions.plot import PlotCTCReport return PlotCTCReport @@ -140,8 +140,8 @@ class ASRInterface: predefined_asr = { - "transformer": "deepspeech.models.u2:U2Model", - "conformer": "deepspeech.models.u2:U2Model", + "transformer": "paddlespeech.s2t.models.u2:U2Model", + "conformer": "paddlespeech.s2t.models.u2:U2Model", } diff --git a/deepspeech/models/ds2/__init__.py b/paddlespeech/s2t/models/ds2/__init__.py similarity index 100% rename from deepspeech/models/ds2/__init__.py rename to paddlespeech/s2t/models/ds2/__init__.py diff --git a/deepspeech/models/ds2/conv.py b/paddlespeech/s2t/models/ds2/conv.py similarity index 97% rename from deepspeech/models/ds2/conv.py rename to paddlespeech/s2t/models/ds2/conv.py index 069b7dd4bed7f9c060ef54c891b293a9045c7b8b..4e766e793ddf4eb05d355cc8ed79f2c1b2f462d1 100644 --- a/deepspeech/models/ds2/conv.py +++ b/paddlespeech/s2t/models/ds2/conv.py @@ -14,9 +14,9 @@ from paddle import nn from paddle.nn import functional as F -from deepspeech.modules.activation import brelu -from deepspeech.modules.mask import make_non_pad_mask -from deepspeech.utils.log import Log +from paddlespeech.s2t.modules.activation import brelu +from paddlespeech.s2t.modules.mask import make_non_pad_mask +from paddlespeech.s2t.utils.log import Log logger = Log(__name__).getlog() diff --git a/deepspeech/models/ds2/deepspeech2.py b/paddlespeech/s2t/models/ds2/deepspeech2.py similarity index 97% rename from deepspeech/models/ds2/deepspeech2.py rename to paddlespeech/s2t/models/ds2/deepspeech2.py index 63327a8c895bafc7440a8d36347dba3a16a053f6..4a7a7c15e9b96edfe5ee4b3f29f406b4b6b62a64 100644 --- a/deepspeech/models/ds2/deepspeech2.py +++ b/paddlespeech/s2t/models/ds2/deepspeech2.py @@ -18,12 +18,12 @@ import paddle from paddle import nn from yacs.config import CfgNode -from deepspeech.models.ds2.conv import ConvStack -from deepspeech.models.ds2.rnn import RNNStack -from deepspeech.modules.ctc import CTCDecoder -from deepspeech.utils import layer_tools -from deepspeech.utils.checkpoint import Checkpoint -from deepspeech.utils.log import Log +from paddlespeech.s2t.models.ds2.conv import ConvStack +from paddlespeech.s2t.models.ds2.rnn import RNNStack +from paddlespeech.s2t.modules.ctc import CTCDecoder +from paddlespeech.s2t.utils import layer_tools +from paddlespeech.s2t.utils.checkpoint import Checkpoint +from paddlespeech.s2t.utils.log import Log logger = Log(__name__).getlog() diff --git a/deepspeech/models/ds2/rnn.py b/paddlespeech/s2t/models/ds2/rnn.py similarity index 98% rename from deepspeech/models/ds2/rnn.py rename to paddlespeech/s2t/models/ds2/rnn.py index d6a8b3942c79244db828004c458f4b6f8c444505..f655b2d822fdcdc282649cac6354ddcdab021c06 100644 --- a/deepspeech/models/ds2/rnn.py +++ b/paddlespeech/s2t/models/ds2/rnn.py @@ -18,9 +18,9 @@ from paddle import nn from paddle.nn import functional as F from paddle.nn import initializer as I -from deepspeech.modules.activation import brelu -from deepspeech.modules.mask import make_non_pad_mask -from deepspeech.utils.log import Log +from paddlespeech.s2t.modules.activation import brelu +from paddlespeech.s2t.modules.mask import make_non_pad_mask +from paddlespeech.s2t.utils.log import Log logger = Log(__name__).getlog() diff --git a/deepspeech/models/ds2_online/__init__.py b/paddlespeech/s2t/models/ds2_online/__init__.py similarity index 100% rename from deepspeech/models/ds2_online/__init__.py rename to paddlespeech/s2t/models/ds2_online/__init__.py diff --git a/deepspeech/models/ds2_online/conv.py b/paddlespeech/s2t/models/ds2_online/conv.py similarity index 95% rename from deepspeech/models/ds2_online/conv.py rename to paddlespeech/s2t/models/ds2_online/conv.py index 4a6fd5abd5b9e2cffee63d287b6f152f63151882..25a9715a3029f73bd1e1d508ec8b70a861144f66 100644 --- a/deepspeech/models/ds2_online/conv.py +++ b/paddlespeech/s2t/models/ds2_online/conv.py @@ -13,7 +13,7 @@ # limitations under the License. import paddle -from deepspeech.modules.subsampling import Conv2dSubsampling4 +from paddlespeech.s2t.modules.subsampling import Conv2dSubsampling4 class Conv2dSubsampling4Online(Conv2dSubsampling4): diff --git a/deepspeech/models/ds2_online/deepspeech2.py b/paddlespeech/s2t/models/ds2_online/deepspeech2.py similarity index 98% rename from deepspeech/models/ds2_online/deepspeech2.py rename to paddlespeech/s2t/models/ds2_online/deepspeech2.py index 52e0c7b1705aba1f37331fa08688d6f2ffbffb08..da04d5c5de8f56ac17801b2871c6c2f89b16712c 100644 --- a/deepspeech/models/ds2_online/deepspeech2.py +++ b/paddlespeech/s2t/models/ds2_online/deepspeech2.py @@ -19,11 +19,11 @@ import paddle.nn.functional as F from paddle import nn from yacs.config import CfgNode -from deepspeech.models.ds2_online.conv import Conv2dSubsampling4Online -from deepspeech.modules.ctc import CTCDecoder -from deepspeech.utils import layer_tools -from deepspeech.utils.checkpoint import Checkpoint -from deepspeech.utils.log import Log +from paddlespeech.s2t.models.ds2_online.conv import Conv2dSubsampling4Online +from paddlespeech.s2t.modules.ctc import CTCDecoder +from paddlespeech.s2t.utils import layer_tools +from paddlespeech.s2t.utils.checkpoint import Checkpoint +from paddlespeech.s2t.utils.log import Log logger = Log(__name__).getlog() __all__ = ['DeepSpeech2ModelOnline', 'DeepSpeech2InferModelOnline'] diff --git a/deepspeech/models/lm/__init__.py b/paddlespeech/s2t/models/lm/__init__.py similarity index 100% rename from deepspeech/models/lm/__init__.py rename to paddlespeech/s2t/models/lm/__init__.py diff --git a/deepspeech/models/lm/transformer.py b/paddlespeech/s2t/models/lm/transformer.py similarity index 96% rename from deepspeech/models/lm/transformer.py rename to paddlespeech/s2t/models/lm/transformer.py index 19e2b758a5a702f052d2fc6e3ab1b41258e5c16e..447f1dbc3bb5a4b86731ec6be52bac5b3af4ab26 100644 --- a/deepspeech/models/lm/transformer.py +++ b/paddlespeech/s2t/models/lm/transformer.py @@ -20,11 +20,11 @@ import paddle import paddle.nn as nn import paddle.nn.functional as F -from deepspeech.decoders.scorers.scorer_interface import BatchScorerInterface -from deepspeech.models.lm_interface import LMInterface -from deepspeech.modules.encoder import TransformerEncoder -from deepspeech.modules.mask import subsequent_mask -from deepspeech.utils.log import Log +from paddlespeech.s2t.decoders.scorers.scorer_interface import BatchScorerInterface +from paddlespeech.s2t.models.lm_interface import LMInterface +from paddlespeech.s2t.modules.encoder import TransformerEncoder +from paddlespeech.s2t.modules.mask import subsequent_mask +from paddlespeech.s2t.utils.log import Log logger = Log(__name__).getlog() diff --git a/deepspeech/models/lm_interface.py b/paddlespeech/s2t/models/lm_interface.py similarity index 91% rename from deepspeech/models/lm_interface.py rename to paddlespeech/s2t/models/lm_interface.py index e2987282141c2f6df1cbd936664a5b9053791d3a..7ae39b351465c06cd4bfafea4f72ab6106b919b9 100644 --- a/deepspeech/models/lm_interface.py +++ b/paddlespeech/s2t/models/lm_interface.py @@ -14,8 +14,8 @@ """Language model interface.""" import argparse -from deepspeech.decoders.scorers.scorer_interface import ScorerInterface -from deepspeech.utils.dynamic_import import dynamic_import +from paddlespeech.s2t.decoders.scorers.scorer_interface import ScorerInterface +from paddlespeech.s2t.utils.dynamic_import import dynamic_import class LMInterface(ScorerInterface): @@ -62,7 +62,7 @@ class LMInterface(ScorerInterface): predefined_lms = { - "transformer": "deepspeech.models.lm.transformer:TransformerLM", + "transformer": "paddlespeech.s2t.models.lm.transformer:TransformerLM", } diff --git a/deepspeech/models/st_interface.py b/paddlespeech/s2t/models/st_interface.py similarity index 95% rename from deepspeech/models/st_interface.py rename to paddlespeech/s2t/models/st_interface.py index 05939f9a724aa1a08c60eed4cc427f8ea6757b2d..331f1e824d44c65fbff8b5a1c54a34c5f7111a80 100644 --- a/deepspeech/models/st_interface.py +++ b/paddlespeech/s2t/models/st_interface.py @@ -13,7 +13,7 @@ # limitations under the License. """ST Interface module.""" from .asr_interface import ASRInterface -from deepspeech.utils.dynamic_import import dynamic_import +from paddlespeech.s2t.utils.dynamic_import import dynamic_import class STInterface(ASRInterface): @@ -55,7 +55,7 @@ class STInterface(ASRInterface): predefined_st = { - "transformer": "deepspeech.models.u2_st:U2STModel", + "transformer": "paddlespeech.s2t.models.u2_st:U2STModel", } diff --git a/deepspeech/models/u2/__init__.py b/paddlespeech/s2t/models/u2/__init__.py similarity index 100% rename from deepspeech/models/u2/__init__.py rename to paddlespeech/s2t/models/u2/__init__.py diff --git a/deepspeech/models/u2/u2.py b/paddlespeech/s2t/models/u2/u2.py similarity index 96% rename from deepspeech/models/u2/u2.py rename to paddlespeech/s2t/models/u2/u2.py index 6cd3b7751d3f938c85736b750fc756e2c51d311f..fd9982716d26ff3f737173646c9fbaf3f7942255 100644 --- a/deepspeech/models/u2/u2.py +++ b/paddlespeech/s2t/models/u2/u2.py @@ -28,29 +28,29 @@ from paddle import jit from paddle import nn from yacs.config import CfgNode -from deepspeech.decoders.scorers.ctc import CTCPrefixScorer -from deepspeech.frontend.utility import IGNORE_ID -from deepspeech.frontend.utility import load_cmvn -from deepspeech.models.asr_interface import ASRInterface -from deepspeech.modules.cmvn import GlobalCMVN -from deepspeech.modules.ctc import CTCDecoder -from deepspeech.modules.decoder import TransformerDecoder -from deepspeech.modules.encoder import ConformerEncoder -from deepspeech.modules.encoder import TransformerEncoder -from deepspeech.modules.loss import LabelSmoothingLoss -from deepspeech.modules.mask import make_pad_mask -from deepspeech.modules.mask import mask_finished_preds -from deepspeech.modules.mask import mask_finished_scores -from deepspeech.modules.mask import subsequent_mask -from deepspeech.utils import checkpoint -from deepspeech.utils import layer_tools -from deepspeech.utils.ctc_utils import remove_duplicates_and_blank -from deepspeech.utils.log import Log -from deepspeech.utils.tensor_utils import add_sos_eos -from deepspeech.utils.tensor_utils import pad_sequence -from deepspeech.utils.tensor_utils import th_accuracy -from deepspeech.utils.utility import log_add -from deepspeech.utils.utility import UpdateConfig +from paddlespeech.s2t.decoders.scorers.ctc import CTCPrefixScorer +from paddlespeech.s2t.frontend.utility import IGNORE_ID +from paddlespeech.s2t.frontend.utility import load_cmvn +from paddlespeech.s2t.models.asr_interface import ASRInterface +from paddlespeech.s2t.modules.cmvn import GlobalCMVN +from paddlespeech.s2t.modules.ctc import CTCDecoder +from paddlespeech.s2t.modules.decoder import TransformerDecoder +from paddlespeech.s2t.modules.encoder import ConformerEncoder +from paddlespeech.s2t.modules.encoder import TransformerEncoder +from paddlespeech.s2t.modules.loss import LabelSmoothingLoss +from paddlespeech.s2t.modules.mask import make_pad_mask +from paddlespeech.s2t.modules.mask import mask_finished_preds +from paddlespeech.s2t.modules.mask import mask_finished_scores +from paddlespeech.s2t.modules.mask import subsequent_mask +from paddlespeech.s2t.utils import checkpoint +from paddlespeech.s2t.utils import layer_tools +from paddlespeech.s2t.utils.ctc_utils import remove_duplicates_and_blank +from paddlespeech.s2t.utils.log import Log +from paddlespeech.s2t.utils.tensor_utils import add_sos_eos +from paddlespeech.s2t.utils.tensor_utils import pad_sequence +from paddlespeech.s2t.utils.tensor_utils import th_accuracy +from paddlespeech.s2t.utils.utility import log_add +from paddlespeech.s2t.utils.utility import UpdateConfig __all__ = ["U2Model", "U2InferModel"] diff --git a/deepspeech/models/u2/updater.py b/paddlespeech/s2t/models/u2/updater.py similarity index 93% rename from deepspeech/models/u2/updater.py rename to paddlespeech/s2t/models/u2/updater.py index 7b70ca047d7d815652fd9ca196e0ba4b11bbe606..bb18fe4160d24fb39196f0286397b879d8069d31 100644 --- a/deepspeech/models/u2/updater.py +++ b/paddlespeech/s2t/models/u2/updater.py @@ -16,12 +16,12 @@ from contextlib import nullcontext import paddle from paddle import distributed as dist -from deepspeech.training.extensions.evaluator import StandardEvaluator -from deepspeech.training.reporter import report -from deepspeech.training.timer import Timer -from deepspeech.training.updaters.standard_updater import StandardUpdater -from deepspeech.utils import layer_tools -from deepspeech.utils.log import Log +from paddlespeech.s2t.training.extensions.evaluator import StandardEvaluator +from paddlespeech.s2t.training.reporter import report +from paddlespeech.s2t.training.timer import Timer +from paddlespeech.s2t.training.updaters.standard_updater import StandardUpdater +from paddlespeech.s2t.utils import layer_tools +from paddlespeech.s2t.utils.log import Log logger = Log(__name__).getlog() diff --git a/deepspeech/models/u2_st/__init__.py b/paddlespeech/s2t/models/u2_st/__init__.py similarity index 100% rename from deepspeech/models/u2_st/__init__.py rename to paddlespeech/s2t/models/u2_st/__init__.py diff --git a/deepspeech/models/u2_st/u2_st.py b/paddlespeech/s2t/models/u2_st/u2_st.py similarity index 96% rename from deepspeech/models/u2_st/u2_st.py rename to paddlespeech/s2t/models/u2_st/u2_st.py index bf98423d43c7679c7829e27deea33bd0c2c38ee9..76c50150e6507495517b98dd00518edf70c87f4b 100644 --- a/deepspeech/models/u2_st/u2_st.py +++ b/paddlespeech/s2t/models/u2_st/u2_st.py @@ -26,23 +26,23 @@ from paddle import jit from paddle import nn from yacs.config import CfgNode -from deepspeech.frontend.utility import IGNORE_ID -from deepspeech.frontend.utility import load_cmvn -from deepspeech.modules.cmvn import GlobalCMVN -from deepspeech.modules.ctc import CTCDecoder -from deepspeech.modules.decoder import TransformerDecoder -from deepspeech.modules.encoder import ConformerEncoder -from deepspeech.modules.encoder import TransformerEncoder -from deepspeech.modules.loss import LabelSmoothingLoss -from deepspeech.modules.mask import mask_finished_preds -from deepspeech.modules.mask import mask_finished_scores -from deepspeech.modules.mask import subsequent_mask -from deepspeech.utils import checkpoint -from deepspeech.utils import layer_tools -from deepspeech.utils.log import Log -from deepspeech.utils.tensor_utils import add_sos_eos -from deepspeech.utils.tensor_utils import th_accuracy -from deepspeech.utils.utility import UpdateConfig +from paddlespeech.s2t.frontend.utility import IGNORE_ID +from paddlespeech.s2t.frontend.utility import load_cmvn +from paddlespeech.s2t.modules.cmvn import GlobalCMVN +from paddlespeech.s2t.modules.ctc import CTCDecoder +from paddlespeech.s2t.modules.decoder import TransformerDecoder +from paddlespeech.s2t.modules.encoder import ConformerEncoder +from paddlespeech.s2t.modules.encoder import TransformerEncoder +from paddlespeech.s2t.modules.loss import LabelSmoothingLoss +from paddlespeech.s2t.modules.mask import mask_finished_preds +from paddlespeech.s2t.modules.mask import mask_finished_scores +from paddlespeech.s2t.modules.mask import subsequent_mask +from paddlespeech.s2t.utils import checkpoint +from paddlespeech.s2t.utils import layer_tools +from paddlespeech.s2t.utils.log import Log +from paddlespeech.s2t.utils.tensor_utils import add_sos_eos +from paddlespeech.s2t.utils.tensor_utils import th_accuracy +from paddlespeech.s2t.utils.utility import UpdateConfig __all__ = ["U2STModel", "U2STInferModel"] diff --git a/deepspeech/modules/__init__.py b/paddlespeech/s2t/modules/__init__.py similarity index 100% rename from deepspeech/modules/__init__.py rename to paddlespeech/s2t/modules/__init__.py diff --git a/deepspeech/modules/activation.py b/paddlespeech/s2t/modules/activation.py similarity index 99% rename from deepspeech/modules/activation.py rename to paddlespeech/s2t/modules/activation.py index 3cb8729e1d81611587088e1b8f9c05806fd43be9..4081f7f81a5ca9a0b8594ff01cff23ef6d3eac94 100644 --- a/deepspeech/modules/activation.py +++ b/paddlespeech/s2t/modules/activation.py @@ -17,7 +17,7 @@ import paddle from paddle import nn from paddle.nn import functional as F -from deepspeech.utils.log import Log +from paddlespeech.s2t.utils.log import Log logger = Log(__name__).getlog() diff --git a/deepspeech/modules/attention.py b/paddlespeech/s2t/modules/attention.py similarity index 99% rename from deepspeech/modules/attention.py rename to paddlespeech/s2t/modules/attention.py index f94797282a5eff2ee5f0d5ae8b558ad53328acee..d5246777c57386b280e7e613baf853d9e7a9ba50 100644 --- a/deepspeech/modules/attention.py +++ b/paddlespeech/s2t/modules/attention.py @@ -20,7 +20,7 @@ import paddle from paddle import nn from paddle.nn import initializer as I -from deepspeech.utils.log import Log +from paddlespeech.s2t.utils.log import Log logger = Log(__name__).getlog() diff --git a/deepspeech/modules/cmvn.py b/paddlespeech/s2t/modules/cmvn.py similarity index 97% rename from deepspeech/modules/cmvn.py rename to paddlespeech/s2t/modules/cmvn.py index b98af052e9a9390bd153b34b80aaa09b81214d22..9aa938af7d0e20f05f7afc3eda748e7853dd36b7 100644 --- a/deepspeech/modules/cmvn.py +++ b/paddlespeech/s2t/modules/cmvn.py @@ -14,7 +14,7 @@ import paddle from paddle import nn -from deepspeech.utils.log import Log +from paddlespeech.s2t.utils.log import Log logger = Log(__name__).getlog() diff --git a/deepspeech/modules/conformer_convolution.py b/paddlespeech/s2t/modules/conformer_convolution.py similarity index 99% rename from deepspeech/modules/conformer_convolution.py rename to paddlespeech/s2t/modules/conformer_convolution.py index 59249d2ac302d321ae476c9b3eec0009f78f1dbb..39b1ee3275bd2c7aa85012976cd9e4d9d75a09da 100644 --- a/deepspeech/modules/conformer_convolution.py +++ b/paddlespeech/s2t/modules/conformer_convolution.py @@ -19,7 +19,7 @@ import paddle from paddle import nn from typeguard import check_argument_types -from deepspeech.utils.log import Log +from paddlespeech.s2t.utils.log import Log logger = Log(__name__).getlog() diff --git a/deepspeech/modules/crf.py b/paddlespeech/s2t/modules/crf.py similarity index 99% rename from deepspeech/modules/crf.py rename to paddlespeech/s2t/modules/crf.py index b6b481a0fe3b347d226270908903bf71366b5e28..66f6b18065f4171c121dd56494e229556bf47af4 100644 --- a/deepspeech/modules/crf.py +++ b/paddlespeech/s2t/modules/crf.py @@ -14,7 +14,7 @@ import paddle from paddle import nn -from deepspeech.utils.log import Log +from paddlespeech.s2t.utils.log import Log logger = Log(__name__).getlog() diff --git a/deepspeech/modules/ctc.py b/paddlespeech/s2t/modules/ctc.py similarity index 96% rename from deepspeech/modules/ctc.py rename to paddlespeech/s2t/modules/ctc.py index df6848db0b91b7dce1a140c8f9c6a57e2810ef2b..120abd2ba0b3e0e0c3c421dd5515d98322fcf90b 100644 --- a/deepspeech/modules/ctc.py +++ b/paddlespeech/s2t/modules/ctc.py @@ -18,16 +18,16 @@ from paddle import nn from paddle.nn import functional as F from typeguard import check_argument_types -from deepspeech.modules.loss import CTCLoss -from deepspeech.utils import ctc_utils -from deepspeech.utils.log import Log +from paddlespeech.s2t.modules.loss import CTCLoss +from paddlespeech.s2t.utils import ctc_utils +from paddlespeech.s2t.utils.log import Log logger = Log(__name__).getlog() try: - from deepspeech.decoders.ctcdecoder.swig_wrapper import ctc_beam_search_decoder_batch # noqa: F401 - from deepspeech.decoders.ctcdecoder.swig_wrapper import ctc_greedy_decoder # noqa: F401 - from deepspeech.decoders.ctcdecoder.swig_wrapper import Scorer # noqa: F401 + from paddlespeech.s2t.decoders.ctcdecoder.swig_wrapper import ctc_beam_search_decoder_batch # noqa: F401 + from paddlespeech.s2t.decoders.ctcdecoder.swig_wrapper import ctc_greedy_decoder # noqa: F401 + from paddlespeech.s2t.decoders.ctcdecoder.swig_wrapper import Scorer # noqa: F401 except Exception as e: logger.info("ctcdecoder not installed!") diff --git a/deepspeech/modules/decoder.py b/paddlespeech/s2t/modules/decoder.py similarity index 94% rename from deepspeech/modules/decoder.py rename to paddlespeech/s2t/modules/decoder.py index 735f06dc6e8b850af203952f04043830b118a898..7d545f5e87718550b3a29884f284f21896feca11 100644 --- a/deepspeech/modules/decoder.py +++ b/paddlespeech/s2t/modules/decoder.py @@ -21,15 +21,15 @@ import paddle from paddle import nn from typeguard import check_argument_types -from deepspeech.decoders.scorers.scorer_interface import BatchScorerInterface -from deepspeech.modules.attention import MultiHeadedAttention -from deepspeech.modules.decoder_layer import DecoderLayer -from deepspeech.modules.embedding import PositionalEncoding -from deepspeech.modules.mask import make_non_pad_mask -from deepspeech.modules.mask import make_xs_mask -from deepspeech.modules.mask import subsequent_mask -from deepspeech.modules.positionwise_feed_forward import PositionwiseFeedForward -from deepspeech.utils.log import Log +from paddlespeech.s2t.decoders.scorers.scorer_interface import BatchScorerInterface +from paddlespeech.s2t.modules.attention import MultiHeadedAttention +from paddlespeech.s2t.modules.decoder_layer import DecoderLayer +from paddlespeech.s2t.modules.embedding import PositionalEncoding +from paddlespeech.s2t.modules.mask import make_non_pad_mask +from paddlespeech.s2t.modules.mask import make_xs_mask +from paddlespeech.s2t.modules.mask import subsequent_mask +from paddlespeech.s2t.modules.positionwise_feed_forward import PositionwiseFeedForward +from paddlespeech.s2t.utils.log import Log logger = Log(__name__).getlog() diff --git a/deepspeech/modules/decoder_layer.py b/paddlespeech/s2t/modules/decoder_layer.py similarity index 99% rename from deepspeech/modules/decoder_layer.py rename to paddlespeech/s2t/modules/decoder_layer.py index 47c42615e929718ba436fdce5363a3b52226371e..816bc9f619d1e6c3fe3d8f680c5be75bb778cdfe 100644 --- a/deepspeech/modules/decoder_layer.py +++ b/paddlespeech/s2t/modules/decoder_layer.py @@ -18,7 +18,7 @@ from typing import Tuple import paddle from paddle import nn -from deepspeech.utils.log import Log +from paddlespeech.s2t.utils.log import Log logger = Log(__name__).getlog() diff --git a/deepspeech/modules/embedding.py b/paddlespeech/s2t/modules/embedding.py similarity index 99% rename from deepspeech/modules/embedding.py rename to paddlespeech/s2t/modules/embedding.py index 64d594c29f875da931bd51572daaf1d4a871d886..938898c13ac236e5334ac36f2e46cf9c930756cc 100644 --- a/deepspeech/modules/embedding.py +++ b/paddlespeech/s2t/modules/embedding.py @@ -18,7 +18,7 @@ from typing import Tuple import paddle from paddle import nn -from deepspeech.utils.log import Log +from paddlespeech.s2t.utils.log import Log logger = Log(__name__).getlog() diff --git a/deepspeech/modules/encoder.py b/paddlespeech/s2t/modules/encoder.py similarity index 94% rename from deepspeech/modules/encoder.py rename to paddlespeech/s2t/modules/encoder.py index 435b68949da47cb89eb206d472f9d0bc06410bfe..246536dbe70045ec4c2552c09a0636aae58e04af 100644 --- a/deepspeech/modules/encoder.py +++ b/paddlespeech/s2t/modules/encoder.py @@ -20,23 +20,23 @@ import paddle from paddle import nn from typeguard import check_argument_types -from deepspeech.modules.activation import get_activation -from deepspeech.modules.attention import MultiHeadedAttention -from deepspeech.modules.attention import RelPositionMultiHeadedAttention -from deepspeech.modules.conformer_convolution import ConvolutionModule -from deepspeech.modules.embedding import NoPositionalEncoding -from deepspeech.modules.embedding import PositionalEncoding -from deepspeech.modules.embedding import RelPositionalEncoding -from deepspeech.modules.encoder_layer import ConformerEncoderLayer -from deepspeech.modules.encoder_layer import TransformerEncoderLayer -from deepspeech.modules.mask import add_optional_chunk_mask -from deepspeech.modules.mask import make_non_pad_mask -from deepspeech.modules.positionwise_feed_forward import PositionwiseFeedForward -from deepspeech.modules.subsampling import Conv2dSubsampling4 -from deepspeech.modules.subsampling import Conv2dSubsampling6 -from deepspeech.modules.subsampling import Conv2dSubsampling8 -from deepspeech.modules.subsampling import LinearNoSubsampling -from deepspeech.utils.log import Log +from paddlespeech.s2t.modules.activation import get_activation +from paddlespeech.s2t.modules.attention import MultiHeadedAttention +from paddlespeech.s2t.modules.attention import RelPositionMultiHeadedAttention +from paddlespeech.s2t.modules.conformer_convolution import ConvolutionModule +from paddlespeech.s2t.modules.embedding import NoPositionalEncoding +from paddlespeech.s2t.modules.embedding import PositionalEncoding +from paddlespeech.s2t.modules.embedding import RelPositionalEncoding +from paddlespeech.s2t.modules.encoder_layer import ConformerEncoderLayer +from paddlespeech.s2t.modules.encoder_layer import TransformerEncoderLayer +from paddlespeech.s2t.modules.mask import add_optional_chunk_mask +from paddlespeech.s2t.modules.mask import make_non_pad_mask +from paddlespeech.s2t.modules.positionwise_feed_forward import PositionwiseFeedForward +from paddlespeech.s2t.modules.subsampling import Conv2dSubsampling4 +from paddlespeech.s2t.modules.subsampling import Conv2dSubsampling6 +from paddlespeech.s2t.modules.subsampling import Conv2dSubsampling8 +from paddlespeech.s2t.modules.subsampling import LinearNoSubsampling +from paddlespeech.s2t.utils.log import Log logger = Log(__name__).getlog() diff --git a/deepspeech/modules/encoder_layer.py b/paddlespeech/s2t/modules/encoder_layer.py similarity index 99% rename from deepspeech/modules/encoder_layer.py rename to paddlespeech/s2t/modules/encoder_layer.py index 6f49cfc86254e67d7d82f1656e9926712c0d354a..0525a6147a436770cccaf34fe187abf4dc110dce 100644 --- a/deepspeech/modules/encoder_layer.py +++ b/paddlespeech/s2t/modules/encoder_layer.py @@ -18,7 +18,7 @@ from typing import Tuple import paddle from paddle import nn -from deepspeech.utils.log import Log +from paddlespeech.s2t.utils.log import Log logger = Log(__name__).getlog() diff --git a/deepspeech/modules/loss.py b/paddlespeech/s2t/modules/loss.py similarity index 99% rename from deepspeech/modules/loss.py rename to paddlespeech/s2t/modules/loss.py index e11388107f5a9fc3199192f6f7881817cb3680a5..012ef242608093f6a6a8b62bb55613c62f30f0b2 100644 --- a/deepspeech/modules/loss.py +++ b/paddlespeech/s2t/modules/loss.py @@ -17,7 +17,7 @@ import paddle from paddle import nn from paddle.nn import functional as F -from deepspeech.utils.log import Log +from paddlespeech.s2t.utils.log import Log logger = Log(__name__).getlog() diff --git a/deepspeech/modules/mask.py b/paddlespeech/s2t/modules/mask.py similarity index 99% rename from deepspeech/modules/mask.py rename to paddlespeech/s2t/modules/mask.py index 52f8e4bca94fcb46ec9e90a69f8665dde4839cab..5c7886d459d23ad434a560478e9c6a2ae831e31b 100644 --- a/deepspeech/modules/mask.py +++ b/paddlespeech/s2t/modules/mask.py @@ -13,7 +13,7 @@ # limitations under the License. import paddle -from deepspeech.utils.log import Log +from paddlespeech.s2t.utils.log import Log logger = Log(__name__).getlog() diff --git a/deepspeech/modules/positionwise_feed_forward.py b/paddlespeech/s2t/modules/positionwise_feed_forward.py similarity index 97% rename from deepspeech/modules/positionwise_feed_forward.py rename to paddlespeech/s2t/modules/positionwise_feed_forward.py index 9732e1aa4af21c17a5f13791492331f42f46ac2e..ccea8e57d8d4880996f5ad1d1fd70fe14660435f 100644 --- a/deepspeech/modules/positionwise_feed_forward.py +++ b/paddlespeech/s2t/modules/positionwise_feed_forward.py @@ -15,7 +15,7 @@ import paddle from paddle import nn -from deepspeech.utils.log import Log +from paddlespeech.s2t.utils.log import Log logger = Log(__name__).getlog() diff --git a/deepspeech/modules/subsampling.py b/paddlespeech/s2t/modules/subsampling.py similarity index 98% rename from deepspeech/modules/subsampling.py rename to paddlespeech/s2t/modules/subsampling.py index 13e2c8efb4a85138801566599e7af7e3410ecfe3..6b8c28c6a0f7d3927f75ea9088eea7d03451e99b 100644 --- a/deepspeech/modules/subsampling.py +++ b/paddlespeech/s2t/modules/subsampling.py @@ -17,8 +17,8 @@ from typing import Tuple import paddle from paddle import nn -from deepspeech.modules.embedding import PositionalEncoding -from deepspeech.utils.log import Log +from paddlespeech.s2t.modules.embedding import PositionalEncoding +from paddlespeech.s2t.utils.log import Log logger = Log(__name__).getlog() diff --git a/deepspeech/training/__init__.py b/paddlespeech/s2t/training/__init__.py similarity index 100% rename from deepspeech/training/__init__.py rename to paddlespeech/s2t/training/__init__.py diff --git a/deepspeech/training/cli.py b/paddlespeech/s2t/training/cli.py similarity index 95% rename from deepspeech/training/cli.py rename to paddlespeech/s2t/training/cli.py index 14a34cb751ee5b66917c9f762d83741a50f53cc0..55b010e98b8e4d50e54b487bc275861e63cb4413 100644 --- a/deepspeech/training/cli.py +++ b/paddlespeech/s2t/training/cli.py @@ -36,10 +36,10 @@ class LoadFromFile(argparse.Action): def default_argument_parser(parser=None): - r"""A simple yet genral argument parser for experiments with parakeet. + r"""A simple yet genral argument parser for experiments with t2s. - This is used in examples with parakeet. And it is intended to be used by - other experiments with parakeet. It requires a minimal set of command line + This is used in examples with t2s. And it is intended to be used by + other experiments with t2s. It requires a minimal set of command line arguments to start a training script. The ``--config`` and ``--opts`` are used for overwrite the deault @@ -56,7 +56,7 @@ def default_argument_parser(parser=None): See Also -------- - parakeet.training.experiment + paddlespeech.t2s.training.experiment Returns ------- argparse.ArgumentParser diff --git a/deepspeech/training/extensions/__init__.py b/paddlespeech/s2t/training/extensions/__init__.py similarity index 100% rename from deepspeech/training/extensions/__init__.py rename to paddlespeech/s2t/training/extensions/__init__.py diff --git a/deepspeech/training/extensions/evaluator.py b/paddlespeech/s2t/training/extensions/evaluator.py similarity index 98% rename from deepspeech/training/extensions/evaluator.py rename to paddlespeech/s2t/training/extensions/evaluator.py index 1026a4ec39e9257551dddb4d9beff9a415a82da3..9da0d731645ca6005fa917d433bca338685613c6 100644 --- a/deepspeech/training/extensions/evaluator.py +++ b/paddlespeech/s2t/training/extensions/evaluator.py @@ -23,7 +23,7 @@ from ..reporter import DictSummary from ..reporter import ObsScope from ..reporter import report from ..timer import Timer -from deepspeech.utils.log import Log +from paddlespeech.s2t.utils.log import Log logger = Log(__name__).getlog() diff --git a/deepspeech/training/extensions/extension.py b/paddlespeech/s2t/training/extensions/extension.py similarity index 100% rename from deepspeech/training/extensions/extension.py rename to paddlespeech/s2t/training/extensions/extension.py diff --git a/deepspeech/training/extensions/plot.py b/paddlespeech/s2t/training/extensions/plot.py similarity index 100% rename from deepspeech/training/extensions/plot.py rename to paddlespeech/s2t/training/extensions/plot.py diff --git a/deepspeech/training/extensions/snapshot.py b/paddlespeech/s2t/training/extensions/snapshot.py similarity index 97% rename from deepspeech/training/extensions/snapshot.py rename to paddlespeech/s2t/training/extensions/snapshot.py index e81eb97fccf9612c240cb5e4dcfae792f8e68800..753c7ec0ec93d76bc0435d1500a0eaf7a44f0826 100644 --- a/deepspeech/training/extensions/snapshot.py +++ b/paddlespeech/s2t/training/extensions/snapshot.py @@ -23,8 +23,8 @@ import jsonlines from . import extension from ..reporter import get_observations from ..updaters.trainer import Trainer -from deepspeech.utils.log import Log -from deepspeech.utils.mp_tools import rank_zero_only +from paddlespeech.s2t.utils.log import Log +from paddlespeech.s2t.utils.mp_tools import rank_zero_only logger = Log(__name__).getlog() diff --git a/deepspeech/training/extensions/visualizer.py b/paddlespeech/s2t/training/extensions/visualizer.py similarity index 100% rename from deepspeech/training/extensions/visualizer.py rename to paddlespeech/s2t/training/extensions/visualizer.py diff --git a/deepspeech/training/gradclip.py b/paddlespeech/s2t/training/gradclip.py similarity index 98% rename from deepspeech/training/gradclip.py rename to paddlespeech/s2t/training/gradclip.py index 87b36acaeccd9fecffba48a7b0c6c61a3ff782b2..26ac501e282087b6906bb44833e389abb346db9f 100644 --- a/deepspeech/training/gradclip.py +++ b/paddlespeech/s2t/training/gradclip.py @@ -16,7 +16,7 @@ from paddle.fluid import core from paddle.fluid import layers from paddle.fluid.dygraph import base as imperative_base -from deepspeech.utils.log import Log +from paddlespeech.s2t.utils.log import Log __all__ = ["ClipGradByGlobalNormWithLog"] diff --git a/deepspeech/training/optimizer.py b/paddlespeech/s2t/training/optimizer.py similarity index 93% rename from deepspeech/training/optimizer.py rename to paddlespeech/s2t/training/optimizer.py index db7069c9812365f113d20ef936155e9d426855aa..8ed30769f727c3345e5d5b304bd39923de4d3608 100644 --- a/deepspeech/training/optimizer.py +++ b/paddlespeech/s2t/training/optimizer.py @@ -19,10 +19,10 @@ import paddle from paddle.optimizer import Optimizer from paddle.regularizer import L2Decay -from deepspeech.training.gradclip import ClipGradByGlobalNormWithLog -from deepspeech.utils.dynamic_import import dynamic_import -from deepspeech.utils.dynamic_import import instance_class -from deepspeech.utils.log import Log +from paddlespeech.s2t.training.gradclip import ClipGradByGlobalNormWithLog +from paddlespeech.s2t.utils.dynamic_import import dynamic_import +from paddlespeech.s2t.utils.dynamic_import import instance_class +from paddlespeech.s2t.utils.log import Log __all__ = ["OptimizerFactory"] diff --git a/deepspeech/training/reporter.py b/paddlespeech/s2t/training/reporter.py similarity index 100% rename from deepspeech/training/reporter.py rename to paddlespeech/s2t/training/reporter.py diff --git a/deepspeech/training/scheduler.py b/paddlespeech/s2t/training/scheduler.py similarity index 95% rename from deepspeech/training/scheduler.py rename to paddlespeech/s2t/training/scheduler.py index bb53281a8a11efa66d607d2cf15fe992d8364eb8..f850f6f5026c64babb62fa8b666db484033e0064 100644 --- a/deepspeech/training/scheduler.py +++ b/paddlespeech/s2t/training/scheduler.py @@ -19,9 +19,9 @@ from typing import Union from paddle.optimizer.lr import LRScheduler from typeguard import check_argument_types -from deepspeech.utils.dynamic_import import dynamic_import -from deepspeech.utils.dynamic_import import instance_class -from deepspeech.utils.log import Log +from paddlespeech.s2t.utils.dynamic_import import dynamic_import +from paddlespeech.s2t.utils.dynamic_import import instance_class +from paddlespeech.s2t.utils.log import Log __all__ = ["WarmupLR", "LRSchedulerFactory"] diff --git a/deepspeech/training/timer.py b/paddlespeech/s2t/training/timer.py similarity index 97% rename from deepspeech/training/timer.py rename to paddlespeech/s2t/training/timer.py index 2ca9d6386de45074ac76c7c754f89cefa36c5459..271ffff1b24e8038c68754fc217e76a1faa30e5d 100644 --- a/deepspeech/training/timer.py +++ b/paddlespeech/s2t/training/timer.py @@ -14,7 +14,7 @@ import datetime import time -from deepspeech.utils.log import Log +from paddlespeech.s2t.utils.log import Log __all__ = ["Timer"] diff --git a/deepspeech/training/trainer.py b/paddlespeech/s2t/training/trainer.py similarity index 97% rename from deepspeech/training/trainer.py rename to paddlespeech/s2t/training/trainer.py index 71a27ed241ae7d7f734f6b854e16abb9b1f7876d..e6328cdf73797fc57b012104acf80838cb6796f0 100644 --- a/deepspeech/training/trainer.py +++ b/paddlespeech/s2t/training/trainer.py @@ -21,16 +21,16 @@ import paddle from paddle import distributed as dist from tensorboardX import SummaryWriter -from deepspeech.training.reporter import ObsScope -from deepspeech.training.reporter import report -from deepspeech.training.timer import Timer -from deepspeech.utils import mp_tools -from deepspeech.utils import profiler -from deepspeech.utils.checkpoint import Checkpoint -from deepspeech.utils.log import Log -from deepspeech.utils.utility import all_version -from deepspeech.utils.utility import seed_all -from deepspeech.utils.utility import UpdateConfig +from paddlespeech.s2t.training.reporter import ObsScope +from paddlespeech.s2t.training.reporter import report +from paddlespeech.s2t.training.timer import Timer +from paddlespeech.s2t.utils import mp_tools +from paddlespeech.s2t.utils import profiler +from paddlespeech.s2t.utils.checkpoint import Checkpoint +from paddlespeech.s2t.utils.log import Log +from paddlespeech.s2t.utils.utility import all_version +from paddlespeech.s2t.utils.utility import seed_all +from paddlespeech.s2t.utils.utility import UpdateConfig __all__ = ["Trainer"] diff --git a/deepspeech/training/triggers/__init__.py b/paddlespeech/s2t/training/triggers/__init__.py similarity index 100% rename from deepspeech/training/triggers/__init__.py rename to paddlespeech/s2t/training/triggers/__init__.py diff --git a/deepspeech/training/triggers/compare_value_trigger.py b/paddlespeech/s2t/training/triggers/compare_value_trigger.py similarity index 100% rename from deepspeech/training/triggers/compare_value_trigger.py rename to paddlespeech/s2t/training/triggers/compare_value_trigger.py diff --git a/deepspeech/training/triggers/interval_trigger.py b/paddlespeech/s2t/training/triggers/interval_trigger.py similarity index 100% rename from deepspeech/training/triggers/interval_trigger.py rename to paddlespeech/s2t/training/triggers/interval_trigger.py diff --git a/deepspeech/training/triggers/limit_trigger.py b/paddlespeech/s2t/training/triggers/limit_trigger.py similarity index 100% rename from deepspeech/training/triggers/limit_trigger.py rename to paddlespeech/s2t/training/triggers/limit_trigger.py diff --git a/deepspeech/training/triggers/time_trigger.py b/paddlespeech/s2t/training/triggers/time_trigger.py similarity index 100% rename from deepspeech/training/triggers/time_trigger.py rename to paddlespeech/s2t/training/triggers/time_trigger.py diff --git a/deepspeech/training/triggers/utils.py b/paddlespeech/s2t/training/triggers/utils.py similarity index 100% rename from deepspeech/training/triggers/utils.py rename to paddlespeech/s2t/training/triggers/utils.py diff --git a/deepspeech/training/updaters/__init__.py b/paddlespeech/s2t/training/updaters/__init__.py similarity index 100% rename from deepspeech/training/updaters/__init__.py rename to paddlespeech/s2t/training/updaters/__init__.py diff --git a/deepspeech/training/updaters/standard_updater.py b/paddlespeech/s2t/training/updaters/standard_updater.py similarity index 97% rename from deepspeech/training/updaters/standard_updater.py rename to paddlespeech/s2t/training/updaters/standard_updater.py index 10c99e7fced7ae94cb09b630e38d21e4153ddbb2..83180a38d6e30500c23dc3b900655ce205baafd5 100644 --- a/deepspeech/training/updaters/standard_updater.py +++ b/paddlespeech/s2t/training/updaters/standard_updater.py @@ -21,10 +21,10 @@ from paddle.nn import Layer from paddle.optimizer import Optimizer from paddle.optimizer.lr import LRScheduler -from deepspeech.training.reporter import report -from deepspeech.training.updaters.updater import UpdaterBase -from deepspeech.training.updaters.updater import UpdaterState -from deepspeech.utils.log import Log +from paddlespeech.s2t.training.reporter import report +from paddlespeech.s2t.training.updaters.updater import UpdaterBase +from paddlespeech.s2t.training.updaters.updater import UpdaterState +from paddlespeech.s2t.utils.log import Log __all__ = ["StandardUpdater"] diff --git a/deepspeech/training/updaters/trainer.py b/paddlespeech/s2t/training/updaters/trainer.py similarity index 94% rename from deepspeech/training/updaters/trainer.py rename to paddlespeech/s2t/training/updaters/trainer.py index 077694659505a7d9e65b70db0f2a54198a03da09..dcf844e360a11963ed0d4d875877df128011e60e 100644 --- a/deepspeech/training/updaters/trainer.py +++ b/paddlespeech/s2t/training/updaters/trainer.py @@ -22,12 +22,12 @@ from typing import Union import six import tqdm -from deepspeech.training.extensions.extension import Extension -from deepspeech.training.extensions.extension import PRIORITY_READER -from deepspeech.training.reporter import ObsScope -from deepspeech.training.triggers import get_trigger -from deepspeech.training.triggers.limit_trigger import LimitTrigger -from deepspeech.training.updaters.updater import UpdaterBase +from paddlespeech.s2t.training.extensions.extension import Extension +from paddlespeech.s2t.training.extensions.extension import PRIORITY_READER +from paddlespeech.s2t.training.reporter import ObsScope +from paddlespeech.s2t.training.triggers import get_trigger +from paddlespeech.s2t.training.triggers.limit_trigger import LimitTrigger +from paddlespeech.s2t.training.updaters.updater import UpdaterBase class _ExtensionEntry(): diff --git a/deepspeech/training/updaters/updater.py b/paddlespeech/s2t/training/updaters/updater.py similarity index 98% rename from deepspeech/training/updaters/updater.py rename to paddlespeech/s2t/training/updaters/updater.py index e5dd65563dd846f8c01dbe68e2c01a931631a311..ff8d925ffcf1525e75816f73355c8a92cf0cd4df 100644 --- a/deepspeech/training/updaters/updater.py +++ b/paddlespeech/s2t/training/updaters/updater.py @@ -15,7 +15,7 @@ from dataclasses import dataclass import paddle -from deepspeech.utils.log import Log +from paddlespeech.s2t.utils.log import Log __all__ = ["UpdaterBase", "UpdaterState"] diff --git a/deepspeech/transform/__init__.py b/paddlespeech/s2t/transform/__init__.py similarity index 100% rename from deepspeech/transform/__init__.py rename to paddlespeech/s2t/transform/__init__.py diff --git a/deepspeech/transform/add_deltas.py b/paddlespeech/s2t/transform/add_deltas.py similarity index 100% rename from deepspeech/transform/add_deltas.py rename to paddlespeech/s2t/transform/add_deltas.py diff --git a/deepspeech/transform/channel_selector.py b/paddlespeech/s2t/transform/channel_selector.py similarity index 100% rename from deepspeech/transform/channel_selector.py rename to paddlespeech/s2t/transform/channel_selector.py diff --git a/deepspeech/transform/cmvn.py b/paddlespeech/s2t/transform/cmvn.py similarity index 100% rename from deepspeech/transform/cmvn.py rename to paddlespeech/s2t/transform/cmvn.py diff --git a/deepspeech/transform/functional.py b/paddlespeech/s2t/transform/functional.py similarity index 94% rename from deepspeech/transform/functional.py rename to paddlespeech/s2t/transform/functional.py index 914e484e30e494bc1e1da3b05da03147a2eb1036..e23d55f9d382c79e4cf05e5c95b07d4dff220c51 100644 --- a/deepspeech/transform/functional.py +++ b/paddlespeech/s2t/transform/functional.py @@ -13,8 +13,8 @@ # limitations under the License. import inspect -from deepspeech.transform.transform_interface import TransformInterface -from deepspeech.utils.check_kwargs import check_kwargs +from paddlespeech.s2t.transform.transform_interface import TransformInterface +from paddlespeech.s2t.utils.check_kwargs import check_kwargs class FuncTrans(TransformInterface): diff --git a/deepspeech/transform/perturb.py b/paddlespeech/s2t/transform/perturb.py similarity index 99% rename from deepspeech/transform/perturb.py rename to paddlespeech/s2t/transform/perturb.py index e425fd2ee40db2d4f1bca3c82d76535c28453962..f7e8bb764c1f972fb3ec8243185542a24de2434e 100644 --- a/deepspeech/transform/perturb.py +++ b/paddlespeech/s2t/transform/perturb.py @@ -16,7 +16,7 @@ import numpy import scipy import soundfile -from deepspeech.io.reader import SoundHDF5File +from paddlespeech.s2t.io.reader import SoundHDF5File class SpeedPerturbation(): diff --git a/deepspeech/transform/spec_augment.py b/paddlespeech/s2t/transform/spec_augment.py similarity index 99% rename from deepspeech/transform/spec_augment.py rename to paddlespeech/s2t/transform/spec_augment.py index 0e5324e73952e56a5c768eb78bd0ba606496050c..01ead8addb9f8a3c720b51848f9b1e6e95d26e2c 100644 --- a/deepspeech/transform/spec_augment.py +++ b/paddlespeech/s2t/transform/spec_augment.py @@ -18,7 +18,7 @@ import numpy from PIL import Image from PIL.Image import BICUBIC -from deepspeech.transform.functional import FuncTrans +from paddlespeech.s2t.transform.functional import FuncTrans def time_warp(x, max_time_warp=80, inplace=False, mode="PIL"): diff --git a/deepspeech/transform/spectrogram.py b/paddlespeech/s2t/transform/spectrogram.py similarity index 100% rename from deepspeech/transform/spectrogram.py rename to paddlespeech/s2t/transform/spectrogram.py diff --git a/deepspeech/transform/transform_interface.py b/paddlespeech/s2t/transform/transform_interface.py similarity index 100% rename from deepspeech/transform/transform_interface.py rename to paddlespeech/s2t/transform/transform_interface.py diff --git a/deepspeech/transform/transformation.py b/paddlespeech/s2t/transform/transformation.py similarity index 78% rename from deepspeech/transform/transformation.py rename to paddlespeech/s2t/transform/transformation.py index afb1db28d03a272f80d7b7354f42a8f53d83e9fb..906048d72203728387fb18ce424cd089a8fd28a4 100644 --- a/deepspeech/transform/transformation.py +++ b/paddlespeech/s2t/transform/transformation.py @@ -21,31 +21,31 @@ from inspect import signature import yaml -from deepspeech.utils.dynamic_import import dynamic_import +from paddlespeech.s2t.utils.dynamic_import import dynamic_import # TODO(karita): inherit TransformInterface # TODO(karita): register cmd arguments in asr_train.py import_alias = dict( - identity="deepspeech.transform.transform_interface:Identity", - time_warp="deepspeech.transform.spec_augment:TimeWarp", - time_mask="deepspeech.transform.spec_augment:TimeMask", - freq_mask="deepspeech.transform.spec_augment:FreqMask", - spec_augment="deepspeech.transform.spec_augment:SpecAugment", - speed_perturbation="deepspeech.transform.perturb:SpeedPerturbation", - volume_perturbation="deepspeech.transform.perturb:VolumePerturbation", - noise_injection="deepspeech.transform.perturb:NoiseInjection", - bandpass_perturbation="deepspeech.transform.perturb:BandpassPerturbation", - rir_convolve="deepspeech.transform.perturb:RIRConvolve", - delta="deepspeech.transform.add_deltas:AddDeltas", - cmvn="deepspeech.transform.cmvn:CMVN", - utterance_cmvn="deepspeech.transform.cmvn:UtteranceCMVN", - fbank="deepspeech.transform.spectrogram:LogMelSpectrogram", - spectrogram="deepspeech.transform.spectrogram:Spectrogram", - stft="deepspeech.transform.spectrogram:Stft", - istft="deepspeech.transform.spectrogram:IStft", - stft2fbank="deepspeech.transform.spectrogram:Stft2LogMelSpectrogram", - wpe="deepspeech.transform.wpe:WPE", - channel_selector="deepspeech.transform.channel_selector:ChannelSelector", ) + identity="paddlespeech.s2t.transform.transform_interface:Identity", + time_warp="paddlespeech.s2t.transform.spec_augment:TimeWarp", + time_mask="paddlespeech.s2t.transform.spec_augment:TimeMask", + freq_mask="paddlespeech.s2t.transform.spec_augment:FreqMask", + spec_augment="paddlespeech.s2t.transform.spec_augment:SpecAugment", + speed_perturbation="paddlespeech.s2t.transform.perturb:SpeedPerturbation", + volume_perturbation="paddlespeech.s2t.transform.perturb:VolumePerturbation", + noise_injection="paddlespeech.s2t.transform.perturb:NoiseInjection", + bandpass_perturbation="paddlespeech.s2t.transform.perturb:BandpassPerturbation", + rir_convolve="paddlespeech.s2t.transform.perturb:RIRConvolve", + delta="paddlespeech.s2t.transform.add_deltas:AddDeltas", + cmvn="paddlespeech.s2t.transform.cmvn:CMVN", + utterance_cmvn="paddlespeech.s2t.transform.cmvn:UtteranceCMVN", + fbank="paddlespeech.s2t.transform.spectrogram:LogMelSpectrogram", + spectrogram="paddlespeech.s2t.transform.spectrogram:Spectrogram", + stft="paddlespeech.s2t.transform.spectrogram:Stft", + istft="paddlespeech.s2t.transform.spectrogram:IStft", + stft2fbank="paddlespeech.s2t.transform.spectrogram:Stft2LogMelSpectrogram", + wpe="paddlespeech.s2t.transform.wpe:WPE", + channel_selector="paddlespeech.s2t.transform.channel_selector:ChannelSelector", ) class Transformation(): diff --git a/deepspeech/transform/wpe.py b/paddlespeech/s2t/transform/wpe.py similarity index 100% rename from deepspeech/transform/wpe.py rename to paddlespeech/s2t/transform/wpe.py diff --git a/deepspeech/utils/__init__.py b/paddlespeech/s2t/utils/__init__.py similarity index 100% rename from deepspeech/utils/__init__.py rename to paddlespeech/s2t/utils/__init__.py diff --git a/deepspeech/utils/asr_utils.py b/paddlespeech/s2t/utils/asr_utils.py similarity index 100% rename from deepspeech/utils/asr_utils.py rename to paddlespeech/s2t/utils/asr_utils.py diff --git a/deepspeech/utils/bleu_score.py b/paddlespeech/s2t/utils/bleu_score.py similarity index 100% rename from deepspeech/utils/bleu_score.py rename to paddlespeech/s2t/utils/bleu_score.py diff --git a/deepspeech/utils/check_kwargs.py b/paddlespeech/s2t/utils/check_kwargs.py similarity index 100% rename from deepspeech/utils/check_kwargs.py rename to paddlespeech/s2t/utils/check_kwargs.py diff --git a/deepspeech/utils/checkpoint.py b/paddlespeech/s2t/utils/checkpoint.py similarity index 99% rename from deepspeech/utils/checkpoint.py rename to paddlespeech/s2t/utils/checkpoint.py index 796cafe045933b13fd3229f72dbcd68981e8046a..5105f95efaebf4347a0d13b4383a1db962835308 100644 --- a/deepspeech/utils/checkpoint.py +++ b/paddlespeech/s2t/utils/checkpoint.py @@ -23,8 +23,8 @@ import paddle from paddle import distributed as dist from paddle.optimizer import Optimizer -from deepspeech.utils import mp_tools -from deepspeech.utils.log import Log +from paddlespeech.s2t.utils import mp_tools +from paddlespeech.s2t.utils.log import Log logger = Log(__name__).getlog() diff --git a/deepspeech/utils/cli_readers.py b/paddlespeech/s2t/utils/cli_readers.py similarity index 99% rename from deepspeech/utils/cli_readers.py rename to paddlespeech/s2t/utils/cli_readers.py index 72aa2bdb73dd9747eccf762c90d7fb34ea4d1997..010adb7a92f4277e9e5c39b0c64636063b7eefff 100644 --- a/deepspeech/utils/cli_readers.py +++ b/paddlespeech/s2t/utils/cli_readers.py @@ -19,7 +19,7 @@ import h5py import kaldiio import soundfile -from deepspeech.io.reader import SoundHDF5File +from paddlespeech.s2t.io.reader import SoundHDF5File def file_reader_helper( diff --git a/deepspeech/utils/cli_utils.py b/paddlespeech/s2t/utils/cli_utils.py similarity index 100% rename from deepspeech/utils/cli_utils.py rename to paddlespeech/s2t/utils/cli_utils.py diff --git a/deepspeech/utils/cli_writers.py b/paddlespeech/s2t/utils/cli_writers.py similarity index 98% rename from deepspeech/utils/cli_writers.py rename to paddlespeech/s2t/utils/cli_writers.py index e07371934f346d5899447bdf2178f94f992200f4..5866a82eeb90503dca0c90d6d02262aeee6dd571 100644 --- a/deepspeech/utils/cli_writers.py +++ b/paddlespeech/s2t/utils/cli_writers.py @@ -19,8 +19,8 @@ import kaldiio import numpy import soundfile -from deepspeech.io.reader import SoundHDF5File -from deepspeech.utils.cli_utils import assert_scipy_wav_style +from paddlespeech.s2t.io.reader import SoundHDF5File +from paddlespeech.s2t.utils.cli_utils import assert_scipy_wav_style def file_writer_helper( diff --git a/deepspeech/utils/ctc_utils.py b/paddlespeech/s2t/utils/ctc_utils.py similarity index 98% rename from deepspeech/utils/ctc_utils.py rename to paddlespeech/s2t/utils/ctc_utils.py index 7e8629c2dbe65b51a8ac64028833c4cbcba20e7d..ff23350a3e38c95c92f470a169a39f74406df9db 100644 --- a/deepspeech/utils/ctc_utils.py +++ b/paddlespeech/s2t/utils/ctc_utils.py @@ -16,9 +16,9 @@ from typing import List import numpy as np import paddle -from deepspeech.utils import text_grid -from deepspeech.utils import utility -from deepspeech.utils.log import Log +from paddlespeech.s2t.utils import text_grid +from paddlespeech.s2t.utils import utility +from paddlespeech.s2t.utils.log import Log logger = Log(__name__).getlog() diff --git a/deepspeech/utils/dynamic_import.py b/paddlespeech/s2t/utils/dynamic_import.py similarity index 89% rename from deepspeech/utils/dynamic_import.py rename to paddlespeech/s2t/utils/dynamic_import.py index 533f15eeefdae8b7d13b8d8742cb5cbddc7696db..3eb0db145c2c849a0c8bb8be08e85c23b95ac627 100644 --- a/deepspeech/utils/dynamic_import.py +++ b/paddlespeech/s2t/utils/dynamic_import.py @@ -18,8 +18,8 @@ from typing import Dict from typing import List from typing import Text -from deepspeech.utils.log import Log -from deepspeech.utils.tensor_utils import has_tensor +from paddlespeech.s2t.utils.log import Log +from paddlespeech.s2t.utils.tensor_utils import has_tensor logger = Log(__name__).getlog() @@ -30,13 +30,13 @@ def dynamic_import(import_path, alias=dict()): """dynamic import module and class :param str import_path: syntax 'module_name:class_name' - e.g., 'deepspeech.models.u2:U2Model' + e.g., 'paddlespeech.s2t.models.u2:U2Model' :param dict alias: shortcut for registered class :return: imported class """ if import_path not in alias and ":" not in import_path: raise ValueError("import_path should be one of {} or " - 'include ":", e.g. "deepspeech.models.u2:U2Model" : ' + 'include ":", e.g. "paddlespeech.s2t.models.u2:U2Model" : ' "{}".format(set(alias), import_path)) if ":" not in import_path: import_path = alias[import_path] diff --git a/deepspeech/utils/error_rate.py b/paddlespeech/s2t/utils/error_rate.py similarity index 100% rename from deepspeech/utils/error_rate.py rename to paddlespeech/s2t/utils/error_rate.py diff --git a/deepspeech/utils/layer_tools.py b/paddlespeech/s2t/utils/layer_tools.py similarity index 100% rename from deepspeech/utils/layer_tools.py rename to paddlespeech/s2t/utils/layer_tools.py diff --git a/deepspeech/utils/log.py b/paddlespeech/s2t/utils/log.py similarity index 100% rename from deepspeech/utils/log.py rename to paddlespeech/s2t/utils/log.py diff --git a/deepspeech/utils/mp_tools.py b/paddlespeech/s2t/utils/mp_tools.py similarity index 100% rename from deepspeech/utils/mp_tools.py rename to paddlespeech/s2t/utils/mp_tools.py diff --git a/deepspeech/utils/profiler.py b/paddlespeech/s2t/utils/profiler.py similarity index 99% rename from deepspeech/utils/profiler.py rename to paddlespeech/s2t/utils/profiler.py index 5733f8ed5bc943d00de36a57852495aaf9320be6..3592157dc17eac5991bbaabdc1b757b7198827ef 100644 --- a/deepspeech/utils/profiler.py +++ b/paddlespeech/s2t/utils/profiler.py @@ -15,7 +15,7 @@ import sys import paddle -from deepspeech.utils.log import Log +from paddlespeech.s2t.utils.log import Log logger = Log(__name__).getlog() diff --git a/deepspeech/utils/socket_server.py b/paddlespeech/s2t/utils/socket_server.py similarity index 98% rename from deepspeech/utils/socket_server.py rename to paddlespeech/s2t/utils/socket_server.py index 45c659f6021043ca96424138f7f1f29c6649cba6..43b56d723c154c35be9b71afad67123bf99c238f 100644 --- a/deepspeech/utils/socket_server.py +++ b/paddlespeech/s2t/utils/socket_server.py @@ -21,7 +21,7 @@ import wave from time import gmtime from time import strftime -from deepspeech.frontend.utility import read_manifest +from paddlespeech.s2t.frontend.utility import read_manifest __all__ = ["socket_send", "warm_up_test", "AsrTCPServer", "AsrRequestHandler"] diff --git a/deepspeech/utils/spec_augment.py b/paddlespeech/s2t/utils/spec_augment.py similarity index 100% rename from deepspeech/utils/spec_augment.py rename to paddlespeech/s2t/utils/spec_augment.py diff --git a/deepspeech/utils/tensor_utils.py b/paddlespeech/s2t/utils/tensor_utils.py similarity index 99% rename from deepspeech/utils/tensor_utils.py rename to paddlespeech/s2t/utils/tensor_utils.py index 0cc03b1934e6adbc545945afbba7c1a44c2ce855..0dbaa0b6b77031d4b8e8aa29fcc9246458b8ab99 100644 --- a/deepspeech/utils/tensor_utils.py +++ b/paddlespeech/s2t/utils/tensor_utils.py @@ -17,7 +17,7 @@ from typing import Tuple import paddle -from deepspeech.utils.log import Log +from paddlespeech.s2t.utils.log import Log __all__ = ["pad_sequence", "add_sos_eos", "th_accuracy", "has_tensor"] diff --git a/deepspeech/utils/text_grid.py b/paddlespeech/s2t/utils/text_grid.py similarity index 100% rename from deepspeech/utils/text_grid.py rename to paddlespeech/s2t/utils/text_grid.py diff --git a/deepspeech/utils/utility.py b/paddlespeech/s2t/utils/utility.py similarity index 98% rename from deepspeech/utils/utility.py rename to paddlespeech/s2t/utils/utility.py index 8773b84ce7995e14ff36f7872a4cd7c3ebe94008..73c7981668c07bae2fcad2190fc8a5bae3c2dc31 100644 --- a/deepspeech/utils/utility.py +++ b/paddlespeech/s2t/utils/utility.py @@ -25,7 +25,7 @@ import numpy as np import paddle import soundfile -from deepspeech.utils.log import Log +from paddlespeech.s2t.utils.log import Log logger = Log(__name__).getlog() diff --git a/parakeet/__init__.py b/paddlespeech/t2s/__init__.py similarity index 100% rename from parakeet/__init__.py rename to paddlespeech/t2s/__init__.py diff --git a/parakeet/audio/__init__.py b/paddlespeech/t2s/audio/__init__.py similarity index 100% rename from parakeet/audio/__init__.py rename to paddlespeech/t2s/audio/__init__.py diff --git a/parakeet/audio/audio.py b/paddlespeech/t2s/audio/audio.py similarity index 100% rename from parakeet/audio/audio.py rename to paddlespeech/t2s/audio/audio.py diff --git a/parakeet/audio/spec_normalizer.py b/paddlespeech/t2s/audio/spec_normalizer.py similarity index 100% rename from parakeet/audio/spec_normalizer.py rename to paddlespeech/t2s/audio/spec_normalizer.py diff --git a/parakeet/data/__init__.py b/paddlespeech/t2s/data/__init__.py similarity index 92% rename from parakeet/data/__init__.py rename to paddlespeech/t2s/data/__init__.py index c71c05bd7f0218d0bc373e57386aa46eeea0fdb4..c605205d6f975716536d387e65feba70df292f9c 100644 --- a/parakeet/data/__init__.py +++ b/paddlespeech/t2s/data/__init__.py @@ -11,7 +11,7 @@ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. -"""Parakeet's infrastructure for data processing. +"""t2s's infrastructure for data processing. """ from .batch import * from .dataset import * diff --git a/parakeet/data/batch.py b/paddlespeech/t2s/data/batch.py similarity index 100% rename from parakeet/data/batch.py rename to paddlespeech/t2s/data/batch.py diff --git a/parakeet/data/dataset.py b/paddlespeech/t2s/data/dataset.py similarity index 100% rename from parakeet/data/dataset.py rename to paddlespeech/t2s/data/dataset.py diff --git a/parakeet/data/get_feats.py b/paddlespeech/t2s/data/get_feats.py similarity index 100% rename from parakeet/data/get_feats.py rename to paddlespeech/t2s/data/get_feats.py diff --git a/parakeet/datasets/__init__.py b/paddlespeech/t2s/datasets/__init__.py similarity index 100% rename from parakeet/datasets/__init__.py rename to paddlespeech/t2s/datasets/__init__.py diff --git a/parakeet/datasets/am_batch_fn.py b/paddlespeech/t2s/datasets/am_batch_fn.py similarity index 99% rename from parakeet/datasets/am_batch_fn.py rename to paddlespeech/t2s/datasets/am_batch_fn.py index 42d5babd0c6bb9e3567d5dd914f1b38ad0580e7f..5ed9aa7af1d9ed9337a1a0cb3709b5ae11d2143f 100644 --- a/parakeet/datasets/am_batch_fn.py +++ b/paddlespeech/t2s/datasets/am_batch_fn.py @@ -14,7 +14,7 @@ import numpy as np import paddle -from parakeet.data.batch import batch_sequences +from paddlespeech.t2s.data.batch import batch_sequences def speedyspeech_batch_fn(examples): diff --git a/parakeet/datasets/common.py b/paddlespeech/t2s/datasets/common.py similarity index 100% rename from parakeet/datasets/common.py rename to paddlespeech/t2s/datasets/common.py diff --git a/parakeet/datasets/data_table.py b/paddlespeech/t2s/datasets/data_table.py similarity index 100% rename from parakeet/datasets/data_table.py rename to paddlespeech/t2s/datasets/data_table.py diff --git a/parakeet/datasets/ljspeech.py b/paddlespeech/t2s/datasets/ljspeech.py similarity index 100% rename from parakeet/datasets/ljspeech.py rename to paddlespeech/t2s/datasets/ljspeech.py diff --git a/parakeet/datasets/preprocess_utils.py b/paddlespeech/t2s/datasets/preprocess_utils.py similarity index 100% rename from parakeet/datasets/preprocess_utils.py rename to paddlespeech/t2s/datasets/preprocess_utils.py diff --git a/parakeet/datasets/vocoder_batch_fn.py b/paddlespeech/t2s/datasets/vocoder_batch_fn.py similarity index 100% rename from parakeet/datasets/vocoder_batch_fn.py rename to paddlespeech/t2s/datasets/vocoder_batch_fn.py diff --git a/parakeet/exps/__init__.py b/paddlespeech/t2s/exps/__init__.py similarity index 100% rename from parakeet/exps/__init__.py rename to paddlespeech/t2s/exps/__init__.py diff --git a/parakeet/exps/fastspeech2/__init__.py b/paddlespeech/t2s/exps/fastspeech2/__init__.py similarity index 100% rename from parakeet/exps/fastspeech2/__init__.py rename to paddlespeech/t2s/exps/fastspeech2/__init__.py diff --git a/parakeet/exps/fastspeech2/inference.py b/paddlespeech/t2s/exps/fastspeech2/inference.py similarity index 98% rename from parakeet/exps/fastspeech2/inference.py rename to paddlespeech/t2s/exps/fastspeech2/inference.py index 4367608874ad3ca5fbacb7f6c473a775acb6eed6..07e9ed7ee33cf2408f15ceb6a9b620d691614253 100644 --- a/parakeet/exps/fastspeech2/inference.py +++ b/paddlespeech/t2s/exps/fastspeech2/inference.py @@ -18,7 +18,7 @@ from pathlib import Path import soundfile as sf from paddle import inference -from parakeet.frontend.zh_frontend import Frontend +from paddlespeech.t2s.frontend.zh_frontend import Frontend def main(): diff --git a/parakeet/exps/fastspeech2/multi_spk_synthesize_e2e.py b/paddlespeech/t2s/exps/fastspeech2/multi_spk_synthesize_e2e.py similarity index 93% rename from parakeet/exps/fastspeech2/multi_spk_synthesize_e2e.py rename to paddlespeech/t2s/exps/fastspeech2/multi_spk_synthesize_e2e.py index 825b3ed364f0673913fb10cb519808cb7f07b9a9..98cf9f8f200eac99d14304500830cc8cc005d2dc 100644 --- a/parakeet/exps/fastspeech2/multi_spk_synthesize_e2e.py +++ b/paddlespeech/t2s/exps/fastspeech2/multi_spk_synthesize_e2e.py @@ -21,12 +21,12 @@ import soundfile as sf import yaml from yacs.config import CfgNode -from parakeet.frontend.zh_frontend import Frontend -from parakeet.models.fastspeech2 import FastSpeech2 -from parakeet.models.fastspeech2 import FastSpeech2Inference -from parakeet.models.parallel_wavegan import PWGGenerator -from parakeet.models.parallel_wavegan import PWGInference -from parakeet.modules.normalizer import ZScore +from paddlespeech.t2s.frontend.zh_frontend import Frontend +from paddlespeech.t2s.models.fastspeech2 import FastSpeech2 +from paddlespeech.t2s.models.fastspeech2 import FastSpeech2Inference +from paddlespeech.t2s.models.parallel_wavegan import PWGGenerator +from paddlespeech.t2s.models.parallel_wavegan import PWGInference +from paddlespeech.t2s.modules.normalizer import ZScore def evaluate(args, fastspeech2_config, pwg_config): diff --git a/parakeet/exps/fastspeech2/multi_spk_synthesize_e2e_en.py b/paddlespeech/t2s/exps/fastspeech2/multi_spk_synthesize_e2e_en.py similarity index 94% rename from parakeet/exps/fastspeech2/multi_spk_synthesize_e2e_en.py rename to paddlespeech/t2s/exps/fastspeech2/multi_spk_synthesize_e2e_en.py index a476198269af4ba4271eb3ab24a98cd04956fb83..9e29eea1948a92e3ef7d1134e2200a883f045d61 100644 --- a/parakeet/exps/fastspeech2/multi_spk_synthesize_e2e_en.py +++ b/paddlespeech/t2s/exps/fastspeech2/multi_spk_synthesize_e2e_en.py @@ -21,12 +21,12 @@ import soundfile as sf import yaml from yacs.config import CfgNode -from parakeet.frontend import English -from parakeet.models.fastspeech2 import FastSpeech2 -from parakeet.models.fastspeech2 import FastSpeech2Inference -from parakeet.models.parallel_wavegan import PWGGenerator -from parakeet.models.parallel_wavegan import PWGInference -from parakeet.modules.normalizer import ZScore +from paddlespeech.t2s.frontend import English +from paddlespeech.t2s.models.fastspeech2 import FastSpeech2 +from paddlespeech.t2s.models.fastspeech2 import FastSpeech2Inference +from paddlespeech.t2s.models.parallel_wavegan import PWGGenerator +from paddlespeech.t2s.models.parallel_wavegan import PWGInference +from paddlespeech.t2s.modules.normalizer import ZScore def evaluate(args, fastspeech2_config, pwg_config): diff --git a/parakeet/exps/fastspeech2/normalize.py b/paddlespeech/t2s/exps/fastspeech2/normalize.py similarity index 99% rename from parakeet/exps/fastspeech2/normalize.py rename to paddlespeech/t2s/exps/fastspeech2/normalize.py index b4b31e3111b00b66fa71d1609ef687307450b816..7283f6b430c92de51db9fe9398cf2ec0f8b3ea5a 100644 --- a/parakeet/exps/fastspeech2/normalize.py +++ b/paddlespeech/t2s/exps/fastspeech2/normalize.py @@ -22,7 +22,7 @@ import numpy as np from sklearn.preprocessing import StandardScaler from tqdm import tqdm -from parakeet.datasets.data_table import DataTable +from paddlespeech.t2s.datasets.data_table import DataTable def main(): diff --git a/parakeet/exps/fastspeech2/preprocess.py b/paddlespeech/t2s/exps/fastspeech2/preprocess.py similarity index 95% rename from parakeet/exps/fastspeech2/preprocess.py rename to paddlespeech/t2s/exps/fastspeech2/preprocess.py index bb796b64c7b969483c3cb2afa947de7c19dd6751..3702ecd314abe9318a465df2fb607885f0f04d2a 100644 --- a/parakeet/exps/fastspeech2/preprocess.py +++ b/paddlespeech/t2s/exps/fastspeech2/preprocess.py @@ -27,14 +27,14 @@ import tqdm import yaml from yacs.config import CfgNode -from parakeet.data.get_feats import Energy -from parakeet.data.get_feats import LogMelFBank -from parakeet.data.get_feats import Pitch -from parakeet.datasets.preprocess_utils import compare_duration_and_mel_length -from parakeet.datasets.preprocess_utils import get_input_token -from parakeet.datasets.preprocess_utils import get_phn_dur -from parakeet.datasets.preprocess_utils import get_spk_id_map -from parakeet.datasets.preprocess_utils import merge_silence +from paddlespeech.t2s.data.get_feats import Energy +from paddlespeech.t2s.data.get_feats import LogMelFBank +from paddlespeech.t2s.data.get_feats import Pitch +from paddlespeech.t2s.datasets.preprocess_utils import compare_duration_and_mel_length +from paddlespeech.t2s.datasets.preprocess_utils import get_input_token +from paddlespeech.t2s.datasets.preprocess_utils import get_phn_dur +from paddlespeech.t2s.datasets.preprocess_utils import get_spk_id_map +from paddlespeech.t2s.datasets.preprocess_utils import merge_silence def process_sentence(config: Dict[str, Any], diff --git a/parakeet/exps/fastspeech2/synthesize.py b/paddlespeech/t2s/exps/fastspeech2/synthesize.py similarity index 93% rename from parakeet/exps/fastspeech2/synthesize.py rename to paddlespeech/t2s/exps/fastspeech2/synthesize.py index 913277571de5d1568eccccbc18ba310232c815c5..1beac5ceb994de811faf5758929e35ca6595c3ff 100644 --- a/parakeet/exps/fastspeech2/synthesize.py +++ b/paddlespeech/t2s/exps/fastspeech2/synthesize.py @@ -22,12 +22,12 @@ import soundfile as sf import yaml from yacs.config import CfgNode -from parakeet.datasets.data_table import DataTable -from parakeet.models.fastspeech2 import FastSpeech2 -from parakeet.models.fastspeech2 import FastSpeech2Inference -from parakeet.models.parallel_wavegan import PWGGenerator -from parakeet.models.parallel_wavegan import PWGInference -from parakeet.modules.normalizer import ZScore +from paddlespeech.t2s.datasets.data_table import DataTable +from paddlespeech.t2s.models.fastspeech2 import FastSpeech2 +from paddlespeech.t2s.models.fastspeech2 import FastSpeech2Inference +from paddlespeech.t2s.models.parallel_wavegan import PWGGenerator +from paddlespeech.t2s.models.parallel_wavegan import PWGInference +from paddlespeech.t2s.modules.normalizer import ZScore def evaluate(args, fastspeech2_config, pwg_config): diff --git a/parakeet/exps/fastspeech2/synthesize_e2e.py b/paddlespeech/t2s/exps/fastspeech2/synthesize_e2e.py similarity index 94% rename from parakeet/exps/fastspeech2/synthesize_e2e.py rename to paddlespeech/t2s/exps/fastspeech2/synthesize_e2e.py index 9c036e9fc91f5335e74c841d04813dd1ef0f3187..b6a8fc587cb64d574bd2f03da44de232d11028a8 100644 --- a/parakeet/exps/fastspeech2/synthesize_e2e.py +++ b/paddlespeech/t2s/exps/fastspeech2/synthesize_e2e.py @@ -24,12 +24,12 @@ from paddle import jit from paddle.static import InputSpec from yacs.config import CfgNode -from parakeet.frontend.zh_frontend import Frontend -from parakeet.models.fastspeech2 import FastSpeech2 -from parakeet.models.fastspeech2 import FastSpeech2Inference -from parakeet.models.parallel_wavegan import PWGGenerator -from parakeet.models.parallel_wavegan import PWGInference -from parakeet.modules.normalizer import ZScore +from paddlespeech.t2s.frontend.zh_frontend import Frontend +from paddlespeech.t2s.models.fastspeech2 import FastSpeech2 +from paddlespeech.t2s.models.fastspeech2 import FastSpeech2Inference +from paddlespeech.t2s.models.parallel_wavegan import PWGGenerator +from paddlespeech.t2s.models.parallel_wavegan import PWGInference +from paddlespeech.t2s.modules.normalizer import ZScore def evaluate(args, fastspeech2_config, pwg_config): diff --git a/parakeet/exps/fastspeech2/synthesize_e2e_en.py b/paddlespeech/t2s/exps/fastspeech2/synthesize_e2e_en.py similarity index 93% rename from parakeet/exps/fastspeech2/synthesize_e2e_en.py rename to paddlespeech/t2s/exps/fastspeech2/synthesize_e2e_en.py index 4e8a20c757e1c4925d5f46134f0bf7a36d08be9d..7a55fbb12a9f79984e1243a503db87dac87a4b61 100644 --- a/parakeet/exps/fastspeech2/synthesize_e2e_en.py +++ b/paddlespeech/t2s/exps/fastspeech2/synthesize_e2e_en.py @@ -21,12 +21,12 @@ import soundfile as sf import yaml from yacs.config import CfgNode -from parakeet.frontend import English -from parakeet.models.fastspeech2 import FastSpeech2 -from parakeet.models.fastspeech2 import FastSpeech2Inference -from parakeet.models.parallel_wavegan import PWGGenerator -from parakeet.models.parallel_wavegan import PWGInference -from parakeet.modules.normalizer import ZScore +from paddlespeech.t2s.frontend import English +from paddlespeech.t2s.models.fastspeech2 import FastSpeech2 +from paddlespeech.t2s.models.fastspeech2 import FastSpeech2Inference +from paddlespeech.t2s.models.parallel_wavegan import PWGGenerator +from paddlespeech.t2s.models.parallel_wavegan import PWGInference +from paddlespeech.t2s.modules.normalizer import ZScore def evaluate(args, fastspeech2_config, pwg_config): diff --git a/parakeet/exps/fastspeech2/synthesize_e2e_melgan.py b/paddlespeech/t2s/exps/fastspeech2/synthesize_e2e_melgan.py similarity index 94% rename from parakeet/exps/fastspeech2/synthesize_e2e_melgan.py rename to paddlespeech/t2s/exps/fastspeech2/synthesize_e2e_melgan.py index 9fba95934fa4243ada81101ef58440fed149e619..92a43d5c4bb93071c388fa4f4c96f82bd795f9a7 100644 --- a/parakeet/exps/fastspeech2/synthesize_e2e_melgan.py +++ b/paddlespeech/t2s/exps/fastspeech2/synthesize_e2e_melgan.py @@ -24,12 +24,12 @@ from paddle import jit from paddle.static import InputSpec from yacs.config import CfgNode -from parakeet.frontend.zh_frontend import Frontend -from parakeet.models.fastspeech2 import FastSpeech2 -from parakeet.models.fastspeech2 import FastSpeech2Inference -from parakeet.models.melgan import MelGANGenerator -from parakeet.models.melgan import MelGANInference -from parakeet.modules.normalizer import ZScore +from paddlespeech.t2s.frontend.zh_frontend import Frontend +from paddlespeech.t2s.models.fastspeech2 import FastSpeech2 +from paddlespeech.t2s.models.fastspeech2 import FastSpeech2Inference +from paddlespeech.t2s.models.melgan import MelGANGenerator +from paddlespeech.t2s.models.melgan import MelGANInference +from paddlespeech.t2s.modules.normalizer import ZScore def evaluate(args, fastspeech2_config, melgan_config): diff --git a/parakeet/exps/fastspeech2/train.py b/paddlespeech/t2s/exps/fastspeech2/train.py similarity index 89% rename from parakeet/exps/fastspeech2/train.py rename to paddlespeech/t2s/exps/fastspeech2/train.py index 47ad1b4dac0ca66bea057a67de26d28659d75f81..5662d15dc8c2e6ca886e937a120e0e43c8351370 100644 --- a/parakeet/exps/fastspeech2/train.py +++ b/paddlespeech/t2s/exps/fastspeech2/train.py @@ -27,17 +27,17 @@ from paddle.io import DataLoader from paddle.io import DistributedBatchSampler from yacs.config import CfgNode -from parakeet.datasets.am_batch_fn import fastspeech2_multi_spk_batch_fn -from parakeet.datasets.am_batch_fn import fastspeech2_single_spk_batch_fn -from parakeet.datasets.data_table import DataTable -from parakeet.models.fastspeech2 import FastSpeech2 -from parakeet.models.fastspeech2 import FastSpeech2Evaluator -from parakeet.models.fastspeech2 import FastSpeech2Updater -from parakeet.training.extensions.snapshot import Snapshot -from parakeet.training.extensions.visualizer import VisualDL -from parakeet.training.optimizer import build_optimizers -from parakeet.training.seeding import seed_everything -from parakeet.training.trainer import Trainer +from paddlespeech.t2s.datasets.am_batch_fn import fastspeech2_multi_spk_batch_fn +from paddlespeech.t2s.datasets.am_batch_fn import fastspeech2_single_spk_batch_fn +from paddlespeech.t2s.datasets.data_table import DataTable +from paddlespeech.t2s.models.fastspeech2 import FastSpeech2 +from paddlespeech.t2s.models.fastspeech2 import FastSpeech2Evaluator +from paddlespeech.t2s.models.fastspeech2 import FastSpeech2Updater +from paddlespeech.t2s.training.extensions.snapshot import Snapshot +from paddlespeech.t2s.training.extensions.visualizer import VisualDL +from paddlespeech.t2s.training.optimizer import build_optimizers +from paddlespeech.t2s.training.seeding import seed_everything +from paddlespeech.t2s.training.trainer import Trainer def train_sp(args, config): diff --git a/parakeet/exps/gan_vocoder/README.md b/paddlespeech/t2s/exps/gan_vocoder/README.md similarity index 100% rename from parakeet/exps/gan_vocoder/README.md rename to paddlespeech/t2s/exps/gan_vocoder/README.md diff --git a/parakeet/exps/gan_vocoder/__init__.py b/paddlespeech/t2s/exps/gan_vocoder/__init__.py similarity index 100% rename from parakeet/exps/gan_vocoder/__init__.py rename to paddlespeech/t2s/exps/gan_vocoder/__init__.py diff --git a/parakeet/exps/gan_vocoder/multi_band_melgan/__init__.py b/paddlespeech/t2s/exps/gan_vocoder/multi_band_melgan/__init__.py similarity index 100% rename from parakeet/exps/gan_vocoder/multi_band_melgan/__init__.py rename to paddlespeech/t2s/exps/gan_vocoder/multi_band_melgan/__init__.py diff --git a/parakeet/exps/gan_vocoder/multi_band_melgan/synthesize.py b/paddlespeech/t2s/exps/gan_vocoder/multi_band_melgan/synthesize.py similarity index 96% rename from parakeet/exps/gan_vocoder/multi_band_melgan/synthesize.py rename to paddlespeech/t2s/exps/gan_vocoder/multi_band_melgan/synthesize.py index 00b1b96c8befe556c3faff800ca4fc56e60b7dab..720b08ce90805f48bb2c0be39e8cbc4bb4fe7d26 100644 --- a/parakeet/exps/gan_vocoder/multi_band_melgan/synthesize.py +++ b/paddlespeech/t2s/exps/gan_vocoder/multi_band_melgan/synthesize.py @@ -24,8 +24,8 @@ from paddle import distributed as dist from timer import timer from yacs.config import CfgNode -from parakeet.datasets.data_table import DataTable -from parakeet.models.melgan import MelGANGenerator +from paddlespeech.t2s.datasets.data_table import DataTable +from paddlespeech.t2s.models.melgan import MelGANGenerator def main(): diff --git a/parakeet/exps/gan_vocoder/multi_band_melgan/train.py b/paddlespeech/t2s/exps/gan_vocoder/multi_band_melgan/train.py similarity index 90% rename from parakeet/exps/gan_vocoder/multi_band_melgan/train.py rename to paddlespeech/t2s/exps/gan_vocoder/multi_band_melgan/train.py index c03fb354b9ac0845b31c293569a877afb8591ce8..45704607137be143a9354a98a71f400d1b1b471c 100644 --- a/parakeet/exps/gan_vocoder/multi_band_melgan/train.py +++ b/paddlespeech/t2s/exps/gan_vocoder/multi_band_melgan/train.py @@ -30,20 +30,20 @@ from paddle.optimizer import Adam from paddle.optimizer.lr import MultiStepDecay from yacs.config import CfgNode -from parakeet.datasets.data_table import DataTable -from parakeet.datasets.vocoder_batch_fn import Clip -from parakeet.models.melgan import MBMelGANEvaluator -from parakeet.models.melgan import MBMelGANUpdater -from parakeet.models.melgan import MelGANGenerator -from parakeet.models.melgan import MelGANMultiScaleDiscriminator -from parakeet.modules.adversarial_loss import DiscriminatorAdversarialLoss -from parakeet.modules.adversarial_loss import GeneratorAdversarialLoss -from parakeet.modules.pqmf import PQMF -from parakeet.modules.stft_loss import MultiResolutionSTFTLoss -from parakeet.training.extensions.snapshot import Snapshot -from parakeet.training.extensions.visualizer import VisualDL -from parakeet.training.seeding import seed_everything -from parakeet.training.trainer import Trainer +from paddlespeech.t2s.datasets.data_table import DataTable +from paddlespeech.t2s.datasets.vocoder_batch_fn import Clip +from paddlespeech.t2s.models.melgan import MBMelGANEvaluator +from paddlespeech.t2s.models.melgan import MBMelGANUpdater +from paddlespeech.t2s.models.melgan import MelGANGenerator +from paddlespeech.t2s.models.melgan import MelGANMultiScaleDiscriminator +from paddlespeech.t2s.modules.adversarial_loss import DiscriminatorAdversarialLoss +from paddlespeech.t2s.modules.adversarial_loss import GeneratorAdversarialLoss +from paddlespeech.t2s.modules.pqmf import PQMF +from paddlespeech.t2s.modules.stft_loss import MultiResolutionSTFTLoss +from paddlespeech.t2s.training.extensions.snapshot import Snapshot +from paddlespeech.t2s.training.extensions.visualizer import VisualDL +from paddlespeech.t2s.training.seeding import seed_everything +from paddlespeech.t2s.training.trainer import Trainer def train_sp(args, config): diff --git a/parakeet/exps/gan_vocoder/normalize.py b/paddlespeech/t2s/exps/gan_vocoder/normalize.py similarity index 98% rename from parakeet/exps/gan_vocoder/normalize.py rename to paddlespeech/t2s/exps/gan_vocoder/normalize.py index c772594bb499378ff7c537125faa58be532e0e36..ba95d3ed61e341ebc458846a1f79099066c2cc7a 100644 --- a/parakeet/exps/gan_vocoder/normalize.py +++ b/paddlespeech/t2s/exps/gan_vocoder/normalize.py @@ -22,7 +22,7 @@ import numpy as np from sklearn.preprocessing import StandardScaler from tqdm import tqdm -from parakeet.datasets.data_table import DataTable +from paddlespeech.t2s.datasets.data_table import DataTable def main(): diff --git a/parakeet/exps/gan_vocoder/parallelwave_gan/__init__.py b/paddlespeech/t2s/exps/gan_vocoder/parallelwave_gan/__init__.py similarity index 100% rename from parakeet/exps/gan_vocoder/parallelwave_gan/__init__.py rename to paddlespeech/t2s/exps/gan_vocoder/parallelwave_gan/__init__.py diff --git a/parakeet/exps/gan_vocoder/parallelwave_gan/synthesize.py b/paddlespeech/t2s/exps/gan_vocoder/parallelwave_gan/synthesize.py similarity index 96% rename from parakeet/exps/gan_vocoder/parallelwave_gan/synthesize.py rename to paddlespeech/t2s/exps/gan_vocoder/parallelwave_gan/synthesize.py index 2400e00b4eb131b1b029d3e2c4b3a45f01a81a23..ce90aaf4dbd8152ae8b2890fd2868042b0fb06e7 100644 --- a/parakeet/exps/gan_vocoder/parallelwave_gan/synthesize.py +++ b/paddlespeech/t2s/exps/gan_vocoder/parallelwave_gan/synthesize.py @@ -24,8 +24,8 @@ from paddle import distributed as dist from timer import timer from yacs.config import CfgNode -from parakeet.datasets.data_table import DataTable -from parakeet.models.parallel_wavegan import PWGGenerator +from paddlespeech.t2s.datasets.data_table import DataTable +from paddlespeech.t2s.models.parallel_wavegan import PWGGenerator def main(): diff --git a/parakeet/exps/gan_vocoder/parallelwave_gan/synthesize_from_wav.py b/paddlespeech/t2s/exps/gan_vocoder/parallelwave_gan/synthesize_from_wav.py similarity index 93% rename from parakeet/exps/gan_vocoder/parallelwave_gan/synthesize_from_wav.py rename to paddlespeech/t2s/exps/gan_vocoder/parallelwave_gan/synthesize_from_wav.py index c451a51c1669c4666be918d8caeee3cbf15bd49b..a04a547e98208f66238af5d680896497afef7e1d 100644 --- a/parakeet/exps/gan_vocoder/parallelwave_gan/synthesize_from_wav.py +++ b/paddlespeech/t2s/exps/gan_vocoder/parallelwave_gan/synthesize_from_wav.py @@ -23,10 +23,10 @@ import soundfile as sf import yaml from yacs.config import CfgNode -from parakeet.data.get_feats import LogMelFBank -from parakeet.models.parallel_wavegan import PWGGenerator -from parakeet.models.parallel_wavegan import PWGInference -from parakeet.modules.normalizer import ZScore +from paddlespeech.t2s.data.get_feats import LogMelFBank +from paddlespeech.t2s.models.parallel_wavegan import PWGGenerator +from paddlespeech.t2s.models.parallel_wavegan import PWGInference +from paddlespeech.t2s.modules.normalizer import ZScore def evaluate(args, config): diff --git a/parakeet/exps/gan_vocoder/parallelwave_gan/train.py b/paddlespeech/t2s/exps/gan_vocoder/parallelwave_gan/train.py similarity index 92% rename from parakeet/exps/gan_vocoder/parallelwave_gan/train.py rename to paddlespeech/t2s/exps/gan_vocoder/parallelwave_gan/train.py index ad50b65c71b324079d85d58f2d85d894ca145708..99801267f5564aa0077b1512bb7fd7559d1e5727 100644 --- a/parakeet/exps/gan_vocoder/parallelwave_gan/train.py +++ b/paddlespeech/t2s/exps/gan_vocoder/parallelwave_gan/train.py @@ -30,17 +30,17 @@ from paddle.optimizer import Adam # No RAdaom from paddle.optimizer.lr import StepDecay from yacs.config import CfgNode -from parakeet.datasets.data_table import DataTable -from parakeet.datasets.vocoder_batch_fn import Clip -from parakeet.models.parallel_wavegan import PWGDiscriminator -from parakeet.models.parallel_wavegan import PWGEvaluator -from parakeet.models.parallel_wavegan import PWGGenerator -from parakeet.models.parallel_wavegan import PWGUpdater -from parakeet.modules.stft_loss import MultiResolutionSTFTLoss -from parakeet.training.extensions.snapshot import Snapshot -from parakeet.training.extensions.visualizer import VisualDL -from parakeet.training.seeding import seed_everything -from parakeet.training.trainer import Trainer +from paddlespeech.t2s.datasets.data_table import DataTable +from paddlespeech.t2s.datasets.vocoder_batch_fn import Clip +from paddlespeech.t2s.models.parallel_wavegan import PWGDiscriminator +from paddlespeech.t2s.models.parallel_wavegan import PWGEvaluator +from paddlespeech.t2s.models.parallel_wavegan import PWGGenerator +from paddlespeech.t2s.models.parallel_wavegan import PWGUpdater +from paddlespeech.t2s.modules.stft_loss import MultiResolutionSTFTLoss +from paddlespeech.t2s.training.extensions.snapshot import Snapshot +from paddlespeech.t2s.training.extensions.visualizer import VisualDL +from paddlespeech.t2s.training.seeding import seed_everything +from paddlespeech.t2s.training.trainer import Trainer def train_sp(args, config): diff --git a/parakeet/exps/gan_vocoder/preprocess.py b/paddlespeech/t2s/exps/gan_vocoder/preprocess.py similarity index 98% rename from parakeet/exps/gan_vocoder/preprocess.py rename to paddlespeech/t2s/exps/gan_vocoder/preprocess.py index c10143c71666e5a7af415c8bcf1921cd05e699ca..852b0c911640dd5d6ec5030275c9905c83d16005 100644 --- a/parakeet/exps/gan_vocoder/preprocess.py +++ b/paddlespeech/t2s/exps/gan_vocoder/preprocess.py @@ -27,9 +27,9 @@ import tqdm import yaml from yacs.config import CfgNode -from parakeet.data.get_feats import LogMelFBank -from parakeet.datasets.preprocess_utils import get_phn_dur -from parakeet.datasets.preprocess_utils import merge_silence +from paddlespeech.t2s.data.get_feats import LogMelFBank +from paddlespeech.t2s.datasets.preprocess_utils import get_phn_dur +from paddlespeech.t2s.datasets.preprocess_utils import merge_silence def process_sentence(config: Dict[str, Any], diff --git a/parakeet/exps/ge2e/__init__.py b/paddlespeech/t2s/exps/ge2e/__init__.py similarity index 100% rename from parakeet/exps/ge2e/__init__.py rename to paddlespeech/t2s/exps/ge2e/__init__.py diff --git a/parakeet/exps/ge2e/audio_processor.py b/paddlespeech/t2s/exps/ge2e/audio_processor.py similarity index 100% rename from parakeet/exps/ge2e/audio_processor.py rename to paddlespeech/t2s/exps/ge2e/audio_processor.py diff --git a/parakeet/exps/ge2e/config.py b/paddlespeech/t2s/exps/ge2e/config.py similarity index 100% rename from parakeet/exps/ge2e/config.py rename to paddlespeech/t2s/exps/ge2e/config.py diff --git a/parakeet/exps/ge2e/dataset_processors.py b/paddlespeech/t2s/exps/ge2e/dataset_processors.py similarity index 98% rename from parakeet/exps/ge2e/dataset_processors.py rename to paddlespeech/t2s/exps/ge2e/dataset_processors.py index 29b584107b1a9c80202612cc9aacc42fad258b4d..a9320d9859067154333c3464a495fc4557379dfc 100644 --- a/parakeet/exps/ge2e/dataset_processors.py +++ b/paddlespeech/t2s/exps/ge2e/dataset_processors.py @@ -19,7 +19,7 @@ from typing import List import numpy as np from tqdm import tqdm -from parakeet.exps.ge2e.audio_processor import SpeakerVerificationPreprocessor +from paddlespeech.t2s.exps.ge2e.audio_processor import SpeakerVerificationPreprocessor def _process_utterance(path_pair, processor: SpeakerVerificationPreprocessor): diff --git a/parakeet/exps/ge2e/inference.py b/paddlespeech/t2s/exps/ge2e/inference.py similarity index 95% rename from parakeet/exps/ge2e/inference.py rename to paddlespeech/t2s/exps/ge2e/inference.py index 156866627d6e4c5d4c52329723ed0fce90266487..a5733941a2b10165382f0c0b641de365c75dfb82 100644 --- a/parakeet/exps/ge2e/inference.py +++ b/paddlespeech/t2s/exps/ge2e/inference.py @@ -18,9 +18,9 @@ import numpy as np import paddle import tqdm -from parakeet.exps.ge2e.audio_processor import SpeakerVerificationPreprocessor -from parakeet.exps.ge2e.config import get_cfg_defaults -from parakeet.models.lstm_speaker_encoder import LSTMSpeakerEncoder +from paddlespeech.t2s.exps.ge2e.audio_processor import SpeakerVerificationPreprocessor +from paddlespeech.t2s.exps.ge2e.config import get_cfg_defaults +from paddlespeech.t2s.models.lstm_speaker_encoder import LSTMSpeakerEncoder def embed_utterance(processor, model, fpath_or_wav): diff --git a/parakeet/exps/ge2e/preprocess.py b/paddlespeech/t2s/exps/ge2e/preprocess.py similarity index 89% rename from parakeet/exps/ge2e/preprocess.py rename to paddlespeech/t2s/exps/ge2e/preprocess.py index f6457251d135906260159053b49e16ae4685109f..604ff0c6735f378cfda7052147823b3dd63a1780 100644 --- a/parakeet/exps/ge2e/preprocess.py +++ b/paddlespeech/t2s/exps/ge2e/preprocess.py @@ -16,12 +16,12 @@ from pathlib import Path from audio_processor import SpeakerVerificationPreprocessor -from parakeet.exps.ge2e.config import get_cfg_defaults -from parakeet.exps.ge2e.dataset_processors import process_aidatatang_200zh -from parakeet.exps.ge2e.dataset_processors import process_librispeech -from parakeet.exps.ge2e.dataset_processors import process_magicdata -from parakeet.exps.ge2e.dataset_processors import process_voxceleb1 -from parakeet.exps.ge2e.dataset_processors import process_voxceleb2 +from paddlespeech.t2s.exps.ge2e.config import get_cfg_defaults +from paddlespeech.t2s.exps.ge2e.dataset_processors import process_aidatatang_200zh +from paddlespeech.t2s.exps.ge2e.dataset_processors import process_librispeech +from paddlespeech.t2s.exps.ge2e.dataset_processors import process_magicdata +from paddlespeech.t2s.exps.ge2e.dataset_processors import process_voxceleb1 +from paddlespeech.t2s.exps.ge2e.dataset_processors import process_voxceleb2 if __name__ == "__main__": parser = argparse.ArgumentParser( diff --git a/parakeet/exps/ge2e/random_cycle.py b/paddlespeech/t2s/exps/ge2e/random_cycle.py similarity index 100% rename from parakeet/exps/ge2e/random_cycle.py rename to paddlespeech/t2s/exps/ge2e/random_cycle.py diff --git a/parakeet/exps/ge2e/speaker_verification_dataset.py b/paddlespeech/t2s/exps/ge2e/speaker_verification_dataset.py similarity index 98% rename from parakeet/exps/ge2e/speaker_verification_dataset.py rename to paddlespeech/t2s/exps/ge2e/speaker_verification_dataset.py index 896676d96bf971632fd09d9d02e5cb369696fb10..a132199692e077c7aced0cce5ba0709528e88a80 100644 --- a/parakeet/exps/ge2e/speaker_verification_dataset.py +++ b/paddlespeech/t2s/exps/ge2e/speaker_verification_dataset.py @@ -18,7 +18,7 @@ import numpy as np from paddle.io import BatchSampler from paddle.io import Dataset -from parakeet.exps.ge2e.random_cycle import random_cycle +from paddlespeech.t2s.exps.ge2e.random_cycle import random_cycle class MultiSpeakerMelDataset(Dataset): diff --git a/parakeet/exps/ge2e/train.py b/paddlespeech/t2s/exps/ge2e/train.py similarity index 88% rename from parakeet/exps/ge2e/train.py rename to paddlespeech/t2s/exps/ge2e/train.py index 7a59c436b45dc083797be1bf60c880dafcca8f71..d3a57c93d75468e2bcc925cef72d561257fdac68 100644 --- a/parakeet/exps/ge2e/train.py +++ b/paddlespeech/t2s/exps/ge2e/train.py @@ -19,13 +19,13 @@ from paddle.io import DataLoader from paddle.nn.clip import ClipGradByGlobalNorm from paddle.optimizer import Adam -from parakeet.exps.ge2e.config import get_cfg_defaults -from parakeet.exps.ge2e.speaker_verification_dataset import Collate -from parakeet.exps.ge2e.speaker_verification_dataset import MultiSpeakerMelDataset -from parakeet.exps.ge2e.speaker_verification_dataset import MultiSpeakerSampler -from parakeet.models.lstm_speaker_encoder import LSTMSpeakerEncoder -from parakeet.training import default_argument_parser -from parakeet.training import ExperimentBase +from paddlespeech.t2s.exps.ge2e.config import get_cfg_defaults +from paddlespeech.t2s.exps.ge2e.speaker_verification_dataset import Collate +from paddlespeech.t2s.exps.ge2e.speaker_verification_dataset import MultiSpeakerMelDataset +from paddlespeech.t2s.exps.ge2e.speaker_verification_dataset import MultiSpeakerSampler +from paddlespeech.t2s.models.lstm_speaker_encoder import LSTMSpeakerEncoder +from paddlespeech.t2s.training import default_argument_parser +from paddlespeech.t2s.training import ExperimentBase class Ge2eExperiment(ExperimentBase): diff --git a/parakeet/exps/sentences.txt b/paddlespeech/t2s/exps/sentences.txt similarity index 100% rename from parakeet/exps/sentences.txt rename to paddlespeech/t2s/exps/sentences.txt diff --git a/parakeet/exps/sentences_en.txt b/paddlespeech/t2s/exps/sentences_en.txt similarity index 100% rename from parakeet/exps/sentences_en.txt rename to paddlespeech/t2s/exps/sentences_en.txt diff --git a/parakeet/exps/speedyspeech/__init__.py b/paddlespeech/t2s/exps/speedyspeech/__init__.py similarity index 100% rename from parakeet/exps/speedyspeech/__init__.py rename to paddlespeech/t2s/exps/speedyspeech/__init__.py diff --git a/parakeet/exps/speedyspeech/inference.py b/paddlespeech/t2s/exps/speedyspeech/inference.py similarity index 98% rename from parakeet/exps/speedyspeech/inference.py rename to paddlespeech/t2s/exps/speedyspeech/inference.py index 77a90915b8186bcc915151c8b86ce672773f6cce..49ce37f23bfd3dc79fa40c3c08c2142f314784e9 100644 --- a/parakeet/exps/speedyspeech/inference.py +++ b/paddlespeech/t2s/exps/speedyspeech/inference.py @@ -18,7 +18,7 @@ from pathlib import Path import soundfile as sf from paddle import inference -from parakeet.frontend.zh_frontend import Frontend +from paddlespeech.t2s.frontend.zh_frontend import Frontend def main(): diff --git a/parakeet/exps/speedyspeech/normalize.py b/paddlespeech/t2s/exps/speedyspeech/normalize.py similarity index 98% rename from parakeet/exps/speedyspeech/normalize.py rename to paddlespeech/t2s/exps/speedyspeech/normalize.py index 8f02c33cc4b33c7281a6bb017e2331e02d86f5ca..91d15c40b201b70780fceea77f37d50af5383c4a 100644 --- a/parakeet/exps/speedyspeech/normalize.py +++ b/paddlespeech/t2s/exps/speedyspeech/normalize.py @@ -22,7 +22,7 @@ import numpy as np from sklearn.preprocessing import StandardScaler from tqdm import tqdm -from parakeet.datasets.data_table import DataTable +from paddlespeech.t2s.datasets.data_table import DataTable def main(): diff --git a/parakeet/exps/speedyspeech/preprocess.py b/paddlespeech/t2s/exps/speedyspeech/preprocess.py similarity index 96% rename from parakeet/exps/speedyspeech/preprocess.py rename to paddlespeech/t2s/exps/speedyspeech/preprocess.py index f3ae294d8bf7674248432fc547a8f248ec68ad4a..aa589d5a323dc2bf67e08d49d455e2cbc347ca47 100644 --- a/parakeet/exps/speedyspeech/preprocess.py +++ b/paddlespeech/t2s/exps/speedyspeech/preprocess.py @@ -27,11 +27,11 @@ import tqdm import yaml from yacs.config import CfgNode -from parakeet.data.get_feats import LogMelFBank -from parakeet.datasets.preprocess_utils import compare_duration_and_mel_length -from parakeet.datasets.preprocess_utils import get_phn_dur -from parakeet.datasets.preprocess_utils import get_phones_tones -from parakeet.datasets.preprocess_utils import merge_silence +from paddlespeech.t2s.data.get_feats import LogMelFBank +from paddlespeech.t2s.datasets.preprocess_utils import compare_duration_and_mel_length +from paddlespeech.t2s.datasets.preprocess_utils import get_phn_dur +from paddlespeech.t2s.datasets.preprocess_utils import get_phones_tones +from paddlespeech.t2s.datasets.preprocess_utils import merge_silence def process_sentence(config: Dict[str, Any], diff --git a/parakeet/exps/speedyspeech/synthesize.py b/paddlespeech/t2s/exps/speedyspeech/synthesize.py similarity index 94% rename from parakeet/exps/speedyspeech/synthesize.py rename to paddlespeech/t2s/exps/speedyspeech/synthesize.py index 43ab4a69bf28510ff69c6f19466b7b79b1cd776c..4482c179e9d4cf7543af75fe6246ed6b6945a760 100644 --- a/parakeet/exps/speedyspeech/synthesize.py +++ b/paddlespeech/t2s/exps/speedyspeech/synthesize.py @@ -25,12 +25,12 @@ from paddle import jit from paddle.static import InputSpec from yacs.config import CfgNode -from parakeet.datasets.data_table import DataTable -from parakeet.models.parallel_wavegan import PWGGenerator -from parakeet.models.parallel_wavegan import PWGInference -from parakeet.models.speedyspeech import SpeedySpeech -from parakeet.models.speedyspeech import SpeedySpeechInference -from parakeet.modules.normalizer import ZScore +from paddlespeech.t2s.datasets.data_table import DataTable +from paddlespeech.t2s.models.parallel_wavegan import PWGGenerator +from paddlespeech.t2s.models.parallel_wavegan import PWGInference +from paddlespeech.t2s.models.speedyspeech import SpeedySpeech +from paddlespeech.t2s.models.speedyspeech import SpeedySpeechInference +from paddlespeech.t2s.modules.normalizer import ZScore def evaluate(args, speedyspeech_config, pwg_config): diff --git a/parakeet/exps/speedyspeech/synthesize_e2e.py b/paddlespeech/t2s/exps/speedyspeech/synthesize_e2e.py similarity index 94% rename from parakeet/exps/speedyspeech/synthesize_e2e.py rename to paddlespeech/t2s/exps/speedyspeech/synthesize_e2e.py index 47e064e958b65689efee52d011e9facbc9671d31..0870d4666b150558c665acfec0599e84c4dca0f4 100644 --- a/parakeet/exps/speedyspeech/synthesize_e2e.py +++ b/paddlespeech/t2s/exps/speedyspeech/synthesize_e2e.py @@ -24,12 +24,12 @@ from paddle import jit from paddle.static import InputSpec from yacs.config import CfgNode -from parakeet.frontend.zh_frontend import Frontend -from parakeet.models.parallel_wavegan import PWGGenerator -from parakeet.models.parallel_wavegan import PWGInference -from parakeet.models.speedyspeech import SpeedySpeech -from parakeet.models.speedyspeech import SpeedySpeechInference -from parakeet.modules.normalizer import ZScore +from paddlespeech.t2s.frontend.zh_frontend import Frontend +from paddlespeech.t2s.models.parallel_wavegan import PWGGenerator +from paddlespeech.t2s.models.parallel_wavegan import PWGInference +from paddlespeech.t2s.models.speedyspeech import SpeedySpeech +from paddlespeech.t2s.models.speedyspeech import SpeedySpeechInference +from paddlespeech.t2s.modules.normalizer import ZScore def evaluate(args, speedyspeech_config, pwg_config): diff --git a/parakeet/exps/speedyspeech/train.py b/paddlespeech/t2s/exps/speedyspeech/train.py similarity index 91% rename from parakeet/exps/speedyspeech/train.py rename to paddlespeech/t2s/exps/speedyspeech/train.py index 6a4bf59e1aeeb0918202bca0bcc3d9cf8bd63211..772a39d7099727f43c35c33a26446717c8712063 100644 --- a/parakeet/exps/speedyspeech/train.py +++ b/paddlespeech/t2s/exps/speedyspeech/train.py @@ -27,16 +27,16 @@ from paddle.io import DataLoader from paddle.io import DistributedBatchSampler from yacs.config import CfgNode -from parakeet.datasets.am_batch_fn import speedyspeech_batch_fn -from parakeet.datasets.data_table import DataTable -from parakeet.models.speedyspeech import SpeedySpeech -from parakeet.models.speedyspeech import SpeedySpeechEvaluator -from parakeet.models.speedyspeech import SpeedySpeechUpdater -from parakeet.training.extensions.snapshot import Snapshot -from parakeet.training.extensions.visualizer import VisualDL -from parakeet.training.optimizer import build_optimizers -from parakeet.training.seeding import seed_everything -from parakeet.training.trainer import Trainer +from paddlespeech.t2s.datasets.am_batch_fn import speedyspeech_batch_fn +from paddlespeech.t2s.datasets.data_table import DataTable +from paddlespeech.t2s.models.speedyspeech import SpeedySpeech +from paddlespeech.t2s.models.speedyspeech import SpeedySpeechEvaluator +from paddlespeech.t2s.models.speedyspeech import SpeedySpeechUpdater +from paddlespeech.t2s.training.extensions.snapshot import Snapshot +from paddlespeech.t2s.training.extensions.visualizer import VisualDL +from paddlespeech.t2s.training.optimizer import build_optimizers +from paddlespeech.t2s.training.seeding import seed_everything +from paddlespeech.t2s.training.trainer import Trainer def train_sp(args, config): diff --git a/parakeet/exps/tacotron2/__init__.py b/paddlespeech/t2s/exps/tacotron2/__init__.py similarity index 100% rename from parakeet/exps/tacotron2/__init__.py rename to paddlespeech/t2s/exps/tacotron2/__init__.py diff --git a/parakeet/exps/tacotron2/config.py b/paddlespeech/t2s/exps/tacotron2/config.py similarity index 100% rename from parakeet/exps/tacotron2/config.py rename to paddlespeech/t2s/exps/tacotron2/config.py diff --git a/parakeet/exps/tacotron2/ljspeech.py b/paddlespeech/t2s/exps/tacotron2/ljspeech.py similarity index 96% rename from parakeet/exps/tacotron2/ljspeech.py rename to paddlespeech/t2s/exps/tacotron2/ljspeech.py index 59c855eb6ca172b8c46ca43b5f0bb741ada74089..08db2a646898db45bcd31594f36b9a26d6c4999c 100644 --- a/parakeet/exps/tacotron2/ljspeech.py +++ b/paddlespeech/t2s/exps/tacotron2/ljspeech.py @@ -17,8 +17,8 @@ from pathlib import Path import numpy as np from paddle.io import Dataset -from parakeet.data.batch import batch_spec -from parakeet.data.batch import batch_text_id +from paddlespeech.t2s.data.batch import batch_spec +from paddlespeech.t2s.data.batch import batch_text_id class LJSpeech(Dataset): diff --git a/parakeet/exps/tacotron2/preprocess.py b/paddlespeech/t2s/exps/tacotron2/preprocess.py similarity index 91% rename from parakeet/exps/tacotron2/preprocess.py rename to paddlespeech/t2s/exps/tacotron2/preprocess.py index 893444855d05887e2e1646a5d04decaaa38df59a..480b33315fdc318fd9c05932d2f30a697ac17d58 100644 --- a/parakeet/exps/tacotron2/preprocess.py +++ b/paddlespeech/t2s/exps/tacotron2/preprocess.py @@ -19,11 +19,11 @@ from pathlib import Path import numpy as np import tqdm -from parakeet.audio import AudioProcessor -from parakeet.audio import LogMagnitude -from parakeet.datasets import LJSpeechMetaData -from parakeet.exps.tacotron2.config import get_cfg_defaults -from parakeet.frontend import EnglishCharacter +from paddlespeech.t2s.audio import AudioProcessor +from paddlespeech.t2s.audio import LogMagnitude +from paddlespeech.t2s.datasets import LJSpeechMetaData +from paddlespeech.t2s.exps.tacotron2.config import get_cfg_defaults +from paddlespeech.t2s.frontend import EnglishCharacter def create_dataset(config, source_path, target_path, verbose=False): diff --git a/parakeet/exps/tacotron2/synthesize.ipynb b/paddlespeech/t2s/exps/tacotron2/synthesize.ipynb similarity index 99% rename from parakeet/exps/tacotron2/synthesize.ipynb rename to paddlespeech/t2s/exps/tacotron2/synthesize.ipynb index f71182f267d6de550b6d0ac9d6def6992eab44f9..cc424311fb687ce0179911cc1c884a1a266e81c2 100644 --- a/parakeet/exps/tacotron2/synthesize.ipynb +++ b/paddlespeech/t2s/exps/tacotron2/synthesize.ipynb @@ -19,8 +19,8 @@ "from IPython import display as ipd\n", "%matplotlib inline\n", "\n", - "from parakeet.utils import display\n", - "from parakeet.utils import layer_tools\n", + "from paddlespeech.t2s.utils import display\n", + "from paddlespeech.t2s.utils import layer_tools\n", "paddle.set_device(\"gpu:0\")\n", "\n", "import sys\n", @@ -45,8 +45,8 @@ "metadata": {}, "outputs": [], "source": [ - "from parakeet.models.tacotron2 import Tacotron2\n", - "from parakeet.frontend import EnglishCharacter" + "from paddlespeech.t2s.models.tacotron2 import Tacotron2\n", + "from paddlespeech.t2s.frontend import EnglishCharacter" ] }, { @@ -198,7 +198,7 @@ "metadata": {}, "outputs": [], "source": [ - "from parakeet.models.waveflow import ConditionalWaveFlow" + "from paddlespeech.t2s.models.waveflow import ConditionalWaveFlow" ] }, { diff --git a/parakeet/exps/tacotron2/synthesize.py b/paddlespeech/t2s/exps/tacotron2/synthesize.py similarity index 93% rename from parakeet/exps/tacotron2/synthesize.py rename to paddlespeech/t2s/exps/tacotron2/synthesize.py index 56257c9b047de6943ccaefe1bdd2df2c4a25a475..613fec02ea3ef8ea95bc63279c9a5feaef0fb24c 100644 --- a/parakeet/exps/tacotron2/synthesize.py +++ b/paddlespeech/t2s/exps/tacotron2/synthesize.py @@ -18,10 +18,10 @@ import numpy as np import paddle from matplotlib import pyplot as plt -from parakeet.exps.tacotron2.config import get_cfg_defaults -from parakeet.frontend import EnglishCharacter -from parakeet.models.tacotron2 import Tacotron2 -from parakeet.utils import display +from paddlespeech.t2s.exps.tacotron2.config import get_cfg_defaults +from paddlespeech.t2s.frontend import EnglishCharacter +from paddlespeech.t2s.models.tacotron2 import Tacotron2 +from paddlespeech.t2s.utils import display def main(config, args): diff --git a/parakeet/exps/tacotron2/train.py b/paddlespeech/t2s/exps/tacotron2/train.py similarity index 93% rename from parakeet/exps/tacotron2/train.py rename to paddlespeech/t2s/exps/tacotron2/train.py index 3677c271d55c440472caa437a1dbcd096387983b..a5f08360ffbc9cc44d3bcc9dee1ad0345ba12f53 100644 --- a/parakeet/exps/tacotron2/train.py +++ b/paddlespeech/t2s/exps/tacotron2/train.py @@ -20,16 +20,16 @@ from paddle import distributed as dist from paddle.io import DataLoader from paddle.io import DistributedBatchSampler -from parakeet.data import dataset -from parakeet.exps.tacotron2.config import get_cfg_defaults -from parakeet.exps.tacotron2.ljspeech import LJSpeech -from parakeet.exps.tacotron2.ljspeech import LJSpeechCollector -from parakeet.models.tacotron2 import Tacotron2 -from parakeet.models.tacotron2 import Tacotron2Loss -from parakeet.training.cli import default_argument_parser -from parakeet.training.experiment import ExperimentBase -from parakeet.utils import display -from parakeet.utils import mp_tools +from paddlespeech.t2s.data import dataset +from paddlespeech.t2s.exps.tacotron2.config import get_cfg_defaults +from paddlespeech.t2s.exps.tacotron2.ljspeech import LJSpeech +from paddlespeech.t2s.exps.tacotron2.ljspeech import LJSpeechCollector +from paddlespeech.t2s.models.tacotron2 import Tacotron2 +from paddlespeech.t2s.models.tacotron2 import Tacotron2Loss +from paddlespeech.t2s.training.cli import default_argument_parser +from paddlespeech.t2s.training.experiment import ExperimentBase +from paddlespeech.t2s.utils import display +from paddlespeech.t2s.utils import mp_tools class Experiment(ExperimentBase): diff --git a/parakeet/exps/transformer_tts/__init__.py b/paddlespeech/t2s/exps/transformer_tts/__init__.py similarity index 100% rename from parakeet/exps/transformer_tts/__init__.py rename to paddlespeech/t2s/exps/transformer_tts/__init__.py diff --git a/parakeet/exps/transformer_tts/normalize.py b/paddlespeech/t2s/exps/transformer_tts/normalize.py similarity index 98% rename from parakeet/exps/transformer_tts/normalize.py rename to paddlespeech/t2s/exps/transformer_tts/normalize.py index 127449ee3ee90075b9e8e30ffcd4a017348b7b35..4bb77c7911a9c2cd43de83ef40c07fadc38d34f4 100644 --- a/parakeet/exps/transformer_tts/normalize.py +++ b/paddlespeech/t2s/exps/transformer_tts/normalize.py @@ -22,7 +22,7 @@ import numpy as np from sklearn.preprocessing import StandardScaler from tqdm import tqdm -from parakeet.datasets.data_table import DataTable +from paddlespeech.t2s.datasets.data_table import DataTable def main(): diff --git a/parakeet/exps/transformer_tts/preprocess.py b/paddlespeech/t2s/exps/transformer_tts/preprocess.py similarity index 98% rename from parakeet/exps/transformer_tts/preprocess.py rename to paddlespeech/t2s/exps/transformer_tts/preprocess.py index 96696eaedff181b3e6b3873b20fc764f2573c83f..93158b671ae69a74717476012661b33961110e31 100644 --- a/parakeet/exps/transformer_tts/preprocess.py +++ b/paddlespeech/t2s/exps/transformer_tts/preprocess.py @@ -26,8 +26,8 @@ import tqdm import yaml from yacs.config import CfgNode as Configuration -from parakeet.data.get_feats import LogMelFBank -from parakeet.frontend import English +from paddlespeech.t2s.data.get_feats import LogMelFBank +from paddlespeech.t2s.frontend import English def get_lj_sentences(file_name, frontend): diff --git a/parakeet/exps/transformer_tts/synthesize.py b/paddlespeech/t2s/exps/transformer_tts/synthesize.py similarity index 92% rename from parakeet/exps/transformer_tts/synthesize.py rename to paddlespeech/t2s/exps/transformer_tts/synthesize.py index 5c1945d28d37b9d2e98de5991a75eb16f7b28212..82fd8f1536eff9b325e48a1839672be276e521e9 100644 --- a/parakeet/exps/transformer_tts/synthesize.py +++ b/paddlespeech/t2s/exps/transformer_tts/synthesize.py @@ -22,12 +22,12 @@ import soundfile as sf import yaml from yacs.config import CfgNode -from parakeet.datasets.data_table import DataTable -from parakeet.models.transformer_tts import TransformerTTS -from parakeet.models.transformer_tts import TransformerTTSInference -from parakeet.models.waveflow import ConditionalWaveFlow -from parakeet.modules.normalizer import ZScore -from parakeet.utils import layer_tools +from paddlespeech.t2s.datasets.data_table import DataTable +from paddlespeech.t2s.models.transformer_tts import TransformerTTS +from paddlespeech.t2s.models.transformer_tts import TransformerTTSInference +from paddlespeech.t2s.models.waveflow import ConditionalWaveFlow +from paddlespeech.t2s.modules.normalizer import ZScore +from paddlespeech.t2s.utils import layer_tools def evaluate(args, acoustic_model_config, vocoder_config): diff --git a/parakeet/exps/transformer_tts/synthesize_e2e.py b/paddlespeech/t2s/exps/transformer_tts/synthesize_e2e.py similarity index 93% rename from parakeet/exps/transformer_tts/synthesize_e2e.py rename to paddlespeech/t2s/exps/transformer_tts/synthesize_e2e.py index 2bee77d35bfae18e3a02145f4f0c3d4c265e67f4..993749f048efa5187c8eecd2e24f2e1a43dcbe7d 100644 --- a/parakeet/exps/transformer_tts/synthesize_e2e.py +++ b/paddlespeech/t2s/exps/transformer_tts/synthesize_e2e.py @@ -21,12 +21,12 @@ import soundfile as sf import yaml from yacs.config import CfgNode -from parakeet.frontend import English -from parakeet.models.transformer_tts import TransformerTTS -from parakeet.models.transformer_tts import TransformerTTSInference -from parakeet.models.waveflow import ConditionalWaveFlow -from parakeet.modules.normalizer import ZScore -from parakeet.utils import layer_tools +from paddlespeech.t2s.frontend import English +from paddlespeech.t2s.models.transformer_tts import TransformerTTS +from paddlespeech.t2s.models.transformer_tts import TransformerTTSInference +from paddlespeech.t2s.models.waveflow import ConditionalWaveFlow +from paddlespeech.t2s.modules.normalizer import ZScore +from paddlespeech.t2s.utils import layer_tools def evaluate(args, acoustic_model_config, vocoder_config): diff --git a/parakeet/exps/transformer_tts/train.py b/paddlespeech/t2s/exps/transformer_tts/train.py similarity index 89% rename from parakeet/exps/transformer_tts/train.py rename to paddlespeech/t2s/exps/transformer_tts/train.py index bf0663908e9d5a2c83c0ed2bce96cb5a697c3c57..7d9020a32a0728295ef31e00cf05348b31fd16ca 100644 --- a/parakeet/exps/transformer_tts/train.py +++ b/paddlespeech/t2s/exps/transformer_tts/train.py @@ -27,16 +27,16 @@ from paddle.io import DataLoader from paddle.io import DistributedBatchSampler from yacs.config import CfgNode -from parakeet.datasets.am_batch_fn import transformer_single_spk_batch_fn -from parakeet.datasets.data_table import DataTable -from parakeet.models.transformer_tts import TransformerTTS -from parakeet.models.transformer_tts import TransformerTTSEvaluator -from parakeet.models.transformer_tts import TransformerTTSUpdater -from parakeet.training.extensions.snapshot import Snapshot -from parakeet.training.extensions.visualizer import VisualDL -from parakeet.training.optimizer import build_optimizers -from parakeet.training.seeding import seed_everything -from parakeet.training.trainer import Trainer +from paddlespeech.t2s.datasets.am_batch_fn import transformer_single_spk_batch_fn +from paddlespeech.t2s.datasets.data_table import DataTable +from paddlespeech.t2s.models.transformer_tts import TransformerTTS +from paddlespeech.t2s.models.transformer_tts import TransformerTTSEvaluator +from paddlespeech.t2s.models.transformer_tts import TransformerTTSUpdater +from paddlespeech.t2s.training.extensions.snapshot import Snapshot +from paddlespeech.t2s.training.extensions.visualizer import VisualDL +from paddlespeech.t2s.training.optimizer import build_optimizers +from paddlespeech.t2s.training.seeding import seed_everything +from paddlespeech.t2s.training.trainer import Trainer def train_sp(args, config): diff --git a/parakeet/exps/voice_cloning/__init__.py b/paddlespeech/t2s/exps/voice_cloning/__init__.py similarity index 100% rename from parakeet/exps/voice_cloning/__init__.py rename to paddlespeech/t2s/exps/voice_cloning/__init__.py diff --git a/parakeet/exps/voice_cloning/tacotron2_ge2e/__init__.py b/paddlespeech/t2s/exps/voice_cloning/tacotron2_ge2e/__init__.py similarity index 100% rename from parakeet/exps/voice_cloning/tacotron2_ge2e/__init__.py rename to paddlespeech/t2s/exps/voice_cloning/tacotron2_ge2e/__init__.py diff --git a/parakeet/exps/voice_cloning/tacotron2_ge2e/aishell3.py b/paddlespeech/t2s/exps/voice_cloning/tacotron2_ge2e/aishell3.py similarity index 89% rename from parakeet/exps/voice_cloning/tacotron2_ge2e/aishell3.py rename to paddlespeech/t2s/exps/voice_cloning/tacotron2_ge2e/aishell3.py index b697ecf3602de5ada3f45709b0855154707c66d8..da95582d0872ab4942fa267657034db78dee0949 100644 --- a/parakeet/exps/voice_cloning/tacotron2_ge2e/aishell3.py +++ b/paddlespeech/t2s/exps/voice_cloning/tacotron2_ge2e/aishell3.py @@ -17,11 +17,11 @@ from pathlib import Path import numpy as np from paddle.io import Dataset -from parakeet.data import batch_spec -from parakeet.data import batch_text_id -from parakeet.exps.voice_cloning.tacotron2_ge2e.preprocess_transcription import _phones -from parakeet.exps.voice_cloning.tacotron2_ge2e.preprocess_transcription import _tones -from parakeet.frontend import Vocab +from paddlespeech.t2s.data import batch_spec +from paddlespeech.t2s.data import batch_text_id +from paddlespeech.t2s.exps.voice_cloning.tacotron2_ge2e.preprocess_transcription import _phones +from paddlespeech.t2s.exps.voice_cloning.tacotron2_ge2e.preprocess_transcription import _tones +from paddlespeech.t2s.frontend import Vocab voc_phones = Vocab(sorted(list(_phones))) print("vocab_phones:\n", voc_phones) diff --git a/parakeet/exps/voice_cloning/tacotron2_ge2e/chinese_g2p.py b/paddlespeech/t2s/exps/voice_cloning/tacotron2_ge2e/chinese_g2p.py similarity index 92% rename from parakeet/exps/voice_cloning/tacotron2_ge2e/chinese_g2p.py rename to paddlespeech/t2s/exps/voice_cloning/tacotron2_ge2e/chinese_g2p.py index f975522f1bf429ee77be2708e70a1cef97de8b81..12de3bb76ee255f1de49e72b405cea3119d00021 100644 --- a/parakeet/exps/voice_cloning/tacotron2_ge2e/chinese_g2p.py +++ b/paddlespeech/t2s/exps/voice_cloning/tacotron2_ge2e/chinese_g2p.py @@ -17,7 +17,7 @@ from typing import Tuple from pypinyin import lazy_pinyin from pypinyin import Style -from parakeet.exps.voice_cloning.tacotron2_ge2e.preprocess_transcription import split_syllable +from paddlespeech.t2s.exps.voice_cloning.tacotron2_ge2e.preprocess_transcription import split_syllable def convert_to_pinyin(text: str) -> List[str]: diff --git a/parakeet/exps/voice_cloning/tacotron2_ge2e/config.py b/paddlespeech/t2s/exps/voice_cloning/tacotron2_ge2e/config.py similarity index 100% rename from parakeet/exps/voice_cloning/tacotron2_ge2e/config.py rename to paddlespeech/t2s/exps/voice_cloning/tacotron2_ge2e/config.py diff --git a/parakeet/exps/voice_cloning/tacotron2_ge2e/extract_mel.py b/paddlespeech/t2s/exps/voice_cloning/tacotron2_ge2e/extract_mel.py similarity index 92% rename from parakeet/exps/voice_cloning/tacotron2_ge2e/extract_mel.py rename to paddlespeech/t2s/exps/voice_cloning/tacotron2_ge2e/extract_mel.py index 53daa3fcd9d58ba08150d460fce1d08497ecc421..d12466f6fc1239e73c1cb18d1c65505f6988ccaf 100644 --- a/parakeet/exps/voice_cloning/tacotron2_ge2e/extract_mel.py +++ b/paddlespeech/t2s/exps/voice_cloning/tacotron2_ge2e/extract_mel.py @@ -19,10 +19,10 @@ from pathlib import Path import numpy as np import tqdm -from parakeet.audio import AudioProcessor -from parakeet.audio.spec_normalizer import LogMagnitude -from parakeet.audio.spec_normalizer import NormalizerBase -from parakeet.exps.voice_cloning.tacotron2_ge2e.config import get_cfg_defaults +from paddlespeech.t2s.audio import AudioProcessor +from paddlespeech.t2s.audio.spec_normalizer import LogMagnitude +from paddlespeech.t2s.audio.spec_normalizer import NormalizerBase +from paddlespeech.t2s.exps.voice_cloning.tacotron2_ge2e.config import get_cfg_defaults def extract_mel(fname: Path, diff --git a/parakeet/exps/voice_cloning/tacotron2_ge2e/lexicon.txt b/paddlespeech/t2s/exps/voice_cloning/tacotron2_ge2e/lexicon.txt similarity index 100% rename from parakeet/exps/voice_cloning/tacotron2_ge2e/lexicon.txt rename to paddlespeech/t2s/exps/voice_cloning/tacotron2_ge2e/lexicon.txt diff --git a/parakeet/exps/voice_cloning/tacotron2_ge2e/preprocess_transcription.py b/paddlespeech/t2s/exps/voice_cloning/tacotron2_ge2e/preprocess_transcription.py similarity index 100% rename from parakeet/exps/voice_cloning/tacotron2_ge2e/preprocess_transcription.py rename to paddlespeech/t2s/exps/voice_cloning/tacotron2_ge2e/preprocess_transcription.py diff --git a/parakeet/exps/voice_cloning/tacotron2_ge2e/process_wav.py b/paddlespeech/t2s/exps/voice_cloning/tacotron2_ge2e/process_wav.py similarity index 100% rename from parakeet/exps/voice_cloning/tacotron2_ge2e/process_wav.py rename to paddlespeech/t2s/exps/voice_cloning/tacotron2_ge2e/process_wav.py diff --git a/parakeet/exps/voice_cloning/tacotron2_ge2e/train.py b/paddlespeech/t2s/exps/voice_cloning/tacotron2_ge2e/train.py similarity index 93% rename from parakeet/exps/voice_cloning/tacotron2_ge2e/train.py rename to paddlespeech/t2s/exps/voice_cloning/tacotron2_ge2e/train.py index 1a9bd8cb9887dada10bb25d883180a20addc1261..ceae13604bf12282f10425b2cf5ceb7a700f0ab3 100644 --- a/parakeet/exps/voice_cloning/tacotron2_ge2e/train.py +++ b/paddlespeech/t2s/exps/voice_cloning/tacotron2_ge2e/train.py @@ -22,16 +22,16 @@ from paddle import distributed as dist from paddle.io import DataLoader from paddle.io import DistributedBatchSampler -from parakeet.data import dataset -from parakeet.exps.voice_cloning.tacotron2_ge2e.aishell3 import AiShell3 -from parakeet.exps.voice_cloning.tacotron2_ge2e.aishell3 import collate_aishell3_examples -from parakeet.exps.voice_cloning.tacotron2_ge2e.config import get_cfg_defaults -from parakeet.models.tacotron2 import Tacotron2 -from parakeet.models.tacotron2 import Tacotron2Loss -from parakeet.training.cli import default_argument_parser -from parakeet.training.experiment import ExperimentBase -from parakeet.utils import display -from parakeet.utils import mp_tools +from paddlespeech.t2s.data import dataset +from paddlespeech.t2s.exps.voice_cloning.tacotron2_ge2e.aishell3 import AiShell3 +from paddlespeech.t2s.exps.voice_cloning.tacotron2_ge2e.aishell3 import collate_aishell3_examples +from paddlespeech.t2s.exps.voice_cloning.tacotron2_ge2e.config import get_cfg_defaults +from paddlespeech.t2s.models.tacotron2 import Tacotron2 +from paddlespeech.t2s.models.tacotron2 import Tacotron2Loss +from paddlespeech.t2s.training.cli import default_argument_parser +from paddlespeech.t2s.training.experiment import ExperimentBase +from paddlespeech.t2s.utils import display +from paddlespeech.t2s.utils import mp_tools class Experiment(ExperimentBase): diff --git a/parakeet/exps/voice_cloning/tacotron2_ge2e/voice_cloning.py b/paddlespeech/t2s/exps/voice_cloning/tacotron2_ge2e/voice_cloning.py similarity index 90% rename from parakeet/exps/voice_cloning/tacotron2_ge2e/voice_cloning.py rename to paddlespeech/t2s/exps/voice_cloning/tacotron2_ge2e/voice_cloning.py index 8afd35b77ee619289a654e4c8807228e89b0b774..c76ce0075593c4bd82dfa8a92ed81e2e0522b6a1 100644 --- a/parakeet/exps/voice_cloning/tacotron2_ge2e/voice_cloning.py +++ b/paddlespeech/t2s/exps/voice_cloning/tacotron2_ge2e/voice_cloning.py @@ -20,14 +20,14 @@ import paddle import soundfile as sf from matplotlib import pyplot as plt -from parakeet.exps.ge2e.audio_processor import SpeakerVerificationPreprocessor -from parakeet.exps.voice_cloning.tacotron2_ge2e.aishell3 import voc_phones -from parakeet.exps.voice_cloning.tacotron2_ge2e.aishell3 import voc_tones -from parakeet.exps.voice_cloning.tacotron2_ge2e.chinese_g2p import convert_sentence -from parakeet.models.lstm_speaker_encoder import LSTMSpeakerEncoder -from parakeet.models.tacotron2 import Tacotron2 -from parakeet.models.waveflow import ConditionalWaveFlow -from parakeet.utils import display +from paddlespeech.t2s.exps.ge2e.audio_processor import SpeakerVerificationPreprocessor +from paddlespeech.t2s.exps.voice_cloning.tacotron2_ge2e.aishell3 import voc_phones +from paddlespeech.t2s.exps.voice_cloning.tacotron2_ge2e.aishell3 import voc_tones +from paddlespeech.t2s.exps.voice_cloning.tacotron2_ge2e.chinese_g2p import convert_sentence +from paddlespeech.t2s.models.lstm_speaker_encoder import LSTMSpeakerEncoder +from paddlespeech.t2s.models.tacotron2 import Tacotron2 +from paddlespeech.t2s.models.waveflow import ConditionalWaveFlow +from paddlespeech.t2s.utils import display def voice_cloning(args): diff --git a/parakeet/exps/waveflow/__init__.py b/paddlespeech/t2s/exps/waveflow/__init__.py similarity index 100% rename from parakeet/exps/waveflow/__init__.py rename to paddlespeech/t2s/exps/waveflow/__init__.py diff --git a/parakeet/exps/waveflow/config.py b/paddlespeech/t2s/exps/waveflow/config.py similarity index 100% rename from parakeet/exps/waveflow/config.py rename to paddlespeech/t2s/exps/waveflow/config.py diff --git a/parakeet/exps/waveflow/ljspeech.py b/paddlespeech/t2s/exps/waveflow/ljspeech.py similarity index 96% rename from parakeet/exps/waveflow/ljspeech.py rename to paddlespeech/t2s/exps/waveflow/ljspeech.py index ca18f400e22037c11cc7d070be082e32ba82fe5e..655b63dade7c355412c087fdae7f3974118a33f7 100644 --- a/parakeet/exps/waveflow/ljspeech.py +++ b/paddlespeech/t2s/exps/waveflow/ljspeech.py @@ -17,8 +17,8 @@ import numpy as np import pandas from paddle.io import Dataset -from parakeet.data.batch import batch_spec -from parakeet.data.batch import batch_wav +from paddlespeech.t2s.data.batch import batch_spec +from paddlespeech.t2s.data.batch import batch_wav class LJSpeech(Dataset): diff --git a/parakeet/exps/waveflow/preprocess.py b/paddlespeech/t2s/exps/waveflow/preprocess.py similarity index 96% rename from parakeet/exps/waveflow/preprocess.py rename to paddlespeech/t2s/exps/waveflow/preprocess.py index d4ec0de5da711ce405dccdd438da2ec299de3863..ef3a29175896d7d02f7a9df4dcc930d33f9476af 100644 --- a/parakeet/exps/waveflow/preprocess.py +++ b/paddlespeech/t2s/exps/waveflow/preprocess.py @@ -20,9 +20,9 @@ import numpy as np import pandas as pd import tqdm -from parakeet.audio import LogMagnitude -from parakeet.datasets import LJSpeechMetaData -from parakeet.exps.waveflow.config import get_cfg_defaults +from paddlespeech.t2s.audio import LogMagnitude +from paddlespeech.t2s.datasets import LJSpeechMetaData +from paddlespeech.t2s.exps.waveflow.config import get_cfg_defaults class Transform(object): diff --git a/parakeet/exps/waveflow/synthesize.py b/paddlespeech/t2s/exps/waveflow/synthesize.py similarity index 93% rename from parakeet/exps/waveflow/synthesize.py rename to paddlespeech/t2s/exps/waveflow/synthesize.py index 4dd52514a08c2d89b356aa227d30ae4fb00c1086..4f07aa4e3c7d80701e2e61eef4fed87b6c8101ff 100644 --- a/parakeet/exps/waveflow/synthesize.py +++ b/paddlespeech/t2s/exps/waveflow/synthesize.py @@ -19,9 +19,9 @@ import numpy as np import paddle import soundfile as sf -from parakeet.exps.waveflow.config import get_cfg_defaults -from parakeet.models.waveflow import ConditionalWaveFlow -from parakeet.utils import layer_tools +from paddlespeech.t2s.exps.waveflow.config import get_cfg_defaults +from paddlespeech.t2s.models.waveflow import ConditionalWaveFlow +from paddlespeech.t2s.utils import layer_tools def main(config, args): diff --git a/parakeet/exps/waveflow/train.py b/paddlespeech/t2s/exps/waveflow/train.py similarity index 89% rename from parakeet/exps/waveflow/train.py rename to paddlespeech/t2s/exps/waveflow/train.py index ecfcbcaac8c57979e11d20555ae7bdb52c952fcf..9d1df13c7fe663856fd3b039f6eb8add0b40f352 100644 --- a/parakeet/exps/waveflow/train.py +++ b/paddlespeech/t2s/exps/waveflow/train.py @@ -19,16 +19,16 @@ from paddle import distributed as dist from paddle.io import DataLoader from paddle.io import DistributedBatchSampler -from parakeet.data import dataset -from parakeet.exps.waveflow.config import get_cfg_defaults -from parakeet.exps.waveflow.ljspeech import LJSpeech -from parakeet.exps.waveflow.ljspeech import LJSpeechClipCollector -from parakeet.exps.waveflow.ljspeech import LJSpeechCollector -from parakeet.models.waveflow import ConditionalWaveFlow -from parakeet.models.waveflow import WaveFlowLoss -from parakeet.training.cli import default_argument_parser -from parakeet.training.experiment import ExperimentBase -from parakeet.utils import mp_tools +from paddlespeech.t2s.data import dataset +from paddlespeech.t2s.exps.waveflow.config import get_cfg_defaults +from paddlespeech.t2s.exps.waveflow.ljspeech import LJSpeech +from paddlespeech.t2s.exps.waveflow.ljspeech import LJSpeechClipCollector +from paddlespeech.t2s.exps.waveflow.ljspeech import LJSpeechCollector +from paddlespeech.t2s.models.waveflow import ConditionalWaveFlow +from paddlespeech.t2s.models.waveflow import WaveFlowLoss +from paddlespeech.t2s.training.cli import default_argument_parser +from paddlespeech.t2s.training.experiment import ExperimentBase +from paddlespeech.t2s.utils import mp_tools class Experiment(ExperimentBase): diff --git a/parakeet/frontend/__init__.py b/paddlespeech/t2s/frontend/__init__.py similarity index 100% rename from parakeet/frontend/__init__.py rename to paddlespeech/t2s/frontend/__init__.py diff --git a/parakeet/frontend/arpabet.py b/paddlespeech/t2s/frontend/arpabet.py similarity index 98% rename from parakeet/frontend/arpabet.py rename to paddlespeech/t2s/frontend/arpabet.py index ae9212b27fcf9470e044af1144311c6d0b514120..094a2bfacbfc585c2b9557bd121be929d13cf4b5 100644 --- a/parakeet/frontend/arpabet.py +++ b/paddlespeech/t2s/frontend/arpabet.py @@ -11,7 +11,7 @@ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. -from parakeet.frontend.phonectic import Phonetics +from paddlespeech.t2s.frontend.phonectic import Phonetics """ A phonology system with ARPABET symbols and limited punctuations. The G2P conversion is done by g2p_en. @@ -19,7 +19,7 @@ conversion is done by g2p_en. Note that g2p_en does not handle words with hypen well. So make sure the input sentence is first normalized. """ -from parakeet.frontend.vocab import Vocab +from paddlespeech.t2s.frontend.vocab import Vocab from g2p_en import G2p diff --git a/parakeet/frontend/generate_lexicon.py b/paddlespeech/t2s/frontend/generate_lexicon.py similarity index 100% rename from parakeet/frontend/generate_lexicon.py rename to paddlespeech/t2s/frontend/generate_lexicon.py diff --git a/paddlespeech/t2s/frontend/normalizer/__init__.py b/paddlespeech/t2s/frontend/normalizer/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..a03329f1e7f3e3d69ef49a46241511a4d05c098c --- /dev/null +++ b/paddlespeech/t2s/frontend/normalizer/__init__.py @@ -0,0 +1,15 @@ +# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved. +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +from paddlespeech.t2s.frontend.normalizer.normalizer import * +from paddlespeech.t2s.frontend.normalizer.numbers import * diff --git a/parakeet/frontend/normalizer/abbrrviation.py b/paddlespeech/t2s/frontend/normalizer/abbrrviation.py similarity index 100% rename from parakeet/frontend/normalizer/abbrrviation.py rename to paddlespeech/t2s/frontend/normalizer/abbrrviation.py diff --git a/parakeet/frontend/normalizer/acronyms.py b/paddlespeech/t2s/frontend/normalizer/acronyms.py similarity index 100% rename from parakeet/frontend/normalizer/acronyms.py rename to paddlespeech/t2s/frontend/normalizer/acronyms.py diff --git a/parakeet/frontend/normalizer/normalizer.py b/paddlespeech/t2s/frontend/normalizer/normalizer.py similarity index 94% rename from parakeet/frontend/normalizer/normalizer.py rename to paddlespeech/t2s/frontend/normalizer/normalizer.py index 795607e5df579f6bfd8589bd8578d8092e56133d..421ebd1f54194f7ac421e8eaa7a757baca2715ea 100644 --- a/parakeet/frontend/normalizer/normalizer.py +++ b/paddlespeech/t2s/frontend/normalizer/normalizer.py @@ -15,7 +15,7 @@ import re import unicodedata from builtins import str as unicode -from parakeet.frontend.normalizer.numbers import normalize_numbers +from paddlespeech.t2s.frontend.normalizer.numbers import normalize_numbers def normalize(sentence): diff --git a/parakeet/frontend/normalizer/numbers.py b/paddlespeech/t2s/frontend/normalizer/numbers.py similarity index 100% rename from parakeet/frontend/normalizer/numbers.py rename to paddlespeech/t2s/frontend/normalizer/numbers.py diff --git a/parakeet/frontend/normalizer/width.py b/paddlespeech/t2s/frontend/normalizer/width.py similarity index 100% rename from parakeet/frontend/normalizer/width.py rename to paddlespeech/t2s/frontend/normalizer/width.py diff --git a/parakeet/frontend/phonectic.py b/paddlespeech/t2s/frontend/phonectic.py similarity index 97% rename from parakeet/frontend/phonectic.py rename to paddlespeech/t2s/frontend/phonectic.py index 874c19795d70e4681db3f38944273d5d7859b3c2..8eac0b48e8ad96f807d788eebac6d3a026a0a7c2 100644 --- a/parakeet/frontend/phonectic.py +++ b/paddlespeech/t2s/frontend/phonectic.py @@ -17,9 +17,9 @@ from abc import abstractmethod from g2p_en import G2p from g2pM import G2pM -from parakeet.frontend.normalizer.normalizer import normalize -from parakeet.frontend.punctuation import get_punctuations -from parakeet.frontend.vocab import Vocab +from paddlespeech.t2s.frontend.normalizer.normalizer import normalize +from paddlespeech.t2s.frontend.punctuation import get_punctuations +from paddlespeech.t2s.frontend.vocab import Vocab # discard opencc untill we find an easy solution to install it on windows # from opencc import OpenCC diff --git a/parakeet/frontend/pinyin.py b/paddlespeech/t2s/frontend/pinyin.py similarity index 98% rename from parakeet/frontend/pinyin.py rename to paddlespeech/t2s/frontend/pinyin.py index 503bfd5d95d36e1b39693b41a5c2b6d6ae07cfd1..f99129ce38567742dacef67b607033a565afd843 100644 --- a/parakeet/frontend/pinyin.py +++ b/paddlespeech/t2s/frontend/pinyin.py @@ -26,8 +26,8 @@ from pypinyin.core import DefaultConverter from pypinyin.core import Pinyin from pypinyin.core import Style -from parakeet.frontend.phonectic import Phonetics -from parakeet.frontend.vocab import Vocab +from paddlespeech.t2s.frontend.phonectic import Phonetics +from paddlespeech.t2s.frontend.vocab import Vocab _punctuations = ['，', '。', '？', '！'] _initials = [ diff --git a/parakeet/frontend/punctuation.py b/paddlespeech/t2s/frontend/punctuation.py similarity index 100% rename from parakeet/frontend/punctuation.py rename to paddlespeech/t2s/frontend/punctuation.py diff --git a/parakeet/frontend/tone_sandhi.py b/paddlespeech/t2s/frontend/tone_sandhi.py similarity index 100% rename from parakeet/frontend/tone_sandhi.py rename to paddlespeech/t2s/frontend/tone_sandhi.py diff --git a/parakeet/frontend/vocab.py b/paddlespeech/t2s/frontend/vocab.py similarity index 100% rename from parakeet/frontend/vocab.py rename to paddlespeech/t2s/frontend/vocab.py diff --git a/parakeet/frontend/zh_frontend.py b/paddlespeech/t2s/frontend/zh_frontend.py similarity index 98% rename from parakeet/frontend/zh_frontend.py rename to paddlespeech/t2s/frontend/zh_frontend.py index 04ce235f7b3400a1c1c60c5786316d1958b6c91a..33bf5ab2479053b35c6d283ea83d3197eceab3bc 100644 --- a/parakeet/frontend/zh_frontend.py +++ b/paddlespeech/t2s/frontend/zh_frontend.py @@ -22,9 +22,9 @@ from g2pM import G2pM from pypinyin import lazy_pinyin from pypinyin import Style -from parakeet.frontend.generate_lexicon import generate_lexicon -from parakeet.frontend.tone_sandhi import ToneSandhi -from parakeet.frontend.zh_normalization.text_normlization import TextNormalizer +from paddlespeech.t2s.frontend.generate_lexicon import generate_lexicon +from paddlespeech.t2s.frontend.tone_sandhi import ToneSandhi +from paddlespeech.t2s.frontend.zh_normalization.text_normlization import TextNormalizer class Frontend(): diff --git a/parakeet/frontend/zh_normalization/README.md b/paddlespeech/t2s/frontend/zh_normalization/README.md similarity index 100% rename from parakeet/frontend/zh_normalization/README.md rename to paddlespeech/t2s/frontend/zh_normalization/README.md diff --git a/paddlespeech/t2s/frontend/zh_normalization/__init__.py b/paddlespeech/t2s/frontend/zh_normalization/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..a9d1f44d707fc182f2ba22a34be1cd200e9dafd8 --- /dev/null +++ b/paddlespeech/t2s/frontend/zh_normalization/__init__.py @@ -0,0 +1,14 @@ +# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved. +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +from paddlespeech.t2s.frontend.zh_normalization.text_normlization import * diff --git a/parakeet/frontend/zh_normalization/char_convert.py b/paddlespeech/t2s/frontend/zh_normalization/char_convert.py similarity index 100% rename from parakeet/frontend/zh_normalization/char_convert.py rename to paddlespeech/t2s/frontend/zh_normalization/char_convert.py diff --git a/parakeet/frontend/zh_normalization/chronology.py b/paddlespeech/t2s/frontend/zh_normalization/chronology.py similarity index 100% rename from parakeet/frontend/zh_normalization/chronology.py rename to paddlespeech/t2s/frontend/zh_normalization/chronology.py diff --git a/parakeet/frontend/zh_normalization/constants.py b/paddlespeech/t2s/frontend/zh_normalization/constants.py similarity index 100% rename from parakeet/frontend/zh_normalization/constants.py rename to paddlespeech/t2s/frontend/zh_normalization/constants.py diff --git a/parakeet/frontend/zh_normalization/num.py b/paddlespeech/t2s/frontend/zh_normalization/num.py similarity index 100% rename from parakeet/frontend/zh_normalization/num.py rename to paddlespeech/t2s/frontend/zh_normalization/num.py diff --git a/parakeet/frontend/zh_normalization/phonecode.py b/paddlespeech/t2s/frontend/zh_normalization/phonecode.py similarity index 100% rename from parakeet/frontend/zh_normalization/phonecode.py rename to paddlespeech/t2s/frontend/zh_normalization/phonecode.py diff --git a/parakeet/frontend/zh_normalization/quantifier.py b/paddlespeech/t2s/frontend/zh_normalization/quantifier.py similarity index 100% rename from parakeet/frontend/zh_normalization/quantifier.py rename to paddlespeech/t2s/frontend/zh_normalization/quantifier.py diff --git a/parakeet/frontend/zh_normalization/text_normlization.py b/paddlespeech/t2s/frontend/zh_normalization/text_normlization.py similarity index 100% rename from parakeet/frontend/zh_normalization/text_normlization.py rename to paddlespeech/t2s/frontend/zh_normalization/text_normlization.py diff --git a/parakeet/models/__init__.py b/paddlespeech/t2s/models/__init__.py similarity index 100% rename from parakeet/models/__init__.py rename to paddlespeech/t2s/models/__init__.py diff --git a/parakeet/models/fastspeech2/__init__.py b/paddlespeech/t2s/models/fastspeech2/__init__.py similarity index 100% rename from parakeet/models/fastspeech2/__init__.py rename to paddlespeech/t2s/models/fastspeech2/__init__.py diff --git a/parakeet/models/fastspeech2/fastspeech2.py b/paddlespeech/t2s/models/fastspeech2/fastspeech2.py similarity index 97% rename from parakeet/models/fastspeech2/fastspeech2.py rename to paddlespeech/t2s/models/fastspeech2/fastspeech2.py index 192517b168a6311764ab768cfc78cfb03829aeb2..754fef2a3ce49165ceba876dcd94353a4f0d0626 100644 --- a/parakeet/models/fastspeech2/fastspeech2.py +++ b/paddlespeech/t2s/models/fastspeech2/fastspeech2.py @@ -21,17 +21,17 @@ import paddle.nn.functional as F from paddle import nn from typeguard import check_argument_types -from parakeet.modules.fastspeech2_predictor.duration_predictor import DurationPredictor -from parakeet.modules.fastspeech2_predictor.duration_predictor import DurationPredictorLoss -from parakeet.modules.fastspeech2_predictor.length_regulator import LengthRegulator -from parakeet.modules.fastspeech2_predictor.variance_predictor import VariancePredictor -from parakeet.modules.fastspeech2_transformer.embedding import PositionalEncoding -from parakeet.modules.fastspeech2_transformer.embedding import ScaledPositionalEncoding -from parakeet.modules.fastspeech2_transformer.encoder import Encoder as TransformerEncoder -from parakeet.modules.nets_utils import initialize -from parakeet.modules.nets_utils import make_non_pad_mask -from parakeet.modules.nets_utils import make_pad_mask -from parakeet.modules.tacotron2.decoder import Postnet +from paddlespeech.t2s.modules.fastspeech2_predictor.duration_predictor import DurationPredictor +from paddlespeech.t2s.modules.fastspeech2_predictor.duration_predictor import DurationPredictorLoss +from paddlespeech.t2s.modules.fastspeech2_predictor.length_regulator import LengthRegulator +from paddlespeech.t2s.modules.fastspeech2_predictor.variance_predictor import VariancePredictor +from paddlespeech.t2s.modules.fastspeech2_transformer.embedding import PositionalEncoding +from paddlespeech.t2s.modules.fastspeech2_transformer.embedding import ScaledPositionalEncoding +from paddlespeech.t2s.modules.fastspeech2_transformer.encoder import Encoder as TransformerEncoder +from paddlespeech.t2s.modules.nets_utils import initialize +from paddlespeech.t2s.modules.nets_utils import make_non_pad_mask +from paddlespeech.t2s.modules.nets_utils import make_pad_mask +from paddlespeech.t2s.modules.tacotron2.decoder import Postnet class FastSpeech2(nn.Layer): diff --git a/parakeet/models/fastspeech2/fastspeech2_updater.py b/paddlespeech/t2s/models/fastspeech2/fastspeech2_updater.py similarity index 95% rename from parakeet/models/fastspeech2/fastspeech2_updater.py rename to paddlespeech/t2s/models/fastspeech2/fastspeech2_updater.py index ea23ec2af5f78e295c6f0a56abd8331751bb9295..4297c8b6166ebddf3f754019826e8c2d74e6cb26 100644 --- a/parakeet/models/fastspeech2/fastspeech2_updater.py +++ b/paddlespeech/t2s/models/fastspeech2/fastspeech2_updater.py @@ -15,10 +15,10 @@ import logging from paddle import distributed as dist -from parakeet.models.fastspeech2 import FastSpeech2Loss -from parakeet.training.extensions.evaluator import StandardEvaluator -from parakeet.training.reporter import report -from parakeet.training.updaters.standard_updater import StandardUpdater +from paddlespeech.t2s.models.fastspeech2 import FastSpeech2Loss +from paddlespeech.t2s.training.extensions.evaluator import StandardEvaluator +from paddlespeech.t2s.training.reporter import report +from paddlespeech.t2s.training.updaters.standard_updater import StandardUpdater logging.basicConfig( format='%(asctime)s [%(levelname)s] [%(filename)s:%(lineno)d] %(message)s', datefmt='[%Y-%m-%d %H:%M:%S]') diff --git a/parakeet/models/lstm_speaker_encoder.py b/paddlespeech/t2s/models/lstm_speaker_encoder.py similarity index 100% rename from parakeet/models/lstm_speaker_encoder.py rename to paddlespeech/t2s/models/lstm_speaker_encoder.py diff --git a/parakeet/models/melgan/__init__.py b/paddlespeech/t2s/models/melgan/__init__.py similarity index 100% rename from parakeet/models/melgan/__init__.py rename to paddlespeech/t2s/models/melgan/__init__.py diff --git a/parakeet/models/melgan/melgan.py b/paddlespeech/t2s/models/melgan/melgan.py similarity index 98% rename from parakeet/models/melgan/melgan.py rename to paddlespeech/t2s/models/melgan/melgan.py index 5de8a298dd5559298703115c9bbedf23624a1a41..94d6e631b9283b075167e216469b259b490b8acd 100644 --- a/parakeet/models/melgan/melgan.py +++ b/paddlespeech/t2s/models/melgan/melgan.py @@ -20,11 +20,11 @@ import numpy as np import paddle from paddle import nn -from parakeet.modules.causal_conv import CausalConv1D -from parakeet.modules.causal_conv import CausalConv1DTranspose -from parakeet.modules.nets_utils import initialize -from parakeet.modules.pqmf import PQMF -from parakeet.modules.residual_stack import ResidualStack +from paddlespeech.t2s.modules.causal_conv import CausalConv1D +from paddlespeech.t2s.modules.causal_conv import CausalConv1DTranspose +from paddlespeech.t2s.modules.nets_utils import initialize +from paddlespeech.t2s.modules.pqmf import PQMF +from paddlespeech.t2s.modules.residual_stack import ResidualStack class MelGANGenerator(nn.Layer): diff --git a/parakeet/models/melgan/multi_band_melgan_updater.py b/paddlespeech/t2s/models/melgan/multi_band_melgan_updater.py similarity index 97% rename from parakeet/models/melgan/multi_band_melgan_updater.py rename to paddlespeech/t2s/models/melgan/multi_band_melgan_updater.py index 0783cb9749ab70434a5395ad07d5a71956195e64..a5d4cdeb99415461db3a9eaeb3ffddd9c38f957e 100644 --- a/parakeet/models/melgan/multi_band_melgan_updater.py +++ b/paddlespeech/t2s/models/melgan/multi_band_melgan_updater.py @@ -21,10 +21,10 @@ from paddle.nn import Layer from paddle.optimizer import Optimizer from paddle.optimizer.lr import LRScheduler -from parakeet.training.extensions.evaluator import StandardEvaluator -from parakeet.training.reporter import report -from parakeet.training.updaters.standard_updater import StandardUpdater -from parakeet.training.updaters.standard_updater import UpdaterState +from paddlespeech.t2s.training.extensions.evaluator import StandardEvaluator +from paddlespeech.t2s.training.reporter import report +from paddlespeech.t2s.training.updaters.standard_updater import StandardUpdater +from paddlespeech.t2s.training.updaters.standard_updater import UpdaterState logging.basicConfig( format='%(asctime)s [%(levelname)s] [%(filename)s:%(lineno)d] %(message)s', datefmt='[%Y-%m-%d %H:%M:%S]') diff --git a/parakeet/models/parallel_wavegan/__init__.py b/paddlespeech/t2s/models/parallel_wavegan/__init__.py similarity index 100% rename from parakeet/models/parallel_wavegan/__init__.py rename to paddlespeech/t2s/models/parallel_wavegan/__init__.py diff --git a/parakeet/models/parallel_wavegan/parallel_wavegan.py b/paddlespeech/t2s/models/parallel_wavegan/parallel_wavegan.py similarity index 100% rename from parakeet/models/parallel_wavegan/parallel_wavegan.py rename to paddlespeech/t2s/models/parallel_wavegan/parallel_wavegan.py diff --git a/parakeet/models/parallel_wavegan/parallel_wavegan_updater.py b/paddlespeech/t2s/models/parallel_wavegan/parallel_wavegan_updater.py similarity index 96% rename from parakeet/models/parallel_wavegan/parallel_wavegan_updater.py rename to paddlespeech/t2s/models/parallel_wavegan/parallel_wavegan_updater.py index 7bd59881d97ea813cbe2044152f9ede509c96e71..4e3daaa3c46f54218eb861697e0d7a5dc528785d 100644 --- a/parakeet/models/parallel_wavegan/parallel_wavegan_updater.py +++ b/paddlespeech/t2s/models/parallel_wavegan/parallel_wavegan_updater.py @@ -22,10 +22,10 @@ from paddle.optimizer import Optimizer from paddle.optimizer.lr import LRScheduler from timer import timer -from parakeet.training.extensions.evaluator import StandardEvaluator -from parakeet.training.reporter import report -from parakeet.training.updaters.standard_updater import StandardUpdater -from parakeet.training.updaters.standard_updater import UpdaterState +from paddlespeech.t2s.training.extensions.evaluator import StandardEvaluator +from paddlespeech.t2s.training.reporter import report +from paddlespeech.t2s.training.updaters.standard_updater import StandardUpdater +from paddlespeech.t2s.training.updaters.standard_updater import UpdaterState logging.basicConfig( format='%(asctime)s [%(levelname)s] [%(filename)s:%(lineno)d] %(message)s', datefmt='[%Y-%m-%d %H:%M:%S]') diff --git a/parakeet/models/speedyspeech/__init__.py b/paddlespeech/t2s/models/speedyspeech/__init__.py similarity index 100% rename from parakeet/models/speedyspeech/__init__.py rename to paddlespeech/t2s/models/speedyspeech/__init__.py diff --git a/parakeet/models/speedyspeech/speedyspeech.py b/paddlespeech/t2s/models/speedyspeech/speedyspeech.py similarity index 98% rename from parakeet/models/speedyspeech/speedyspeech.py rename to paddlespeech/t2s/models/speedyspeech/speedyspeech.py index dea567b6afc0c34ed99936648db5783350deade5..0689ec45337c869812646f0acd45f14fda956dee 100644 --- a/parakeet/models/speedyspeech/speedyspeech.py +++ b/paddlespeech/t2s/models/speedyspeech/speedyspeech.py @@ -14,8 +14,8 @@ import paddle from paddle import nn -from parakeet.modules.expansion import expand -from parakeet.modules.positional_encoding import sinusoid_position_encoding +from paddlespeech.t2s.modules.expansion import expand +from paddlespeech.t2s.modules.positional_encoding import sinusoid_position_encoding class ResidualBlock(nn.Layer): diff --git a/parakeet/models/speedyspeech/speedyspeech_updater.py b/paddlespeech/t2s/models/speedyspeech/speedyspeech_updater.py similarity index 93% rename from parakeet/models/speedyspeech/speedyspeech_updater.py rename to paddlespeech/t2s/models/speedyspeech/speedyspeech_updater.py index a17c93c7924ca42784b6dabeebeb908bc0f33030..4883a87e53a527d90e205755a0e98b5257955139 100644 --- a/parakeet/models/speedyspeech/speedyspeech_updater.py +++ b/paddlespeech/t2s/models/speedyspeech/speedyspeech_updater.py @@ -18,12 +18,12 @@ from paddle import distributed as dist from paddle.fluid.layers import huber_loss from paddle.nn import functional as F -from parakeet.modules.losses import masked_l1_loss -from parakeet.modules.losses import weighted_mean -from parakeet.modules.ssim import ssim -from parakeet.training.extensions.evaluator import StandardEvaluator -from parakeet.training.reporter import report -from parakeet.training.updaters.standard_updater import StandardUpdater +from paddlespeech.t2s.modules.losses import masked_l1_loss +from paddlespeech.t2s.modules.losses import weighted_mean +from paddlespeech.t2s.modules.ssim import ssim +from paddlespeech.t2s.training.extensions.evaluator import StandardEvaluator +from paddlespeech.t2s.training.reporter import report +from paddlespeech.t2s.training.updaters.standard_updater import StandardUpdater logging.basicConfig( format='%(asctime)s [%(levelname)s] [%(filename)s:%(lineno)d] %(message)s', datefmt='[%Y-%m-%d %H:%M:%S]') diff --git a/parakeet/models/tacotron2.py b/paddlespeech/t2s/models/tacotron2.py similarity index 99% rename from parakeet/models/tacotron2.py rename to paddlespeech/t2s/models/tacotron2.py index 07af6b3f51adf449e817d2a2d6ed8668757281ff..b0946a5ba0c42b3c895b782993f8c47ef5e7a14c 100644 --- a/parakeet/models/tacotron2.py +++ b/paddlespeech/t2s/models/tacotron2.py @@ -20,10 +20,10 @@ from paddle.nn import functional as F from paddle.nn import initializer as I from tqdm import trange -from parakeet.modules.attention import LocationSensitiveAttention -from parakeet.modules.conv import Conv1dBatchNorm -from parakeet.modules.losses import guided_attention_loss -from parakeet.utils import checkpoint +from paddlespeech.t2s.modules.attention import LocationSensitiveAttention +from paddlespeech.t2s.modules.conv import Conv1dBatchNorm +from paddlespeech.t2s.modules.losses import guided_attention_loss +from paddlespeech.t2s.utils import checkpoint __all__ = ["Tacotron2", "Tacotron2Loss"] diff --git a/parakeet/models/transformer_tts/__init__.py b/paddlespeech/t2s/models/transformer_tts/__init__.py similarity index 100% rename from parakeet/models/transformer_tts/__init__.py rename to paddlespeech/t2s/models/transformer_tts/__init__.py diff --git a/parakeet/models/transformer_tts/transformer_tts.py b/paddlespeech/t2s/models/transformer_tts/transformer_tts.py similarity index 97% rename from parakeet/models/transformer_tts/transformer_tts.py rename to paddlespeech/t2s/models/transformer_tts/transformer_tts.py index bb3674f383d70ee7bd6539196a8932c5715884ac..f8feb553a1137092edab285f3b1bf2a2f8cd7db4 100644 --- a/parakeet/models/transformer_tts/transformer_tts.py +++ b/paddlespeech/t2s/models/transformer_tts/transformer_tts.py @@ -22,19 +22,19 @@ import paddle.nn.functional as F from paddle import nn from typeguard import check_argument_types -from parakeet.modules.fastspeech2_transformer.attention import MultiHeadedAttention -from parakeet.modules.fastspeech2_transformer.decoder import Decoder -from parakeet.modules.fastspeech2_transformer.embedding import PositionalEncoding -from parakeet.modules.fastspeech2_transformer.embedding import ScaledPositionalEncoding -from parakeet.modules.fastspeech2_transformer.encoder import Encoder -from parakeet.modules.fastspeech2_transformer.mask import subsequent_mask -from parakeet.modules.nets_utils import initialize -from parakeet.modules.nets_utils import make_non_pad_mask -from parakeet.modules.nets_utils import make_pad_mask -from parakeet.modules.style_encoder import StyleEncoder -from parakeet.modules.tacotron2.decoder import Postnet -from parakeet.modules.tacotron2.decoder import Prenet as DecoderPrenet -from parakeet.modules.tacotron2.encoder import Encoder as EncoderPrenet +from paddlespeech.t2s.modules.fastspeech2_transformer.attention import MultiHeadedAttention +from paddlespeech.t2s.modules.fastspeech2_transformer.decoder import Decoder +from paddlespeech.t2s.modules.fastspeech2_transformer.embedding import PositionalEncoding +from paddlespeech.t2s.modules.fastspeech2_transformer.embedding import ScaledPositionalEncoding +from paddlespeech.t2s.modules.fastspeech2_transformer.encoder import Encoder +from paddlespeech.t2s.modules.fastspeech2_transformer.mask import subsequent_mask +from paddlespeech.t2s.modules.nets_utils import initialize +from paddlespeech.t2s.modules.nets_utils import make_non_pad_mask +from paddlespeech.t2s.modules.nets_utils import make_pad_mask +from paddlespeech.t2s.modules.style_encoder import StyleEncoder +from paddlespeech.t2s.modules.tacotron2.decoder import Postnet +from paddlespeech.t2s.modules.tacotron2.decoder import Prenet as DecoderPrenet +from paddlespeech.t2s.modules.tacotron2.encoder import Encoder as EncoderPrenet class TransformerTTS(nn.Layer): diff --git a/parakeet/models/transformer_tts/transformer_tts_updater.py b/paddlespeech/t2s/models/transformer_tts/transformer_tts_updater.py similarity index 97% rename from parakeet/models/transformer_tts/transformer_tts_updater.py rename to paddlespeech/t2s/models/transformer_tts/transformer_tts_updater.py index 4bec475859316bb580868a031489a82551d9a546..f16cf4dd9e76e7992197aa486352ac08c25198e1 100644 --- a/parakeet/models/transformer_tts/transformer_tts_updater.py +++ b/paddlespeech/t2s/models/transformer_tts/transformer_tts_updater.py @@ -17,11 +17,11 @@ from typing import Sequence import paddle from paddle import distributed as dist -from parakeet.models.transformer_tts import GuidedMultiHeadAttentionLoss -from parakeet.models.transformer_tts import TransformerTTSLoss -from parakeet.training.extensions.evaluator import StandardEvaluator -from parakeet.training.reporter import report -from parakeet.training.updaters.standard_updater import StandardUpdater +from paddlespeech.t2s.models.transformer_tts import GuidedMultiHeadAttentionLoss +from paddlespeech.t2s.models.transformer_tts import TransformerTTSLoss +from paddlespeech.t2s.training.extensions.evaluator import StandardEvaluator +from paddlespeech.t2s.training.reporter import report +from paddlespeech.t2s.training.updaters.standard_updater import StandardUpdater logging.basicConfig( format='%(asctime)s [%(levelname)s] [%(filename)s:%(lineno)d] %(message)s', datefmt='[%Y-%m-%d %H:%M:%S]') diff --git a/parakeet/models/waveflow.py b/paddlespeech/t2s/models/waveflow.py similarity index 99% rename from parakeet/models/waveflow.py rename to paddlespeech/t2s/models/waveflow.py index b6317bf8b5c83aee6a70b99208f691e2a8c88b8f..c57429db1fc3ea9587e8c3a0eaec95c09330da9f 100644 --- a/parakeet/models/waveflow.py +++ b/paddlespeech/t2s/models/waveflow.py @@ -23,8 +23,8 @@ from paddle import nn from paddle.nn import functional as F from paddle.nn import initializer as I -from parakeet.modules import geometry as geo -from parakeet.utils import checkpoint +from paddlespeech.t2s.modules import geometry as geo +from paddlespeech.t2s.utils import checkpoint __all__ = ["WaveFlow", "ConditionalWaveFlow", "WaveFlowLoss"] diff --git a/parakeet/modules/__init__.py b/paddlespeech/t2s/modules/__init__.py similarity index 100% rename from parakeet/modules/__init__.py rename to paddlespeech/t2s/modules/__init__.py diff --git a/parakeet/modules/adversarial_loss.py b/paddlespeech/t2s/modules/adversarial_loss.py similarity index 100% rename from parakeet/modules/adversarial_loss.py rename to paddlespeech/t2s/modules/adversarial_loss.py diff --git a/parakeet/modules/attention.py b/paddlespeech/t2s/modules/attention.py similarity index 100% rename from parakeet/modules/attention.py rename to paddlespeech/t2s/modules/attention.py diff --git a/parakeet/modules/audio.py b/paddlespeech/t2s/modules/audio.py similarity index 100% rename from parakeet/modules/audio.py rename to paddlespeech/t2s/modules/audio.py diff --git a/parakeet/modules/causal_conv.py b/paddlespeech/t2s/modules/causal_conv.py similarity index 100% rename from parakeet/modules/causal_conv.py rename to paddlespeech/t2s/modules/causal_conv.py diff --git a/parakeet/modules/conv.py b/paddlespeech/t2s/modules/conv.py similarity index 100% rename from parakeet/modules/conv.py rename to paddlespeech/t2s/modules/conv.py diff --git a/parakeet/modules/expansion.py b/paddlespeech/t2s/modules/expansion.py similarity index 100% rename from parakeet/modules/expansion.py rename to paddlespeech/t2s/modules/expansion.py diff --git a/parakeet/modules/fastspeech2_predictor/__init__.py b/paddlespeech/t2s/modules/fastspeech2_predictor/__init__.py similarity index 100% rename from parakeet/modules/fastspeech2_predictor/__init__.py rename to paddlespeech/t2s/modules/fastspeech2_predictor/__init__.py diff --git a/parakeet/modules/fastspeech2_predictor/duration_predictor.py b/paddlespeech/t2s/modules/fastspeech2_predictor/duration_predictor.py similarity index 97% rename from parakeet/modules/fastspeech2_predictor/duration_predictor.py rename to paddlespeech/t2s/modules/fastspeech2_predictor/duration_predictor.py index d0f5262c5e44dd7565418962d309e1b63a51541e..eac7cf99e5fc1c152563032016edc504c2bc99e8 100644 --- a/parakeet/modules/fastspeech2_predictor/duration_predictor.py +++ b/paddlespeech/t2s/modules/fastspeech2_predictor/duration_predictor.py @@ -15,8 +15,8 @@ import paddle from paddle import nn -from parakeet.modules.layer_norm import LayerNorm -from parakeet.modules.masked_fill import masked_fill +from paddlespeech.t2s.modules.layer_norm import LayerNorm +from paddlespeech.t2s.modules.masked_fill import masked_fill class DurationPredictor(nn.Layer): diff --git a/parakeet/modules/fastspeech2_predictor/length_regulator.py b/paddlespeech/t2s/modules/fastspeech2_predictor/length_regulator.py similarity index 100% rename from parakeet/modules/fastspeech2_predictor/length_regulator.py rename to paddlespeech/t2s/modules/fastspeech2_predictor/length_regulator.py diff --git a/parakeet/modules/fastspeech2_predictor/variance_predictor.py b/paddlespeech/t2s/modules/fastspeech2_predictor/variance_predictor.py similarity index 96% rename from parakeet/modules/fastspeech2_predictor/variance_predictor.py rename to paddlespeech/t2s/modules/fastspeech2_predictor/variance_predictor.py index 0a980dd585a28addc92479259230a3cff32cb377..0fd108d323b75e21d3132d6164b709a8514156aa 100644 --- a/parakeet/modules/fastspeech2_predictor/variance_predictor.py +++ b/paddlespeech/t2s/modules/fastspeech2_predictor/variance_predictor.py @@ -16,8 +16,8 @@ import paddle from paddle import nn from typeguard import check_argument_types -from parakeet.modules.layer_norm import LayerNorm -from parakeet.modules.masked_fill import masked_fill +from paddlespeech.t2s.modules.layer_norm import LayerNorm +from paddlespeech.t2s.modules.masked_fill import masked_fill class VariancePredictor(nn.Layer): diff --git a/parakeet/modules/fastspeech2_transformer/__init__.py b/paddlespeech/t2s/modules/fastspeech2_transformer/__init__.py similarity index 100% rename from parakeet/modules/fastspeech2_transformer/__init__.py rename to paddlespeech/t2s/modules/fastspeech2_transformer/__init__.py diff --git a/parakeet/modules/fastspeech2_transformer/attention.py b/paddlespeech/t2s/modules/fastspeech2_transformer/attention.py similarity index 98% rename from parakeet/modules/fastspeech2_transformer/attention.py rename to paddlespeech/t2s/modules/fastspeech2_transformer/attention.py index 0bac47426d38ca002b65b6dd88e17033d8a88fa3..a61f1245d34c75d7fd66bc7a6a111d9d8ef858a3 100644 --- a/parakeet/modules/fastspeech2_transformer/attention.py +++ b/paddlespeech/t2s/modules/fastspeech2_transformer/attention.py @@ -18,7 +18,7 @@ import numpy import paddle from paddle import nn -from parakeet.modules.masked_fill import masked_fill +from paddlespeech.t2s.modules.masked_fill import masked_fill class MultiHeadedAttention(nn.Layer): diff --git a/parakeet/modules/fastspeech2_transformer/decoder.py b/paddlespeech/t2s/modules/fastspeech2_transformer/decoder.py similarity index 93% rename from parakeet/modules/fastspeech2_transformer/decoder.py rename to paddlespeech/t2s/modules/fastspeech2_transformer/decoder.py index 0f09014f628669ee5f74b33116cb25af9daebee5..c41e39955700d2ff63431b3104699167857bc8f6 100644 --- a/parakeet/modules/fastspeech2_transformer/decoder.py +++ b/paddlespeech/t2s/modules/fastspeech2_transformer/decoder.py @@ -22,14 +22,14 @@ import paddle import paddle.nn.functional as F from paddle import nn -from parakeet.modules.fastspeech2_transformer.attention import MultiHeadedAttention -from parakeet.modules.fastspeech2_transformer.decoder_layer import DecoderLayer -from parakeet.modules.fastspeech2_transformer.embedding import PositionalEncoding -from parakeet.modules.fastspeech2_transformer.lightconv import LightweightConvolution -from parakeet.modules.fastspeech2_transformer.mask import subsequent_mask -from parakeet.modules.fastspeech2_transformer.positionwise_feed_forward import PositionwiseFeedForward -from parakeet.modules.fastspeech2_transformer.repeat import repeat -from parakeet.modules.layer_norm import LayerNorm +from paddlespeech.t2s.modules.fastspeech2_transformer.attention import MultiHeadedAttention +from paddlespeech.t2s.modules.fastspeech2_transformer.decoder_layer import DecoderLayer +from paddlespeech.t2s.modules.fastspeech2_transformer.embedding import PositionalEncoding +from paddlespeech.t2s.modules.fastspeech2_transformer.lightconv import LightweightConvolution +from paddlespeech.t2s.modules.fastspeech2_transformer.mask import subsequent_mask +from paddlespeech.t2s.modules.fastspeech2_transformer.positionwise_feed_forward import PositionwiseFeedForward +from paddlespeech.t2s.modules.fastspeech2_transformer.repeat import repeat +from paddlespeech.t2s.modules.layer_norm import LayerNorm class Decoder(nn.Layer): diff --git a/parakeet/modules/fastspeech2_transformer/decoder_layer.py b/paddlespeech/t2s/modules/fastspeech2_transformer/decoder_layer.py similarity index 98% rename from parakeet/modules/fastspeech2_transformer/decoder_layer.py rename to paddlespeech/t2s/modules/fastspeech2_transformer/decoder_layer.py index f968051e629ae818aea03411c9295463341d68f3..9b042483b058f495f1cc1117bfbb53205e7171e2 100644 --- a/parakeet/modules/fastspeech2_transformer/decoder_layer.py +++ b/paddlespeech/t2s/modules/fastspeech2_transformer/decoder_layer.py @@ -15,7 +15,7 @@ import paddle from paddle import nn -from parakeet.modules.layer_norm import LayerNorm +from paddlespeech.t2s.modules.layer_norm import LayerNorm class DecoderLayer(nn.Layer): diff --git a/parakeet/modules/fastspeech2_transformer/embedding.py b/paddlespeech/t2s/modules/fastspeech2_transformer/embedding.py similarity index 100% rename from parakeet/modules/fastspeech2_transformer/embedding.py rename to paddlespeech/t2s/modules/fastspeech2_transformer/embedding.py diff --git a/parakeet/modules/fastspeech2_transformer/encoder.py b/paddlespeech/t2s/modules/fastspeech2_transformer/encoder.py similarity index 92% rename from parakeet/modules/fastspeech2_transformer/encoder.py rename to paddlespeech/t2s/modules/fastspeech2_transformer/encoder.py index 996e9dee08aab5069f22d0e144f886687cc077dd..904b9d8b1f3a3770035cc6df76dca73ab56063e8 100644 --- a/parakeet/modules/fastspeech2_transformer/encoder.py +++ b/paddlespeech/t2s/modules/fastspeech2_transformer/encoder.py @@ -15,13 +15,13 @@ import logging from paddle import nn -from parakeet.modules.fastspeech2_transformer.attention import MultiHeadedAttention -from parakeet.modules.fastspeech2_transformer.embedding import PositionalEncoding -from parakeet.modules.fastspeech2_transformer.encoder_layer import EncoderLayer -from parakeet.modules.fastspeech2_transformer.multi_layer_conv import Conv1dLinear -from parakeet.modules.fastspeech2_transformer.multi_layer_conv import MultiLayeredConv1d -from parakeet.modules.fastspeech2_transformer.positionwise_feed_forward import PositionwiseFeedForward -from parakeet.modules.fastspeech2_transformer.repeat import repeat +from paddlespeech.t2s.modules.fastspeech2_transformer.attention import MultiHeadedAttention +from paddlespeech.t2s.modules.fastspeech2_transformer.embedding import PositionalEncoding +from paddlespeech.t2s.modules.fastspeech2_transformer.encoder_layer import EncoderLayer +from paddlespeech.t2s.modules.fastspeech2_transformer.multi_layer_conv import Conv1dLinear +from paddlespeech.t2s.modules.fastspeech2_transformer.multi_layer_conv import MultiLayeredConv1d +from paddlespeech.t2s.modules.fastspeech2_transformer.positionwise_feed_forward import PositionwiseFeedForward +from paddlespeech.t2s.modules.fastspeech2_transformer.repeat import repeat class Encoder(nn.Layer): diff --git a/parakeet/modules/fastspeech2_transformer/encoder_layer.py b/paddlespeech/t2s/modules/fastspeech2_transformer/encoder_layer.py similarity index 100% rename from parakeet/modules/fastspeech2_transformer/encoder_layer.py rename to paddlespeech/t2s/modules/fastspeech2_transformer/encoder_layer.py diff --git a/parakeet/modules/fastspeech2_transformer/lightconv.py b/paddlespeech/t2s/modules/fastspeech2_transformer/lightconv.py similarity index 97% rename from parakeet/modules/fastspeech2_transformer/lightconv.py rename to paddlespeech/t2s/modules/fastspeech2_transformer/lightconv.py index 061168848e75e1cd3a0255457d2292cd4a2f7b0a..3aceed318c52a9488b3d3eabc2063f0162287879 100644 --- a/parakeet/modules/fastspeech2_transformer/lightconv.py +++ b/paddlespeech/t2s/modules/fastspeech2_transformer/lightconv.py @@ -17,8 +17,8 @@ import paddle import paddle.nn.functional as F from paddle import nn -from parakeet.modules.glu import GLU -from parakeet.modules.masked_fill import masked_fill +from paddlespeech.t2s.modules.glu import GLU +from paddlespeech.t2s.modules.masked_fill import masked_fill MIN_VALUE = float(numpy.finfo(numpy.float32).min) diff --git a/parakeet/modules/fastspeech2_transformer/mask.py b/paddlespeech/t2s/modules/fastspeech2_transformer/mask.py similarity index 100% rename from parakeet/modules/fastspeech2_transformer/mask.py rename to paddlespeech/t2s/modules/fastspeech2_transformer/mask.py diff --git a/parakeet/modules/fastspeech2_transformer/multi_layer_conv.py b/paddlespeech/t2s/modules/fastspeech2_transformer/multi_layer_conv.py similarity index 100% rename from parakeet/modules/fastspeech2_transformer/multi_layer_conv.py rename to paddlespeech/t2s/modules/fastspeech2_transformer/multi_layer_conv.py diff --git a/parakeet/modules/fastspeech2_transformer/positionwise_feed_forward.py b/paddlespeech/t2s/modules/fastspeech2_transformer/positionwise_feed_forward.py similarity index 100% rename from parakeet/modules/fastspeech2_transformer/positionwise_feed_forward.py rename to paddlespeech/t2s/modules/fastspeech2_transformer/positionwise_feed_forward.py diff --git a/parakeet/modules/fastspeech2_transformer/repeat.py b/paddlespeech/t2s/modules/fastspeech2_transformer/repeat.py similarity index 100% rename from parakeet/modules/fastspeech2_transformer/repeat.py rename to paddlespeech/t2s/modules/fastspeech2_transformer/repeat.py diff --git a/parakeet/modules/geometry.py b/paddlespeech/t2s/modules/geometry.py similarity index 100% rename from parakeet/modules/geometry.py rename to paddlespeech/t2s/modules/geometry.py diff --git a/parakeet/modules/glu.py b/paddlespeech/t2s/modules/glu.py similarity index 100% rename from parakeet/modules/glu.py rename to paddlespeech/t2s/modules/glu.py diff --git a/parakeet/modules/layer_norm.py b/paddlespeech/t2s/modules/layer_norm.py similarity index 100% rename from parakeet/modules/layer_norm.py rename to paddlespeech/t2s/modules/layer_norm.py diff --git a/parakeet/modules/losses.py b/paddlespeech/t2s/modules/losses.py similarity index 100% rename from parakeet/modules/losses.py rename to paddlespeech/t2s/modules/losses.py diff --git a/parakeet/modules/masked_fill.py b/paddlespeech/t2s/modules/masked_fill.py similarity index 100% rename from parakeet/modules/masked_fill.py rename to paddlespeech/t2s/modules/masked_fill.py diff --git a/parakeet/modules/masking.py b/paddlespeech/t2s/modules/masking.py similarity index 100% rename from parakeet/modules/masking.py rename to paddlespeech/t2s/modules/masking.py diff --git a/parakeet/modules/nets_utils.py b/paddlespeech/t2s/modules/nets_utils.py similarity index 100% rename from parakeet/modules/nets_utils.py rename to paddlespeech/t2s/modules/nets_utils.py diff --git a/parakeet/modules/normalizer.py b/paddlespeech/t2s/modules/normalizer.py similarity index 100% rename from parakeet/modules/normalizer.py rename to paddlespeech/t2s/modules/normalizer.py diff --git a/parakeet/modules/positional_encoding.py b/paddlespeech/t2s/modules/positional_encoding.py similarity index 100% rename from parakeet/modules/positional_encoding.py rename to paddlespeech/t2s/modules/positional_encoding.py diff --git a/parakeet/modules/pqmf.py b/paddlespeech/t2s/modules/pqmf.py similarity index 100% rename from parakeet/modules/pqmf.py rename to paddlespeech/t2s/modules/pqmf.py diff --git a/parakeet/modules/residual_stack.py b/paddlespeech/t2s/modules/residual_stack.py similarity index 98% rename from parakeet/modules/residual_stack.py rename to paddlespeech/t2s/modules/residual_stack.py index 135c32e5770994b63bc0353c74c6089fc2992e83..71bd4f0c557313b81bdec069b7fc4be3fe5ad113 100644 --- a/parakeet/modules/residual_stack.py +++ b/paddlespeech/t2s/modules/residual_stack.py @@ -17,7 +17,7 @@ from typing import Dict from paddle import nn -from parakeet.modules.causal_conv import CausalConv1D +from paddlespeech.t2s.modules.causal_conv import CausalConv1D class ResidualStack(nn.Layer): diff --git a/parakeet/modules/ssim.py b/paddlespeech/t2s/modules/ssim.py similarity index 100% rename from parakeet/modules/ssim.py rename to paddlespeech/t2s/modules/ssim.py diff --git a/parakeet/modules/stft_loss.py b/paddlespeech/t2s/modules/stft_loss.py similarity index 100% rename from parakeet/modules/stft_loss.py rename to paddlespeech/t2s/modules/stft_loss.py diff --git a/parakeet/modules/style_encoder.py b/paddlespeech/t2s/modules/style_encoder.py similarity index 98% rename from parakeet/modules/style_encoder.py rename to paddlespeech/t2s/modules/style_encoder.py index fb27258ceeb566c966efca2892ffd2456060e854..c6b12d445af96436dbb404ef279a0751bc0dfe84 100644 --- a/parakeet/modules/style_encoder.py +++ b/paddlespeech/t2s/modules/style_encoder.py @@ -18,7 +18,7 @@ import paddle from paddle import nn from typeguard import check_argument_types -from parakeet.modules.fastspeech2_transformer.attention import MultiHeadedAttention as BaseMultiHeadedAttention +from paddlespeech.t2s.modules.fastspeech2_transformer.attention import MultiHeadedAttention as BaseMultiHeadedAttention class StyleEncoder(nn.Layer): diff --git a/parakeet/modules/tacotron2/__init__.py b/paddlespeech/t2s/modules/tacotron2/__init__.py similarity index 100% rename from parakeet/modules/tacotron2/__init__.py rename to paddlespeech/t2s/modules/tacotron2/__init__.py diff --git a/parakeet/modules/tacotron2/decoder.py b/paddlespeech/t2s/modules/tacotron2/decoder.py similarity index 100% rename from parakeet/modules/tacotron2/decoder.py rename to paddlespeech/t2s/modules/tacotron2/decoder.py diff --git a/parakeet/modules/tacotron2/encoder.py b/paddlespeech/t2s/modules/tacotron2/encoder.py similarity index 100% rename from parakeet/modules/tacotron2/encoder.py rename to paddlespeech/t2s/modules/tacotron2/encoder.py diff --git a/parakeet/modules/transformer.py b/paddlespeech/t2s/modules/transformer.py similarity index 99% rename from parakeet/modules/transformer.py rename to paddlespeech/t2s/modules/transformer.py index 490458befc531a192f714c4ebd265ba70e4d43d5..e50d58d44bc6663414a7390589d3a8d7ad6f2c5b 100644 --- a/parakeet/modules/transformer.py +++ b/paddlespeech/t2s/modules/transformer.py @@ -14,7 +14,7 @@ from paddle import nn from paddle.nn import functional as F -from parakeet.modules import attention as attn +from paddlespeech.t2s.modules import attention as attn __all__ = [ "PositionwiseFFN", diff --git a/parakeet/training/__init__.py b/paddlespeech/t2s/training/__init__.py similarity index 100% rename from parakeet/training/__init__.py rename to paddlespeech/t2s/training/__init__.py diff --git a/parakeet/training/cli.py b/paddlespeech/t2s/training/cli.py similarity index 91% rename from parakeet/training/cli.py rename to paddlespeech/t2s/training/cli.py index a6309941dea7021ded718c164df8498500110a3a..3b9fd42e3fcd6e9292f1ecebb4857c3daecacbf9 100644 --- a/parakeet/training/cli.py +++ b/paddlespeech/t2s/training/cli.py @@ -15,10 +15,10 @@ import argparse def default_argument_parser(): - r"""A simple yet genral argument parser for experiments with parakeet. + r"""A simple yet genral argument parser for experiments with t2s. - This is used in examples with parakeet. And it is intended to be used by - other experiments with parakeet. It requires a minimal set of command line + This is used in examples with t2s. And it is intended to be used by + other experiments with t2s. It requires a minimal set of command line arguments to start a training script. The ``--config`` and ``--opts`` are used for overwrite the deault @@ -34,7 +34,7 @@ def default_argument_parser(): See Also -------- - parakeet.training.experiment + paddlespeech.t2s.training.experiment Returns ------- diff --git a/parakeet/training/default_config.py b/paddlespeech/t2s/training/default_config.py similarity index 100% rename from parakeet/training/default_config.py rename to paddlespeech/t2s/training/default_config.py diff --git a/parakeet/training/experiment.py b/paddlespeech/t2s/training/experiment.py similarity index 99% rename from parakeet/training/experiment.py rename to paddlespeech/t2s/training/experiment.py index 739fd75de792d5c74c294acca92aa8f881e69c2a..7a6a7e992799a367c35143ae474d67f7a4d22a72 100644 --- a/parakeet/training/experiment.py +++ b/paddlespeech/t2s/training/experiment.py @@ -20,8 +20,8 @@ from paddle import distributed as dist from paddle.io import DistributedBatchSampler from visualdl import LogWriter -from parakeet.utils import checkpoint -from parakeet.utils import mp_tools +from paddlespeech.t2s.utils import checkpoint +from paddlespeech.t2s.utils import mp_tools __all__ = ["ExperimentBase"] diff --git a/parakeet/training/extension.py b/paddlespeech/t2s/training/extension.py similarity index 100% rename from parakeet/training/extension.py rename to paddlespeech/t2s/training/extension.py diff --git a/parakeet/training/extensions/__init__.py b/paddlespeech/t2s/training/extensions/__init__.py similarity index 100% rename from parakeet/training/extensions/__init__.py rename to paddlespeech/t2s/training/extensions/__init__.py diff --git a/parakeet/training/extensions/evaluator.py b/paddlespeech/t2s/training/extensions/evaluator.py similarity index 91% rename from parakeet/training/extensions/evaluator.py rename to paddlespeech/t2s/training/extensions/evaluator.py index 47b352728d9139774255cd2284723d9d06940f8e..28249d096655f84d3a60becea38273b184d30140 100644 --- a/parakeet/training/extensions/evaluator.py +++ b/paddlespeech/t2s/training/extensions/evaluator.py @@ -17,10 +17,10 @@ import paddle from paddle.io import DataLoader from paddle.nn import Layer -from parakeet.training import extension -from parakeet.training.reporter import DictSummary -from parakeet.training.reporter import report -from parakeet.training.reporter import scope +from paddlespeech.t2s.training import extension +from paddlespeech.t2s.training.reporter import DictSummary +from paddlespeech.t2s.training.reporter import report +from paddlespeech.t2s.training.reporter import scope class StandardEvaluator(extension.Extension): diff --git a/parakeet/training/extensions/snapshot.py b/paddlespeech/t2s/training/extensions/snapshot.py similarity index 95% rename from parakeet/training/extensions/snapshot.py rename to paddlespeech/t2s/training/extensions/snapshot.py index 7806dd6efa13fee6d11e5244927142b6536ba952..2e4015969ed88d7a77f1df33b4362a291c4db963 100644 --- a/parakeet/training/extensions/snapshot.py +++ b/paddlespeech/t2s/training/extensions/snapshot.py @@ -21,9 +21,9 @@ from typing import List import jsonlines -from parakeet.training import extension -from parakeet.training.trainer import Trainer -from parakeet.utils.mp_tools import rank_zero_only +from paddlespeech.t2s.training import extension +from paddlespeech.t2s.training.trainer import Trainer +from paddlespeech.t2s.utils.mp_tools import rank_zero_only def load_records(records_fp): diff --git a/parakeet/training/extensions/visualizer.py b/paddlespeech/t2s/training/extensions/visualizer.py similarity index 93% rename from parakeet/training/extensions/visualizer.py rename to paddlespeech/t2s/training/extensions/visualizer.py index bc62c97603a937578de58c2e5a5d90b65c572802..748a7c48f1b45841976a782ef1b941a83a929e8d 100644 --- a/parakeet/training/extensions/visualizer.py +++ b/paddlespeech/t2s/training/extensions/visualizer.py @@ -13,8 +13,8 @@ # limitations under the License. from visualdl import LogWriter -from parakeet.training import extension -from parakeet.training.trainer import Trainer +from paddlespeech.t2s.training import extension +from paddlespeech.t2s.training.trainer import Trainer class VisualDL(extension.Extension): diff --git a/parakeet/training/optimizer.py b/paddlespeech/t2s/training/optimizer.py similarity index 100% rename from parakeet/training/optimizer.py rename to paddlespeech/t2s/training/optimizer.py diff --git a/parakeet/training/reporter.py b/paddlespeech/t2s/training/reporter.py similarity index 100% rename from parakeet/training/reporter.py rename to paddlespeech/t2s/training/reporter.py diff --git a/parakeet/training/seeding.py b/paddlespeech/t2s/training/seeding.py similarity index 100% rename from parakeet/training/seeding.py rename to paddlespeech/t2s/training/seeding.py diff --git a/parakeet/training/trainer.py b/paddlespeech/t2s/training/trainer.py similarity index 94% rename from parakeet/training/trainer.py rename to paddlespeech/t2s/training/trainer.py index dd4862f5540b3f3a602e05f440445b7af992d7b0..9a32bca8dba548cf9a52a06d7c2e45b8bd881898 100644 --- a/parakeet/training/trainer.py +++ b/paddlespeech/t2s/training/trainer.py @@ -21,13 +21,13 @@ from typing import Union import six -from parakeet.training.extension import Extension -from parakeet.training.extension import PRIORITY_READER -from parakeet.training.reporter import scope -from parakeet.training.trigger import get_trigger -from parakeet.training.triggers.limit_trigger import LimitTrigger -from parakeet.training.updater import UpdaterBase -from parakeet.utils import profiler +from paddlespeech.t2s.training.extension import Extension +from paddlespeech.t2s.training.extension import PRIORITY_READER +from paddlespeech.t2s.training.reporter import scope +from paddlespeech.t2s.training.trigger import get_trigger +from paddlespeech.t2s.training.triggers.limit_trigger import LimitTrigger +from paddlespeech.t2s.training.updater import UpdaterBase +from paddlespeech.t2s.utils import profiler class _ExtensionEntry(object): diff --git a/parakeet/training/trigger.py b/paddlespeech/t2s/training/trigger.py similarity index 91% rename from parakeet/training/trigger.py rename to paddlespeech/t2s/training/trigger.py index aae1d54493ba613e8bac075b524348f337d6d9bd..2899562397fdce5a9e6ec88bf61931a52aa202f0 100644 --- a/parakeet/training/trigger.py +++ b/paddlespeech/t2s/training/trigger.py @@ -11,7 +11,7 @@ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. -from parakeet.training.triggers.interval_trigger import IntervalTrigger +from paddlespeech.t2s.training.triggers.interval_trigger import IntervalTrigger def never_fail_trigger(trainer): diff --git a/parakeet/training/triggers/__init__.py b/paddlespeech/t2s/training/triggers/__init__.py similarity index 100% rename from parakeet/training/triggers/__init__.py rename to paddlespeech/t2s/training/triggers/__init__.py diff --git a/parakeet/training/triggers/interval_trigger.py b/paddlespeech/t2s/training/triggers/interval_trigger.py similarity index 100% rename from parakeet/training/triggers/interval_trigger.py rename to paddlespeech/t2s/training/triggers/interval_trigger.py diff --git a/parakeet/training/triggers/limit_trigger.py b/paddlespeech/t2s/training/triggers/limit_trigger.py similarity index 100% rename from parakeet/training/triggers/limit_trigger.py rename to paddlespeech/t2s/training/triggers/limit_trigger.py diff --git a/parakeet/training/triggers/time_trigger.py b/paddlespeech/t2s/training/triggers/time_trigger.py similarity index 100% rename from parakeet/training/triggers/time_trigger.py rename to paddlespeech/t2s/training/triggers/time_trigger.py diff --git a/parakeet/training/updater.py b/paddlespeech/t2s/training/updater.py similarity index 100% rename from parakeet/training/updater.py rename to paddlespeech/t2s/training/updater.py diff --git a/parakeet/training/updaters/__init__.py b/paddlespeech/t2s/training/updaters/__init__.py similarity index 100% rename from parakeet/training/updaters/__init__.py rename to paddlespeech/t2s/training/updaters/__init__.py diff --git a/parakeet/training/updaters/standard_updater.py b/paddlespeech/t2s/training/updaters/standard_updater.py similarity index 97% rename from parakeet/training/updaters/standard_updater.py rename to paddlespeech/t2s/training/updaters/standard_updater.py index ea3ec3fad7c80ccb9fbc8540d5df4a29cac68451..2d00d196f8dc9a09b3507e93fa86bef4dd6e7a8e 100644 --- a/parakeet/training/updaters/standard_updater.py +++ b/paddlespeech/t2s/training/updaters/standard_updater.py @@ -23,9 +23,9 @@ from paddle.nn import Layer from paddle.optimizer import Optimizer from timer import timer -from parakeet.training.reporter import report -from parakeet.training.updater import UpdaterBase -from parakeet.training.updater import UpdaterState +from paddlespeech.t2s.training.reporter import report +from paddlespeech.t2s.training.updater import UpdaterBase +from paddlespeech.t2s.training.updater import UpdaterState class StandardUpdater(UpdaterBase): diff --git a/parakeet/utils/__init__.py b/paddlespeech/t2s/utils/__init__.py similarity index 100% rename from parakeet/utils/__init__.py rename to paddlespeech/t2s/utils/__init__.py diff --git a/parakeet/utils/checkpoint.py b/paddlespeech/t2s/utils/checkpoint.py similarity index 99% rename from parakeet/utils/checkpoint.py rename to paddlespeech/t2s/utils/checkpoint.py index 8df791bb2783a3b2faadd1699c7a97d06ad4c45c..1e222c50c12790f3ef5b63d24a6ebd1483122b1b 100644 --- a/parakeet/utils/checkpoint.py +++ b/paddlespeech/t2s/utils/checkpoint.py @@ -16,7 +16,7 @@ import os import paddle from paddle import distributed as dist -from parakeet.utils import mp_tools +from paddlespeech.t2s.utils import mp_tools __all__ = ["load_parameters", "save_parameters"] diff --git a/parakeet/utils/display.py b/paddlespeech/t2s/utils/display.py similarity index 100% rename from parakeet/utils/display.py rename to paddlespeech/t2s/utils/display.py diff --git a/parakeet/utils/error_rate.py b/paddlespeech/t2s/utils/error_rate.py similarity index 100% rename from parakeet/utils/error_rate.py rename to paddlespeech/t2s/utils/error_rate.py diff --git a/parakeet/utils/h5_utils.py b/paddlespeech/t2s/utils/h5_utils.py similarity index 100% rename from parakeet/utils/h5_utils.py rename to paddlespeech/t2s/utils/h5_utils.py diff --git a/parakeet/utils/internals.py b/paddlespeech/t2s/utils/internals.py similarity index 100% rename from parakeet/utils/internals.py rename to paddlespeech/t2s/utils/internals.py diff --git a/parakeet/utils/layer_tools.py b/paddlespeech/t2s/utils/layer_tools.py similarity index 100% rename from parakeet/utils/layer_tools.py rename to paddlespeech/t2s/utils/layer_tools.py diff --git a/parakeet/utils/mp_tools.py b/paddlespeech/t2s/utils/mp_tools.py similarity index 100% rename from parakeet/utils/mp_tools.py rename to paddlespeech/t2s/utils/mp_tools.py diff --git a/parakeet/utils/profile.py b/paddlespeech/t2s/utils/profile.py similarity index 100% rename from parakeet/utils/profile.py rename to paddlespeech/t2s/utils/profile.py diff --git a/parakeet/utils/profiler.py b/paddlespeech/t2s/utils/profiler.py similarity index 100% rename from parakeet/utils/profiler.py rename to paddlespeech/t2s/utils/profiler.py diff --git a/parakeet/utils/scheduler.py b/paddlespeech/t2s/utils/scheduler.py similarity index 100% rename from parakeet/utils/scheduler.py rename to paddlespeech/t2s/utils/scheduler.py diff --git a/parakeet/utils/timeline.py b/paddlespeech/t2s/utils/timeline.py similarity index 100% rename from parakeet/utils/timeline.py rename to paddlespeech/t2s/utils/timeline.py diff --git a/text_processing/.gitignore b/paddlespeech/text/.gitignore similarity index 100% rename from text_processing/.gitignore rename to paddlespeech/text/.gitignore diff --git a/text_processing/README.md b/paddlespeech/text/README.md similarity index 100% rename from text_processing/README.md rename to paddlespeech/text/README.md diff --git a/text_processing/examples/punctuation_restoration/chinese/README.md b/paddlespeech/text/examples/punctuation_restoration/chinese/README.md similarity index 100% rename from text_processing/examples/punctuation_restoration/chinese/README.md rename to paddlespeech/text/examples/punctuation_restoration/chinese/README.md diff --git a/text_processing/examples/punctuation_restoration/chinese/conf/blstm.yaml b/paddlespeech/text/examples/punctuation_restoration/chinese/conf/blstm.yaml similarity index 100% rename from text_processing/examples/punctuation_restoration/chinese/conf/blstm.yaml rename to paddlespeech/text/examples/punctuation_restoration/chinese/conf/blstm.yaml diff --git a/text_processing/examples/punctuation_restoration/chinese/conf/data_conf/chinese.yaml b/paddlespeech/text/examples/punctuation_restoration/chinese/conf/data_conf/chinese.yaml similarity index 100% rename from text_processing/examples/punctuation_restoration/chinese/conf/data_conf/chinese.yaml rename to paddlespeech/text/examples/punctuation_restoration/chinese/conf/data_conf/chinese.yaml diff --git a/text_processing/examples/punctuation_restoration/chinese/conf/train_conf/bertBLSTM_zh.yaml b/paddlespeech/text/examples/punctuation_restoration/chinese/conf/train_conf/bertBLSTM_zh.yaml similarity index 100% rename from text_processing/examples/punctuation_restoration/chinese/conf/train_conf/bertBLSTM_zh.yaml rename to paddlespeech/text/examples/punctuation_restoration/chinese/conf/train_conf/bertBLSTM_zh.yaml diff --git a/text_processing/examples/punctuation_restoration/chinese/conf/train_conf/bertLinear_zh.yaml b/paddlespeech/text/examples/punctuation_restoration/chinese/conf/train_conf/bertLinear_zh.yaml similarity index 100% rename from text_processing/examples/punctuation_restoration/chinese/conf/train_conf/bertLinear_zh.yaml rename to paddlespeech/text/examples/punctuation_restoration/chinese/conf/train_conf/bertLinear_zh.yaml diff --git a/text_processing/examples/punctuation_restoration/chinese/local/avg.sh b/paddlespeech/text/examples/punctuation_restoration/chinese/local/avg.sh similarity index 100% rename from text_processing/examples/punctuation_restoration/chinese/local/avg.sh rename to paddlespeech/text/examples/punctuation_restoration/chinese/local/avg.sh diff --git a/text_processing/examples/punctuation_restoration/chinese/local/data.sh b/paddlespeech/text/examples/punctuation_restoration/chinese/local/data.sh similarity index 100% rename from text_processing/examples/punctuation_restoration/chinese/local/data.sh rename to paddlespeech/text/examples/punctuation_restoration/chinese/local/data.sh diff --git a/text_processing/examples/punctuation_restoration/chinese/local/test.sh b/paddlespeech/text/examples/punctuation_restoration/chinese/local/test.sh similarity index 100% rename from text_processing/examples/punctuation_restoration/chinese/local/test.sh rename to paddlespeech/text/examples/punctuation_restoration/chinese/local/test.sh diff --git a/text_processing/examples/punctuation_restoration/chinese/local/train.sh b/paddlespeech/text/examples/punctuation_restoration/chinese/local/train.sh similarity index 100% rename from text_processing/examples/punctuation_restoration/chinese/local/train.sh rename to paddlespeech/text/examples/punctuation_restoration/chinese/local/train.sh diff --git a/text_processing/examples/punctuation_restoration/chinese/path.sh b/paddlespeech/text/examples/punctuation_restoration/chinese/path.sh similarity index 100% rename from text_processing/examples/punctuation_restoration/chinese/path.sh rename to paddlespeech/text/examples/punctuation_restoration/chinese/path.sh diff --git a/text_processing/examples/punctuation_restoration/chinese/run.sh b/paddlespeech/text/examples/punctuation_restoration/chinese/run.sh similarity index 100% rename from text_processing/examples/punctuation_restoration/chinese/run.sh rename to paddlespeech/text/examples/punctuation_restoration/chinese/run.sh diff --git a/text_processing/examples/punctuation_restoration/english/README.md b/paddlespeech/text/examples/punctuation_restoration/english/README.md similarity index 100% rename from text_processing/examples/punctuation_restoration/english/README.md rename to paddlespeech/text/examples/punctuation_restoration/english/README.md diff --git a/text_processing/examples/punctuation_restoration/english/conf/data_conf/english.yaml b/paddlespeech/text/examples/punctuation_restoration/english/conf/data_conf/english.yaml similarity index 100% rename from text_processing/examples/punctuation_restoration/english/conf/data_conf/english.yaml rename to paddlespeech/text/examples/punctuation_restoration/english/conf/data_conf/english.yaml diff --git a/text_processing/examples/punctuation_restoration/english/conf/train_conf/bertBLSTM_base_en.yaml b/paddlespeech/text/examples/punctuation_restoration/english/conf/train_conf/bertBLSTM_base_en.yaml similarity index 100% rename from text_processing/examples/punctuation_restoration/english/conf/train_conf/bertBLSTM_base_en.yaml rename to paddlespeech/text/examples/punctuation_restoration/english/conf/train_conf/bertBLSTM_base_en.yaml diff --git a/text_processing/examples/punctuation_restoration/english/conf/train_conf/bertLinear_en.yaml b/paddlespeech/text/examples/punctuation_restoration/english/conf/train_conf/bertLinear_en.yaml similarity index 100% rename from text_processing/examples/punctuation_restoration/english/conf/train_conf/bertLinear_en.yaml rename to paddlespeech/text/examples/punctuation_restoration/english/conf/train_conf/bertLinear_en.yaml diff --git a/text_processing/examples/punctuation_restoration/english/local/avg.sh b/paddlespeech/text/examples/punctuation_restoration/english/local/avg.sh similarity index 100% rename from text_processing/examples/punctuation_restoration/english/local/avg.sh rename to paddlespeech/text/examples/punctuation_restoration/english/local/avg.sh diff --git a/text_processing/examples/punctuation_restoration/english/local/data.sh b/paddlespeech/text/examples/punctuation_restoration/english/local/data.sh similarity index 100% rename from text_processing/examples/punctuation_restoration/english/local/data.sh rename to paddlespeech/text/examples/punctuation_restoration/english/local/data.sh diff --git a/text_processing/examples/punctuation_restoration/english/local/test.sh b/paddlespeech/text/examples/punctuation_restoration/english/local/test.sh similarity index 100% rename from text_processing/examples/punctuation_restoration/english/local/test.sh rename to paddlespeech/text/examples/punctuation_restoration/english/local/test.sh diff --git a/text_processing/examples/punctuation_restoration/english/local/train.sh b/paddlespeech/text/examples/punctuation_restoration/english/local/train.sh similarity index 100% rename from text_processing/examples/punctuation_restoration/english/local/train.sh rename to paddlespeech/text/examples/punctuation_restoration/english/local/train.sh diff --git a/text_processing/examples/punctuation_restoration/english/path.sh b/paddlespeech/text/examples/punctuation_restoration/english/path.sh similarity index 100% rename from text_processing/examples/punctuation_restoration/english/path.sh rename to paddlespeech/text/examples/punctuation_restoration/english/path.sh diff --git a/text_processing/examples/punctuation_restoration/english/run.sh b/paddlespeech/text/examples/punctuation_restoration/english/run.sh similarity index 100% rename from text_processing/examples/punctuation_restoration/english/run.sh rename to paddlespeech/text/examples/punctuation_restoration/english/run.sh diff --git a/text_processing/requirements.txt b/paddlespeech/text/requirements.txt similarity index 100% rename from text_processing/requirements.txt rename to paddlespeech/text/requirements.txt diff --git a/text_processing/speechtask/punctuation_restoration/bin/avg_model.py b/paddlespeech/text/speechtask/punctuation_restoration/bin/avg_model.py similarity index 100% rename from text_processing/speechtask/punctuation_restoration/bin/avg_model.py rename to paddlespeech/text/speechtask/punctuation_restoration/bin/avg_model.py diff --git a/text_processing/speechtask/punctuation_restoration/bin/pre_data.py b/paddlespeech/text/speechtask/punctuation_restoration/bin/pre_data.py similarity index 100% rename from text_processing/speechtask/punctuation_restoration/bin/pre_data.py rename to paddlespeech/text/speechtask/punctuation_restoration/bin/pre_data.py diff --git a/text_processing/speechtask/punctuation_restoration/bin/test.py b/paddlespeech/text/speechtask/punctuation_restoration/bin/test.py similarity index 100% rename from text_processing/speechtask/punctuation_restoration/bin/test.py rename to paddlespeech/text/speechtask/punctuation_restoration/bin/test.py diff --git a/text_processing/speechtask/punctuation_restoration/bin/train.py b/paddlespeech/text/speechtask/punctuation_restoration/bin/train.py similarity index 100% rename from text_processing/speechtask/punctuation_restoration/bin/train.py rename to paddlespeech/text/speechtask/punctuation_restoration/bin/train.py diff --git a/text_processing/speechtask/punctuation_restoration/io/__init__.py b/paddlespeech/text/speechtask/punctuation_restoration/io/__init__.py similarity index 100% rename from text_processing/speechtask/punctuation_restoration/io/__init__.py rename to paddlespeech/text/speechtask/punctuation_restoration/io/__init__.py diff --git a/text_processing/speechtask/punctuation_restoration/io/collator.py b/paddlespeech/text/speechtask/punctuation_restoration/io/collator.py similarity index 100% rename from text_processing/speechtask/punctuation_restoration/io/collator.py rename to paddlespeech/text/speechtask/punctuation_restoration/io/collator.py diff --git a/text_processing/speechtask/punctuation_restoration/io/common.py b/paddlespeech/text/speechtask/punctuation_restoration/io/common.py similarity index 100% rename from text_processing/speechtask/punctuation_restoration/io/common.py rename to paddlespeech/text/speechtask/punctuation_restoration/io/common.py diff --git a/text_processing/speechtask/punctuation_restoration/io/dataset.py b/paddlespeech/text/speechtask/punctuation_restoration/io/dataset.py similarity index 100% rename from text_processing/speechtask/punctuation_restoration/io/dataset.py rename to paddlespeech/text/speechtask/punctuation_restoration/io/dataset.py diff --git a/text_processing/speechtask/punctuation_restoration/model/BertBLSTM.py b/paddlespeech/text/speechtask/punctuation_restoration/model/BertBLSTM.py similarity index 100% rename from text_processing/speechtask/punctuation_restoration/model/BertBLSTM.py rename to paddlespeech/text/speechtask/punctuation_restoration/model/BertBLSTM.py diff --git a/text_processing/speechtask/punctuation_restoration/model/BertLinear.py b/paddlespeech/text/speechtask/punctuation_restoration/model/BertLinear.py similarity index 100% rename from text_processing/speechtask/punctuation_restoration/model/BertLinear.py rename to paddlespeech/text/speechtask/punctuation_restoration/model/BertLinear.py diff --git a/text_processing/speechtask/punctuation_restoration/model/blstm.py b/paddlespeech/text/speechtask/punctuation_restoration/model/blstm.py similarity index 100% rename from text_processing/speechtask/punctuation_restoration/model/blstm.py rename to paddlespeech/text/speechtask/punctuation_restoration/model/blstm.py diff --git a/text_processing/speechtask/punctuation_restoration/model/lstm.py b/paddlespeech/text/speechtask/punctuation_restoration/model/lstm.py similarity index 100% rename from text_processing/speechtask/punctuation_restoration/model/lstm.py rename to paddlespeech/text/speechtask/punctuation_restoration/model/lstm.py diff --git a/text_processing/speechtask/punctuation_restoration/modules/__init__.py b/paddlespeech/text/speechtask/punctuation_restoration/modules/__init__.py similarity index 100% rename from text_processing/speechtask/punctuation_restoration/modules/__init__.py rename to paddlespeech/text/speechtask/punctuation_restoration/modules/__init__.py diff --git a/text_processing/speechtask/punctuation_restoration/modules/activation.py b/paddlespeech/text/speechtask/punctuation_restoration/modules/activation.py similarity index 100% rename from text_processing/speechtask/punctuation_restoration/modules/activation.py rename to paddlespeech/text/speechtask/punctuation_restoration/modules/activation.py diff --git a/text_processing/speechtask/punctuation_restoration/modules/attention.py b/paddlespeech/text/speechtask/punctuation_restoration/modules/attention.py similarity index 100% rename from text_processing/speechtask/punctuation_restoration/modules/attention.py rename to paddlespeech/text/speechtask/punctuation_restoration/modules/attention.py diff --git a/text_processing/speechtask/punctuation_restoration/modules/crf.py b/paddlespeech/text/speechtask/punctuation_restoration/modules/crf.py similarity index 100% rename from text_processing/speechtask/punctuation_restoration/modules/crf.py rename to paddlespeech/text/speechtask/punctuation_restoration/modules/crf.py diff --git a/text_processing/speechtask/punctuation_restoration/training/__init__.py b/paddlespeech/text/speechtask/punctuation_restoration/training/__init__.py similarity index 100% rename from text_processing/speechtask/punctuation_restoration/training/__init__.py rename to paddlespeech/text/speechtask/punctuation_restoration/training/__init__.py diff --git a/text_processing/speechtask/punctuation_restoration/training/loss.py b/paddlespeech/text/speechtask/punctuation_restoration/training/loss.py similarity index 100% rename from text_processing/speechtask/punctuation_restoration/training/loss.py rename to paddlespeech/text/speechtask/punctuation_restoration/training/loss.py diff --git a/text_processing/speechtask/punctuation_restoration/training/trainer.py b/paddlespeech/text/speechtask/punctuation_restoration/training/trainer.py similarity index 100% rename from text_processing/speechtask/punctuation_restoration/training/trainer.py rename to paddlespeech/text/speechtask/punctuation_restoration/training/trainer.py diff --git a/text_processing/speechtask/punctuation_restoration/utils/__init__.py b/paddlespeech/text/speechtask/punctuation_restoration/utils/__init__.py similarity index 100% rename from text_processing/speechtask/punctuation_restoration/utils/__init__.py rename to paddlespeech/text/speechtask/punctuation_restoration/utils/__init__.py diff --git a/text_processing/speechtask/punctuation_restoration/utils/checkpoint.py b/paddlespeech/text/speechtask/punctuation_restoration/utils/checkpoint.py similarity index 100% rename from text_processing/speechtask/punctuation_restoration/utils/checkpoint.py rename to paddlespeech/text/speechtask/punctuation_restoration/utils/checkpoint.py diff --git a/text_processing/speechtask/punctuation_restoration/utils/default_parser.py b/paddlespeech/text/speechtask/punctuation_restoration/utils/default_parser.py similarity index 93% rename from text_processing/speechtask/punctuation_restoration/utils/default_parser.py rename to paddlespeech/text/speechtask/punctuation_restoration/utils/default_parser.py index b83d989d62645d7f21df3f5b5c18006666a69df1..405b29a2b5f4cf925e59951cf385f54e06239025 100644 --- a/text_processing/speechtask/punctuation_restoration/utils/default_parser.py +++ b/paddlespeech/text/speechtask/punctuation_restoration/utils/default_parser.py @@ -15,10 +15,10 @@ import argparse def default_argument_parser(): - r"""A simple yet genral argument parser for experiments with parakeet. + r"""A simple yet genral argument parser for experiments with t2s. - This is used in examples with parakeet. And it is intended to be used by - other experiments with parakeet. It requires a minimal set of command line + This is used in examples with t2s. And it is intended to be used by + other experiments with t2s. It requires a minimal set of command line arguments to start a training script. The ``--config`` and ``--opts`` are used for overwrite the deault @@ -35,7 +35,7 @@ def default_argument_parser(): See Also -------- - parakeet.training.experiment + paddlespeech.t2s.training.experiment Returns ------- argparse.ArgumentParser diff --git a/text_processing/speechtask/punctuation_restoration/utils/layer_tools.py b/paddlespeech/text/speechtask/punctuation_restoration/utils/layer_tools.py similarity index 100% rename from text_processing/speechtask/punctuation_restoration/utils/layer_tools.py rename to paddlespeech/text/speechtask/punctuation_restoration/utils/layer_tools.py diff --git a/text_processing/speechtask/punctuation_restoration/utils/mp_tools.py b/paddlespeech/text/speechtask/punctuation_restoration/utils/mp_tools.py similarity index 100% rename from text_processing/speechtask/punctuation_restoration/utils/mp_tools.py rename to paddlespeech/text/speechtask/punctuation_restoration/utils/mp_tools.py diff --git a/text_processing/speechtask/punctuation_restoration/utils/punct_pre.py b/paddlespeech/text/speechtask/punctuation_restoration/utils/punct_pre.py similarity index 100% rename from text_processing/speechtask/punctuation_restoration/utils/punct_pre.py rename to paddlespeech/text/speechtask/punctuation_restoration/utils/punct_pre.py diff --git a/text_processing/speechtask/punctuation_restoration/utils/utility.py b/paddlespeech/text/speechtask/punctuation_restoration/utils/utility.py similarity index 100% rename from text_processing/speechtask/punctuation_restoration/utils/utility.py rename to paddlespeech/text/speechtask/punctuation_restoration/utils/utility.py diff --git a/parakeet/frontend/normalizer/__init__.py b/parakeet/frontend/normalizer/__init__.py deleted file mode 100644 index d1f2bfc537106f0a50e20864e5875be35fbd964c..0000000000000000000000000000000000000000 --- a/parakeet/frontend/normalizer/__init__.py +++ /dev/null @@ -1,15 +0,0 @@ -# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved. -# -# Licensed under the Apache License, Version 2.0 (the "License"); -# you may not use this file except in compliance with the License. -# You may obtain a copy of the License at -# -# http://www.apache.org/licenses/LICENSE-2.0 -# -# Unless required by applicable law or agreed to in writing, software -# distributed under the License is distributed on an "AS IS" BASIS, -# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. -# See the License for the specific language governing permissions and -# limitations under the License. -from parakeet.frontend.normalizer.normalizer import * -from parakeet.frontend.normalizer.numbers import * diff --git a/parakeet/frontend/zh_normalization/__init__.py b/parakeet/frontend/zh_normalization/__init__.py deleted file mode 100644 index 1e49408043e59814353c39b952ca422926f37c92..0000000000000000000000000000000000000000 --- a/parakeet/frontend/zh_normalization/__init__.py +++ /dev/null @@ -1,14 +0,0 @@ -# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved. -# -# Licensed under the Apache License, Version 2.0 (the "License"); -# you may not use this file except in compliance with the License. -# You may obtain a copy of the License at -# -# http://www.apache.org/licenses/LICENSE-2.0 -# -# Unless required by applicable law or agreed to in writing, software -# distributed under the License is distributed on an "AS IS" BASIS, -# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. -# See the License for the specific language governing permissions and -# limitations under the License. -from parakeet.frontend.zh_normalization.text_normlization import * diff --git a/setup.py b/setup.py index a2e4c031cf73978e3efecac97b7eb2b3cba0b8e2..95044e742fa5ecd0ffbae30db8b21c3c5a9f380c 100644 --- a/setup.py +++ b/setup.py @@ -80,7 +80,7 @@ def _post_install(install_lib_dir): print("autolog install.") # ctcdecoder - ctcdecoder_dir = HERE / 'deepspeech/decoders/ctcdecoder/swig' + ctcdecoder_dir = HERE / 'paddlespeech/s2t/decoders/ctcdecoder/swig' with pushd(ctcdecoder_dir): check_call("bash -e setup.sh") print("ctcdecoder install.") diff --git a/setup.sh b/setup.sh index aefdab9862442f29c03a6cb63d7234c332bf91d3..0f04226daad3078d7036298c25f2e471df850da3 100644 --- a/setup.sh +++ b/setup.sh @@ -69,7 +69,7 @@ fi # install decoders python3 -c "import pkg_resources; pkg_resources.require(\"swig_decoders==1.1\")" if [ $? != 0 ]; then - cd deepspeech/decoders/ctcdecoder/swig > /dev/null + cd paddlespeech/s2t/decoders/ctcdecoder/swig > /dev/null bash setup.sh cd - > /dev/null fi diff --git a/tests/benchmark/pwgan/README.md b/tests/benchmark/pwgan/README.md index 369f4b74f6dc54bb6386cbd4a918f37f5fc0ee92..bfc2bc077d43a03b1739086288bb330f173713a7 100644 --- a/tests/benchmark/pwgan/README.md +++ b/tests/benchmark/pwgan/README.md @@ -5,7 +5,7 @@ 即可运行. 执行逻辑： 1. cd 到 ../../../ (也就是 Deepspeech 目录) -2. 安装 parakeet 所需依赖 +2. 安装 paddlespeech/t2s 所需依赖 3. 从 bos 下载数据集并解压缩 4. 预处理数据集为训练 pwg 所需格式，保存到 Deepspeech/dump 文件夹底下 5. 按照不同的参数执行 run_benchmark.sh 脚本 diff --git a/tests/benchmark/pwgan/run_all.sh b/tests/benchmark/pwgan/run_all.sh index e4bb17f8cd1bdf8a571d8aec5af0d9d6e61fdaf8..9d722aaf19800e472dd2df6ce782013e4dad15cb 100755 --- a/tests/benchmark/pwgan/run_all.sh +++ b/tests/benchmark/pwgan/run_all.sh @@ -25,11 +25,11 @@ fi # 数据预处理 if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then - python3 parakeet/exps/gan_vocoder/preprocess.py --rootdir=BZNSYP/ --dumpdir=dump --num-cpu=20 --cut-sil=True --dur-file=durations.txt --config=examples/csmsc/voc1/conf/default.yaml + python3 paddlespeech/t2s/exps/gan_vocoder/preprocess.py --rootdir=BZNSYP/ --dumpdir=dump --num-cpu=20 --cut-sil=True --dur-file=durations.txt --config=examples/csmsc/voc1/conf/default.yaml python3 utils/compute_statistics.py --metadata=dump/train/raw/metadata.jsonl --field-name="feats" - python3 parakeet/exps/gan_vocoder/normalize.py --metadata=dump/train/raw/metadata.jsonl --dumpdir=dump/train/norm --stats=dump/train/feats_stats.npy - python3 parakeet/exps/gan_vocoder/normalize.py --metadata=dump/dev/raw/metadata.jsonl --dumpdir=dump/dev/norm --stats=dump/train/feats_stats.npy - python3 parakeet/exps/gan_vocoder/normalize.py --metadata=dump/test/raw/metadata.jsonl --dumpdir=dump/test/norm --stats=dump/train/feats_stats.npy + python3 paddlespeech/t2s/exps/gan_vocoder/normalize.py --metadata=dump/train/raw/metadata.jsonl --dumpdir=dump/train/norm --stats=dump/train/feats_stats.npy + python3 paddlespeech/t2s/exps/gan_vocoder/normalize.py --metadata=dump/dev/raw/metadata.jsonl --dumpdir=dump/dev/norm --stats=dump/train/feats_stats.npy + python3 paddlespeech/t2s/exps/gan_vocoder/normalize.py --metadata=dump/test/raw/metadata.jsonl --dumpdir=dump/test/norm --stats=dump/train/feats_stats.npy fi # 3 批量运行（如不方便批量，1，2需放到单个模型中） if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then diff --git a/tests/benchmark/pwgan/run_benchmark.sh b/tests/benchmark/pwgan/run_benchmark.sh index e961e442b49c4e86b493c508a40b25fe91a14d69..be5733da177b526c21fbb8c84bab885a3d0c797b 100755 --- a/tests/benchmark/pwgan/run_benchmark.sh +++ b/tests/benchmark/pwgan/run_benchmark.sh @@ -29,8 +29,8 @@ function _train(){ --run-benchmark=true" case ${run_mode} in - sp) train_cmd="python3 parakeet/exps/gan_vocoder/parallelwave_gan/train.py --nprocs=1 ${train_cmd}" ;; - mp) train_cmd="python3 parakeet/exps/gan_vocoder/parallelwave_gan/train.py --nprocs=8 ${train_cmd}" + sp) train_cmd="python3 paddlespeech/t2s/exps/gan_vocoder/parallelwave_gan/train.py --nprocs=1 ${train_cmd}" ;; + mp) train_cmd="python3 paddlespeech/t2s/exps/gan_vocoder/parallelwave_gan/train.py --nprocs=8 ${train_cmd}" log_parse_file="mylog/workerlog.0" ;; *) echo "choose run_mode(sp or mp)"; exit 1; esac diff --git a/tests/chains/ds2/ds2_params_lite_train_infer.txt b/tests/chains/ds2/ds2_params_lite_train_infer.txt index 70d54f8bc0b73a8aae46a40721d326acb9d421a8..c1cbfbb92fc325b598f056c26561a29f5b2c341c 100644 --- a/tests/chains/ds2/ds2_params_lite_train_infer.txt +++ b/tests/chains/ds2/ds2_params_lite_train_infer.txt @@ -13,7 +13,7 @@ null:null null:null ## trainer:norm_train -norm_train: ../../../deepspeech/exps/deepspeech2/bin/train.py --config conf/deepspeech2.yaml --model_type offline --profiler-options "" --output exp/deepspeech_tiny --seed 0 +norm_train: ../../../paddlespeech/s2t/exps/deepspeech2/bin/train.py --config conf/deepspeech2.yaml --model_type offline --profiler-options "" --output exp/deepspeech_tiny --seed 0 pact_train:null fpgm_train:null distill_train:null @@ -21,13 +21,13 @@ null:null null:null ## ===========================eval_params=========================== -eval: ../../../deepspeech/exps/deepspeech2/bin/test.py --nproc 1 --config conf/deepspeech2.yaml --checkpoint_path exp/deepspeech_tiny/checkpoints/9 --result_file tests/9.rsl --model_type offline +eval: ../../../paddlespeech/s2t/exps/deepspeech2/bin/test.py --nproc 1 --config conf/deepspeech2.yaml --checkpoint_path exp/deepspeech_tiny/checkpoints/9 --result_file tests/9.rsl --model_type offline null:null ## ===========================infer_params=========================== null:null null:null -norm_export: ../../../deepspeech/exps/deepspeech2/bin/export.py --nproc 1 --config conf/deepspeech2.yaml --model_type offline --checkpoint_path exp/deepspeech_tiny/checkpoints/9 --export_path exp/deepspeech_tiny/checkpoints/9.jit +norm_export: ../../../paddlespeech/s2t/exps/deepspeech2/bin/export.py --nproc 1 --config conf/deepspeech2.yaml --model_type offline --checkpoint_path exp/deepspeech_tiny/checkpoints/9 --export_path exp/deepspeech_tiny/checkpoints/9.jit quant_export:null fpgm_export:null distill_export:null diff --git a/tests/chains/ds2/ds2_params_whole_train_infer.txt b/tests/chains/ds2/ds2_params_whole_train_infer.txt index 90ce7d89437d708c3e1350e09f026262204d090a..bfcb745f6c22027ded7fc7334567ae007eb463d4 100644 --- a/tests/chains/ds2/ds2_params_whole_train_infer.txt +++ b/tests/chains/ds2/ds2_params_whole_train_infer.txt @@ -13,7 +13,7 @@ null:null null:null ## trainer:norm_train -norm_train: ../../../deepspeech/exps/deepspeech2/bin/train.py --config conf/deepspeech2.yaml --model_type offline --profiler-options "" --output exp/deepspeech_whole --seed 0 +norm_train: ../../../paddlespeech/s2t/exps/deepspeech2/bin/train.py --config conf/deepspeech2.yaml --model_type offline --profiler-options "" --output exp/deepspeech_whole --seed 0 pact_train:null fpgm_train:null distill_train:null @@ -21,13 +21,13 @@ null:null null:null ## ===========================eval_params=========================== -eval: ../../../deepspeech/exps/deepspeech2/bin/test.py --nproc 1 --config conf/deepspeech2.yaml --result_file tests/49.rsl --checkpoint_path exp/deepspeech_whole/checkpoints/49 --model_type offline +eval: ../../../paddlespeech/s2t/exps/deepspeech2/bin/test.py --nproc 1 --config conf/deepspeech2.yaml --result_file tests/49.rsl --checkpoint_path exp/deepspeech_whole/checkpoints/49 --model_type offline null:null ## ===========================infer_params=========================== null:null null:null -norm_export: ../../../deepspeech/exps/deepspeech2/bin/export.py --nproc 1 --config conf/deepspeech2.yaml --model_type offline --checkpoint_path exp/deepspeech_whole/checkpoints/49 --export_path exp/deepspeech_whole/checkpoints/49.jit +norm_export: ../../../paddlespeech/s2t/exps/deepspeech2/bin/export.py --nproc 1 --config conf/deepspeech2.yaml --model_type offline --checkpoint_path exp/deepspeech_whole/checkpoints/49 --export_path exp/deepspeech_whole/checkpoints/49.jit quant_export:null fpgm_export:null distill_export:null diff --git a/tests/chains/speedyspeech/speedyspeech_params_lite_multi_gpu.txt b/tests/chains/speedyspeech/speedyspeech_params_lite_multi_gpu.txt index ad3420521d7c5e8163f634d3a36c5b2dfdb2f5fa..0f64da271424942f93b669b97aecfb33ba8632e3 100644 --- a/tests/chains/speedyspeech/speedyspeech_params_lite_multi_gpu.txt +++ b/tests/chains/speedyspeech/speedyspeech_params_lite_multi_gpu.txt @@ -13,7 +13,7 @@ null:null null:null ## trainer:norm_train -norm_train:../../../parakeet/exps/speedyspeech/train.py --train-metadata=train_data/mini_BZNSYP/train/norm/metadata.jsonl --dev-metadata=train_data/mini_BZNSYP/dev/norm/metadata.jsonl --config=../../../examples/csmsc/tts2/conf/default.yaml --batch_size=32 --max_epoch=20 --num_snapshots=10 --output-dir=exp/default --phones-dict=train_data/mini_BZNSYP/phone_id_map.txt --tones-dict=train_data/mini_BZNSYP/tone_id_map.txt --use-relative-path=True +norm_train:../../../paddlespeech/t2s/exps/speedyspeech/train.py --train-metadata=train_data/mini_BZNSYP/train/norm/metadata.jsonl --dev-metadata=train_data/mini_BZNSYP/dev/norm/metadata.jsonl --config=../../../examples/csmsc/tts2/conf/default.yaml --batch_size=32 --max_epoch=20 --num_snapshots=10 --output-dir=exp/default --phones-dict=train_data/mini_BZNSYP/phone_id_map.txt --tones-dict=train_data/mini_BZNSYP/tone_id_map.txt --use-relative-path=True null:null null:null null:null @@ -21,7 +21,7 @@ null:null null:null ## ===========================eval_params=========================== -eval:../../../parakeet/exps/speedyspeech/synthesize_e2e.py --speedyspeech-config=../../../examples/csmsc/tts2/conf/default.yaml --speedyspeech-checkpoint=exp/default/checkpoints/snapshot_iter_20.pdz --speedyspeech-stat=train_data/mini_BZNSYP/train/feats_stats.npy --pwg-config=pretrain_models/pwg_baker_ckpt_0.4/pwg_default.yaml --pwg-checkpoint=pretrain_models/pwg_baker_ckpt_0.4/pwg_snapshot_iter_400000.pdz --pwg-stat=pretrain_models/pwg_baker_ckpt_0.4/pwg_stats.npy --text=../../../parakeet/exps/sentences.txt --output-dir=e2e --inference-dir=inference --device="gpu" --phones-dict=train_data/mini_BZNSYP/phone_id_map.txt --tones-dict=train_data/mini_BZNSYP/tone_id_map.txt +eval:../../../paddlespeech/t2s/exps/speedyspeech/synthesize_e2e.py --speedyspeech-config=../../../examples/csmsc/tts2/conf/default.yaml --speedyspeech-checkpoint=exp/default/checkpoints/snapshot_iter_20.pdz --speedyspeech-stat=train_data/mini_BZNSYP/train/feats_stats.npy --pwg-config=pretrain_models/pwg_baker_ckpt_0.4/pwg_default.yaml --pwg-checkpoint=pretrain_models/pwg_baker_ckpt_0.4/pwg_snapshot_iter_400000.pdz --pwg-stat=pretrain_models/pwg_baker_ckpt_0.4/pwg_stats.npy --text=../../../paddlespeech/t2s/exps/sentences.txt --output-dir=e2e --inference-dir=inference --device="gpu" --phones-dict=train_data/mini_BZNSYP/phone_id_map.txt --tones-dict=train_data/mini_BZNSYP/tone_id_map.txt null:null ## ===========================infer_params=========================== @@ -37,7 +37,7 @@ null:null null:null null:null null:null -inference:../../../parakeet/exps/speedyspeech/inference.py --inference-dir=pretrain_models/speedyspeech_pwg_inference_0.5 --text=../../../parakeet/exps/sentences.txt --output-dir=inference_out --enable-auto-log --phones-dict=pretrain_models/speedyspeech_pwg_inference_0.5/phone_id_map.txt --tones-dict=pretrain_models/speedyspeech_pwg_inference_0.5/tone_id_map.txt +inference:../../../paddlespeech/t2s/exps/speedyspeech/inference.py --inference-dir=pretrain_models/speedyspeech_pwg_inference_0.5 --text=../../../paddlespeech/t2s/exps/sentences.txt --output-dir=inference_out --enable-auto-log --phones-dict=pretrain_models/speedyspeech_pwg_inference_0.5/phone_id_map.txt --tones-dict=pretrain_models/speedyspeech_pwg_inference_0.5/tone_id_map.txt null:null null:null null:null diff --git a/tests/chains/speedyspeech/speedyspeech_params_lite_single_gpu.txt b/tests/chains/speedyspeech/speedyspeech_params_lite_single_gpu.txt index eaad714debd4c47588711f8b4eaabb053e1772b1..beda4c04e06d5d055e407e3f6c67cbc35dbf5806 100644 --- a/tests/chains/speedyspeech/speedyspeech_params_lite_single_gpu.txt +++ b/tests/chains/speedyspeech/speedyspeech_params_lite_single_gpu.txt @@ -13,7 +13,7 @@ null:null null:null ## trainer:norm_train -norm_train:../../../parakeet/exps/speedyspeech/train.py --train-metadata=train_data/mini_BZNSYP/train/norm/metadata.jsonl --dev-metadata=train_data/mini_BZNSYP/dev/norm/metadata.jsonl --config=../../../examples/csmsc/tts2/conf/default.yaml --batch_size=32 --max_epoch=10 --num_snapshots=10 --output-dir=exp/default --phones-dict=train_data/mini_BZNSYP/phone_id_map.txt --tones-dict=train_data/mini_BZNSYP/tone_id_map.txt --use-relative-path=True +norm_train:../../../paddlespeech/t2s/exps/speedyspeech/train.py --train-metadata=train_data/mini_BZNSYP/train/norm/metadata.jsonl --dev-metadata=train_data/mini_BZNSYP/dev/norm/metadata.jsonl --config=../../../examples/csmsc/tts2/conf/default.yaml --batch_size=32 --max_epoch=10 --num_snapshots=10 --output-dir=exp/default --phones-dict=train_data/mini_BZNSYP/phone_id_map.txt --tones-dict=train_data/mini_BZNSYP/tone_id_map.txt --use-relative-path=True null:null null:null null:null @@ -21,7 +21,7 @@ null:null null:null ## ===========================eval_params=========================== -eval:../../../parakeet/exps/speedyspeech/synthesize_e2e.py --speedyspeech-config=../../../examples/csmsc/tts2/conf/default.yaml --speedyspeech-checkpoint=exp/default/checkpoints/snapshot_iter_30.pdz --speedyspeech-stat=train_data/mini_BZNSYP/train/feats_stats.npy --pwg-config=pretrain_models/pwg_baker_ckpt_0.4/pwg_default.yaml --pwg-checkpoint=pretrain_models/pwg_baker_ckpt_0.4/pwg_snapshot_iter_400000.pdz --pwg-stat=pretrain_models/pwg_baker_ckpt_0.4/pwg_stats.npy --text=../../../parakeet/exps/sentences.txt --output-dir=e2e --inference-dir=inference --device="gpu" --phones-dict=train_data/mini_BZNSYP/phone_id_map.txt --tones-dict=train_data/mini_BZNSYP/tone_id_map.txt +eval:../../../paddlespeech/t2s/exps/speedyspeech/synthesize_e2e.py --speedyspeech-config=../../../examples/csmsc/tts2/conf/default.yaml --speedyspeech-checkpoint=exp/default/checkpoints/snapshot_iter_30.pdz --speedyspeech-stat=train_data/mini_BZNSYP/train/feats_stats.npy --pwg-config=pretrain_models/pwg_baker_ckpt_0.4/pwg_default.yaml --pwg-checkpoint=pretrain_models/pwg_baker_ckpt_0.4/pwg_snapshot_iter_400000.pdz --pwg-stat=pretrain_models/pwg_baker_ckpt_0.4/pwg_stats.npy --text=../../../paddlespeech/t2s/exps/sentences.txt --output-dir=e2e --inference-dir=inference --device="gpu" --phones-dict=train_data/mini_BZNSYP/phone_id_map.txt --tones-dict=train_data/mini_BZNSYP/tone_id_map.txt null:null ## ===========================infer_params=========================== @@ -37,7 +37,7 @@ null:null null:null null:null null:null -inference:../../../parakeet/exps/speedyspeech/inference.py --inference-dir=pretrain_models/speedyspeech_pwg_inference_0.5 --text=../../../parakeet/exps/sentences.txt --output-dir=inference_out --enable-auto-log --phones-dict=pretrain_models/speedyspeech_pwg_inference_0.5/phone_id_map.txt --tones-dict=pretrain_models/speedyspeech_pwg_inference_0.5/tone_id_map.txt +inference:../../../paddlespeech/t2s/exps/speedyspeech/inference.py --inference-dir=pretrain_models/speedyspeech_pwg_inference_0.5 --text=../../../paddlespeech/t2s/exps/sentences.txt --output-dir=inference_out --enable-auto-log --phones-dict=pretrain_models/speedyspeech_pwg_inference_0.5/phone_id_map.txt --tones-dict=pretrain_models/speedyspeech_pwg_inference_0.5/tone_id_map.txt --use_gpu:True null:null null:null diff --git a/tests/chains/speedyspeech/speedyspeech_params_whole_multi_gpu.txt b/tests/chains/speedyspeech/speedyspeech_params_whole_multi_gpu.txt index 236805fc5fcd677f50144a13848ca840f61cc6de..ecdbf76dc0fce5463e69a3dae86fa030df866f9c 100644 --- a/tests/chains/speedyspeech/speedyspeech_params_whole_multi_gpu.txt +++ b/tests/chains/speedyspeech/speedyspeech_params_whole_multi_gpu.txt @@ -13,7 +13,7 @@ null:null null:null ## trainer:norm_train -norm_train:../../../parakeet/exps/speedyspeech/train.py --train-metadata=train_data/processed_BZNSYP/train/norm/metadata.jsonl --dev-metadata=train_data/processed_BZNSYP/dev/norm/metadata.jsonl --config=../../../examples/csmsc/tts2/conf/default.yaml --output-dir=exp/whole --phones-dict=train_data/processed_BZNSYP/phone_id_map.txt --tones-dict=train_data/processed_BZNSYP/tone_id_map.txt --use-relative-path=True +norm_train:../../../paddlespeech/t2s/exps/speedyspeech/train.py --train-metadata=train_data/processed_BZNSYP/train/norm/metadata.jsonl --dev-metadata=train_data/processed_BZNSYP/dev/norm/metadata.jsonl --config=../../../examples/csmsc/tts2/conf/default.yaml --output-dir=exp/whole --phones-dict=train_data/processed_BZNSYP/phone_id_map.txt --tones-dict=train_data/processed_BZNSYP/tone_id_map.txt --use-relative-path=True null:null null:null null:null @@ -21,7 +21,7 @@ null:null null:null ## ===========================eval_params=========================== -eval:../../../parakeet/exps/speedyspeech/synthesize_e2e.py --speedyspeech-config=pretrain_models/speedyspeech_nosil_baker_ckpt_0.5/default.yaml --speedyspeech-checkpoint=pretrain_models/speedyspeech_nosil_baker_ckpt_0.5/snapshot_iter_11400.pdz --speedyspeech-stat=pretrain_models/speedyspeech_nosil_baker_ckpt_0.5/feats_stats.npy --pwg-config=pretrain_models/pwg_baker_ckpt_0.4/pwg_default.yaml --pwg-checkpoint=pretrain_models/pwg_baker_ckpt_0.4/pwg_snapshot_iter_400000.pdz --pwg-stat=pretrain_models/pwg_baker_ckpt_0.4/pwg_stats.npy --text=../../../parakeet/exps/sentences.txt --output-dir=e2e --inference-dir=inference --device="gpu" --phones-dict=pretrain_models/speedyspeech_nosil_baker_ckpt_0.5/phone_id_map.txt --tones-dict=pretrain_models/speedyspeech_nosil_baker_ckpt_0.5/tone_id_map.txt +eval:../../../paddlespeech/t2s/exps/speedyspeech/synthesize_e2e.py --speedyspeech-config=pretrain_models/speedyspeech_nosil_baker_ckpt_0.5/default.yaml --speedyspeech-checkpoint=pretrain_models/speedyspeech_nosil_baker_ckpt_0.5/snapshot_iter_11400.pdz --speedyspeech-stat=pretrain_models/speedyspeech_nosil_baker_ckpt_0.5/feats_stats.npy --pwg-config=pretrain_models/pwg_baker_ckpt_0.4/pwg_default.yaml --pwg-checkpoint=pretrain_models/pwg_baker_ckpt_0.4/pwg_snapshot_iter_400000.pdz --pwg-stat=pretrain_models/pwg_baker_ckpt_0.4/pwg_stats.npy --text=../../../paddlespeech/t2s/exps/sentences.txt --output-dir=e2e --inference-dir=inference --device="gpu" --phones-dict=pretrain_models/speedyspeech_nosil_baker_ckpt_0.5/phone_id_map.txt --tones-dict=pretrain_models/speedyspeech_nosil_baker_ckpt_0.5/tone_id_map.txt null:null ## ===========================infer_params=========================== @@ -37,7 +37,7 @@ null:null null:null null:null null:null -inference:../../../parakeet/exps/speedyspeech/inference.py --inference-dir=pretrain_models/speedyspeech_pwg_inference_0.5 --text=../../../parakeet/exps/sentences.txt --output-dir=inference_out --enable-auto-log --phones-dict=pretrain_models/speedyspeech_pwg_inference_0.5/phone_id_map.txt --tones-dict=pretrain_models/speedyspeech_pwg_inference_0.5/tone_id_map.txt +inference:../../../paddlespeech/t2s/exps/speedyspeech/inference.py --inference-dir=pretrain_models/speedyspeech_pwg_inference_0.5 --text=../../../paddlespeech/t2s/exps/sentences.txt --output-dir=inference_out --enable-auto-log --phones-dict=pretrain_models/speedyspeech_pwg_inference_0.5/phone_id_map.txt --tones-dict=pretrain_models/speedyspeech_pwg_inference_0.5/tone_id_map.txt null:null null:null null:null diff --git a/tests/chains/speedyspeech/speedyspeech_params_whole_single_gpu.txt b/tests/chains/speedyspeech/speedyspeech_params_whole_single_gpu.txt index 9caeb18e7cdc86d766e3d0489d5407b424c127f7..523b5c6e303db86c4f1f3c3597fbcf75a54c61c2 100644 --- a/tests/chains/speedyspeech/speedyspeech_params_whole_single_gpu.txt +++ b/tests/chains/speedyspeech/speedyspeech_params_whole_single_gpu.txt @@ -13,7 +13,7 @@ null:null null:null ## trainer:norm_train -norm_train:../../../parakeet/exps/speedyspeech/train.py --train-metadata=train_data/processed_BZNSYP/train/norm/metadata.jsonl --dev-metadata=train_data/processed_BZNSYP/dev/norm/metadata.jsonl --config=../../../examples/csmsc/tts2/conf/default.yaml --output-dir=exp/whole --phones-dict=train_data/processed_BZNSYP/phone_id_map.txt --tones-dict=train_data/processed_BZNSYP/tone_id_map.txt --use-relative-path=True +norm_train:../../../paddlespeech/t2s/exps/speedyspeech/train.py --train-metadata=train_data/processed_BZNSYP/train/norm/metadata.jsonl --dev-metadata=train_data/processed_BZNSYP/dev/norm/metadata.jsonl --config=../../../examples/csmsc/tts2/conf/default.yaml --output-dir=exp/whole --phones-dict=train_data/processed_BZNSYP/phone_id_map.txt --tones-dict=train_data/processed_BZNSYP/tone_id_map.txt --use-relative-path=True null:null null:null null:null @@ -21,7 +21,7 @@ null:null null:null ## ===========================eval_params=========================== -eval:../../../parakeet/exps/speedyspeech/synthesize_e2e.py --speedyspeech-config=pretrain_models/speedyspeech_nosil_baker_ckpt_0.5/default.yaml --speedyspeech-checkpoint=pretrain_models/speedyspeech_nosil_baker_ckpt_0.5/snapshot_iter_11400.pdz --speedyspeech-stat=pretrain_models/speedyspeech_nosil_baker_ckpt_0.5/feats_stats.npy --pwg-config=pretrain_models/pwg_baker_ckpt_0.4/pwg_default.yaml --pwg-checkpoint=pretrain_models/pwg_baker_ckpt_0.4/pwg_snapshot_iter_400000.pdz --pwg-stat=pretrain_models/pwg_baker_ckpt_0.4/pwg_stats.npy --text=../../../parakeet/exps/sentences.txt --output-dir=e2e --inference-dir=inference --device="gpu" --phones-dict=pretrain_models/speedyspeech_nosil_baker_ckpt_0.5/phone_id_map.txt --tones-dict=pretrain_models/speedyspeech_nosil_baker_ckpt_0.5/tone_id_map.txt +eval:../../../paddlespeech/t2s/exps/speedyspeech/synthesize_e2e.py --speedyspeech-config=pretrain_models/speedyspeech_nosil_baker_ckpt_0.5/default.yaml --speedyspeech-checkpoint=pretrain_models/speedyspeech_nosil_baker_ckpt_0.5/snapshot_iter_11400.pdz --speedyspeech-stat=pretrain_models/speedyspeech_nosil_baker_ckpt_0.5/feats_stats.npy --pwg-config=pretrain_models/pwg_baker_ckpt_0.4/pwg_default.yaml --pwg-checkpoint=pretrain_models/pwg_baker_ckpt_0.4/pwg_snapshot_iter_400000.pdz --pwg-stat=pretrain_models/pwg_baker_ckpt_0.4/pwg_stats.npy --text=../../../paddlespeech/t2s/exps/sentences.txt --output-dir=e2e --inference-dir=inference --device="gpu" --phones-dict=pretrain_models/speedyspeech_nosil_baker_ckpt_0.5/phone_id_map.txt --tones-dict=pretrain_models/speedyspeech_nosil_baker_ckpt_0.5/tone_id_map.txt null:null ## ===========================infer_params=========================== @@ -37,7 +37,7 @@ null:null null:null null:null null:null -inference:../../../parakeet/exps/speedyspeech/inference.py --inference-dir=pretrain_models/speedyspeech_pwg_inference_0.5 --text=../../../parakeet/exps/sentences.txt --output-dir=inference_out --enable-auto-log --phones-dict=pretrain_models/speedyspeech_pwg_inference_0.5/phone_id_map.txt --tones-dict=pretrain_models/speedyspeech_pwg_inference_0.5/tone_id_map.txt +inference:../../../paddlespeech/t2s/exps/speedyspeech/inference.py --inference-dir=pretrain_models/speedyspeech_pwg_inference_0.5 --text=../../../paddlespeech/t2s/exps/sentences.txt --output-dir=inference_out --enable-auto-log --phones-dict=pretrain_models/speedyspeech_pwg_inference_0.5/phone_id_map.txt --tones-dict=pretrain_models/speedyspeech_pwg_inference_0.5/tone_id_map.txt null:null null:null null:null diff --git a/tests/unit/asr/deepspeech2_model_test.py b/tests/unit/asr/deepspeech2_model_test.py index 00df8195b1063effad12857c0d8e919cb39cbee0..5835445d2a1b88fff97a4b251c8b07f322e343e5 100644 --- a/tests/unit/asr/deepspeech2_model_test.py +++ b/tests/unit/asr/deepspeech2_model_test.py @@ -16,7 +16,7 @@ import unittest import numpy as np import paddle -from deepspeech.models.ds2 import DeepSpeech2Model +from paddlespeech.s2t.models.ds2 import DeepSpeech2Model class TestDeepSpeech2Model(unittest.TestCase): diff --git a/tests/unit/asr/deepspeech2_online_model_test.py b/tests/unit/asr/deepspeech2_online_model_test.py index 6264070be91d68a7d27e04840a80e858af7ae410..f623c5acd5066795cfa1cae43c622254a5ac88e0 100644 --- a/tests/unit/asr/deepspeech2_online_model_test.py +++ b/tests/unit/asr/deepspeech2_online_model_test.py @@ -16,7 +16,7 @@ import unittest import numpy as np import paddle -from deepspeech.models.ds2_online import DeepSpeech2ModelOnline +from paddlespeech.s2t.models.ds2_online import DeepSpeech2ModelOnline class TestDeepSpeech2ModelOnline(unittest.TestCase): diff --git a/tests/unit/asr/error_rate_test.py b/tests/unit/asr/error_rate_test.py index aef25a2ce33cf97c61a6f1609dbb644c0a9ac594..e5f262c7d5793d84edfc9335f5023cf805ac9bc7 100644 --- a/tests/unit/asr/error_rate_test.py +++ b/tests/unit/asr/error_rate_test.py @@ -14,7 +14,7 @@ """Test error rate.""" import unittest -from deepspeech.utils import error_rate +from paddlespeech.s2t.utils import error_rate class TestParse(unittest.TestCase): diff --git a/tests/unit/asr/mask_test.py b/tests/unit/asr/mask_test.py index f44aca8fce256a7c38b0b7276bb18b663eb13ce0..d6935997f01992e5973a9ab9a34549ba9a01bdff 100644 --- a/tests/unit/asr/mask_test.py +++ b/tests/unit/asr/mask_test.py @@ -16,8 +16,8 @@ import unittest import numpy as np import paddle -from deepspeech.modules.mask import make_non_pad_mask -from deepspeech.modules.mask import make_pad_mask +from paddlespeech.s2t.modules.mask import make_non_pad_mask +from paddlespeech.s2t.modules.mask import make_pad_mask class TestU2Model(unittest.TestCase): diff --git a/tests/unit/asr/u2_model_test.py b/tests/unit/asr/u2_model_test.py index 58600e6baae1adc80e3b51c846c5137dd7428b77..5b11d2ad3e2d42e7bd6d291dcc633475ffd034c2 100644 --- a/tests/unit/asr/u2_model_test.py +++ b/tests/unit/asr/u2_model_test.py @@ -17,8 +17,8 @@ import numpy as np import paddle from yacs.config import CfgNode as CN -from deepspeech.models.u2 import U2Model -from deepspeech.utils.layer_tools import summary +from paddlespeech.s2t.models.u2 import U2Model +from paddlespeech.s2t.utils.layer_tools import summary class TestU2Model(unittest.TestCase): diff --git a/tests/unit/tts/test_data_table.py b/tests/unit/tts/test_data_table.py index 3664ea310463a8b66e239b3b6e4f9b98af0a5990..3ff5bc1afaf27f9468a8f0d48ba5f11e1848676d 100644 --- a/tests/unit/tts/test_data_table.py +++ b/tests/unit/tts/test_data_table.py @@ -11,7 +11,7 @@ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. -from parakeet.datasets.data_tabel import DataTable +from paddlespeech.t2s.datasets.data_tabel import DataTable def test_audio_dataset(): diff --git a/tests/unit/tts/test_expansion.py b/tests/unit/tts/test_expansion.py index 418e9ba19a8a567cc4d2fe7316559f22143c9fff..db626e3cfafbaaab394f54316d67296effc33f1d 100644 --- a/tests/unit/tts/test_expansion.py +++ b/tests/unit/tts/test_expansion.py @@ -13,7 +13,7 @@ # limitations under the License. import paddle -from parakeet.modules import expansion +from paddlespeech.t2s.modules import expansion def test_expand(): diff --git a/tests/unit/tts/test_pwg.py b/tests/unit/tts/test_pwg.py index 2f07a4ab88dd3c1f4672b33f38238008f3cc9231..78cb34f2596e41003b9216730cb2ddb6ef5cf558 100644 --- a/tests/unit/tts/test_pwg.py +++ b/tests/unit/tts/test_pwg.py @@ -18,13 +18,13 @@ from parallel_wavegan.layers import upsample from parallel_wavegan.models import parallel_wavegan as pwgan from timer import timer -from parakeet.models.parallel_wavegan import ConvInUpsampleNet -from parakeet.models.parallel_wavegan import PWGDiscriminator -from parakeet.models.parallel_wavegan import PWGGenerator -from parakeet.models.parallel_wavegan import ResidualBlock -from parakeet.models.parallel_wavegan import ResidualPWGDiscriminator -from parakeet.utils.layer_tools import summary -from parakeet.utils.profile import synchronize +from paddlespeech.t2s.models.parallel_wavegan import ConvInUpsampleNet +from paddlespeech.t2s.models.parallel_wavegan import PWGDiscriminator +from paddlespeech.t2s.models.parallel_wavegan import PWGGenerator +from paddlespeech.t2s.models.parallel_wavegan import ResidualBlock +from paddlespeech.t2s.models.parallel_wavegan import ResidualPWGDiscriminator +from paddlespeech.t2s.utils.layer_tools import summary +from paddlespeech.t2s.utils.profile import synchronize paddle.set_device("gpu:0") device = torch.device("cuda:0") diff --git a/tests/unit/tts/test_reporter.py b/tests/unit/tts/test_reporter.py index bba81d6208da626937a239e9df4f7f11bd357266..a1d83f1f960bf9fbd34fdd452d43c3b2cebfca33 100644 --- a/tests/unit/tts/test_reporter.py +++ b/tests/unit/tts/test_reporter.py @@ -13,9 +13,9 @@ # limitations under the License. import numpy as np -from parakeet.training.reporter import report -from parakeet.training.reporter import scope -from parakeet.training.reporter import Summary +from paddlespeech.t2s.training.reporter import report +from paddlespeech.t2s.training.reporter import scope +from paddlespeech.t2s.training.reporter import Summary def test_reporter_scope(): diff --git a/tests/unit/tts/test_snapshot.py b/tests/unit/tts/test_snapshot.py index e940a81f17bcb5dc5cd114f194a2e19c4f859ccd..6ceff3e5acfd31b0f71670300363e062c8b05fed 100644 --- a/tests/unit/tts/test_snapshot.py +++ b/tests/unit/tts/test_snapshot.py @@ -17,9 +17,9 @@ from itertools import count from paddle import nn from paddle.optimizer import Adam -from parakeet.training.extensions.snapshot import Snapshot -from parakeet.training.trainer import Trainer -from parakeet.training.updater import StandardUpdater +from paddlespeech.t2s.training.extensions.snapshot import Snapshot +from paddlespeech.t2s.training.trainer import Trainer +from paddlespeech.t2s.training.updater import StandardUpdater def test_snapshot(): diff --git a/tests/unit/tts/test_stft.py b/tests/unit/tts/test_stft.py index 8e6ce470a7411f868aa51f6d1504429f87bff2e6..d2d56dca400ffd8da055509583944d0b660a5cb4 100644 --- a/tests/unit/tts/test_stft.py +++ b/tests/unit/tts/test_stft.py @@ -18,8 +18,8 @@ import torch from parallel_wavegan.losses import stft_loss as sl from scipy import signal -from parakeet.modules.stft_loss import MultiResolutionSTFTLoss -from parakeet.modules.stft_loss import STFT +from paddlespeech.t2s.modules.stft_loss import MultiResolutionSTFTLoss +from paddlespeech.t2s.modules.stft_loss import STFT def test_stft(): diff --git a/utils/apply-cmvn.py b/utils/apply-cmvn.py index f80053fbefb2895c7eb45097be650a9b7165d52f..b92e58f456d13677769e2a9ef07e062d4a2288a6 100755 --- a/utils/apply-cmvn.py +++ b/utils/apply-cmvn.py @@ -6,11 +6,11 @@ from distutils.util import strtobool import kaldiio import numpy -from deepspeech.transform.cmvn import CMVN -from deepspeech.utils.cli_readers import file_reader_helper -from deepspeech.utils.cli_utils import get_commandline_args -from deepspeech.utils.cli_utils import is_scipy_wav_style -from deepspeech.utils.cli_writers import file_writer_helper +from paddlespeech.s2t.transform.cmvn import CMVN +from paddlespeech.s2t.utils.cli_readers import file_reader_helper +from paddlespeech.s2t.utils.cli_utils import get_commandline_args +from paddlespeech.s2t.utils.cli_utils import is_scipy_wav_style +from paddlespeech.s2t.utils.cli_writers import file_writer_helper def get_parser(): diff --git a/utils/build_vocab.py b/utils/build_vocab.py index 67c22fbbfec2e252c4a7df8b4b82870cfff68d6e..6a90314759a20d8ade3e33995a1afd9bfa770d3c 100755 --- a/utils/build_vocab.py +++ b/utils/build_vocab.py @@ -21,14 +21,14 @@ import os import tempfile from collections import Counter -from deepspeech.frontend.featurizer.text_featurizer import TextFeaturizer -from deepspeech.frontend.utility import BLANK -from deepspeech.frontend.utility import read_manifest -from deepspeech.frontend.utility import SOS -from deepspeech.frontend.utility import SPACE -from deepspeech.frontend.utility import UNK -from deepspeech.utils.utility import add_arguments -from deepspeech.utils.utility import print_arguments +from paddlespeech.s2t.frontend.featurizer.text_featurizer import TextFeaturizer +from paddlespeech.s2t.frontend.utility import BLANK +from paddlespeech.s2t.frontend.utility import read_manifest +from paddlespeech.s2t.frontend.utility import SOS +from paddlespeech.s2t.frontend.utility import SPACE +from paddlespeech.s2t.frontend.utility import UNK +from paddlespeech.s2t.utils.utility import add_arguments +from paddlespeech.s2t.utils.utility import print_arguments parser = argparse.ArgumentParser(description=__doc__) add_arg = functools.partial(add_arguments, argparser=parser) diff --git a/utils/compute-cmvn-stats.py b/utils/compute-cmvn-stats.py index 706d8cd53b24cbe7c4a1243b416cee0bc0e2203e..276bcd36e9c5baa2b1ef6a561a4cbd2e84da1cfc 100755 --- a/utils/compute-cmvn-stats.py +++ b/utils/compute-cmvn-stats.py @@ -5,11 +5,11 @@ import logging import kaldiio import numpy as np -from deepspeech.transform.transformation import Transformation -from deepspeech.utils.cli_readers import file_reader_helper -from deepspeech.utils.cli_utils import get_commandline_args -from deepspeech.utils.cli_utils import is_scipy_wav_style -from deepspeech.utils.cli_writers import file_writer_helper +from paddlespeech.s2t.transform.transformation import Transformation +from paddlespeech.s2t.utils.cli_readers import file_reader_helper +from paddlespeech.s2t.utils.cli_utils import get_commandline_args +from paddlespeech.s2t.utils.cli_utils import is_scipy_wav_style +from paddlespeech.s2t.utils.cli_writers import file_writer_helper def get_parser(): diff --git a/utils/compute_mean_std.py b/utils/compute_mean_std.py index 0f63715a286c1af82a99f69eb56cf273620fef3d..296d272a46525fc3fdbe42b572e12924fb5557a2 100755 --- a/utils/compute_mean_std.py +++ b/utils/compute_mean_std.py @@ -16,11 +16,11 @@ import argparse import functools -from deepspeech.frontend.augmentor.augmentation import AugmentationPipeline -from deepspeech.frontend.featurizer.audio_featurizer import AudioFeaturizer -from deepspeech.frontend.normalizer import FeatureNormalizer -from deepspeech.utils.utility import add_arguments -from deepspeech.utils.utility import print_arguments +from paddlespeech.s2t.frontend.augmentor.augmentation import AugmentationPipeline +from paddlespeech.s2t.frontend.featurizer.audio_featurizer import AudioFeaturizer +from paddlespeech.s2t.frontend.normalizer import FeatureNormalizer +from paddlespeech.s2t.utils.utility import add_arguments +from paddlespeech.s2t.utils.utility import print_arguments parser = argparse.ArgumentParser(description=__doc__) add_arg = functools.partial(add_arguments, argparser=parser) diff --git a/utils/compute_statistics.py b/utils/compute_statistics.py index 84e50ded5ed29cd7e56f36bd3b2fd852392581aa..e8021c19d0de3e8c64ad3a318d3e9c8ad2758315 100755 --- a/utils/compute_statistics.py +++ b/utils/compute_statistics.py @@ -21,7 +21,7 @@ import numpy as np from sklearn.preprocessing import StandardScaler from tqdm import tqdm -from parakeet.datasets.data_table import DataTable +from paddlespeech.t2s.datasets.data_table import DataTable def main(): diff --git a/utils/copy-feats.py b/utils/copy-feats.py index 7d1b858969b7016714f1de0f131947e161a0b506..2e120881468bd97c88fe1c85e668386ebc012c99 100755 --- a/utils/copy-feats.py +++ b/utils/copy-feats.py @@ -3,11 +3,11 @@ import argparse import logging from distutils.util import strtobool -from deepspeech.transform.transformation import Transformation -from deepspeech.utils.cli_readers import file_reader_helper -from deepspeech.utils.cli_utils import get_commandline_args -from deepspeech.utils.cli_utils import is_scipy_wav_style -from deepspeech.utils.cli_writers import file_writer_helper +from paddlespeech.s2t.transform.transformation import Transformation +from paddlespeech.s2t.utils.cli_readers import file_reader_helper +from paddlespeech.s2t.utils.cli_utils import get_commandline_args +from paddlespeech.s2t.utils.cli_utils import is_scipy_wav_style +from paddlespeech.s2t.utils.cli_writers import file_writer_helper def get_parser(): diff --git a/utils/dump_manifest.py b/utils/dump_manifest.py index 4f115590abfea184500c74cdc87ddb1f40e48f37..b5f7b64a44dead5bac2ea66ee5fdab09d9c255b6 100755 --- a/utils/dump_manifest.py +++ b/utils/dump_manifest.py @@ -17,7 +17,7 @@ import argparse from pathlib import Path from typing import Union -from deepspeech.frontend.utility import read_manifest +from paddlespeech.s2t.frontend.utility import read_manifest key_whitelist = set(['feat', 'text', 'syllable', 'phone']) filename = { diff --git a/utils/feat-to-shape.py b/utils/feat-to-shape.py index 7b36b7e5face1e877a2698a305c2dab7382b0bce..bbc9242f4a1cb7ba9c0a462a8adb612e00197b5d 100755 --- a/utils/feat-to-shape.py +++ b/utils/feat-to-shape.py @@ -3,10 +3,10 @@ import argparse import logging import sys -from deepspeech.transform.transformation import Transformation -from deepspeech.utils.cli_readers import file_reader_helper -from deepspeech.utils.cli_utils import get_commandline_args -from deepspeech.utils.cli_utils import is_scipy_wav_style +from paddlespeech.s2t.transform.transformation import Transformation +from paddlespeech.s2t.utils.cli_readers import file_reader_helper +from paddlespeech.s2t.utils.cli_utils import get_commandline_args +from paddlespeech.s2t.utils.cli_utils import is_scipy_wav_style def get_parser(): diff --git a/utils/format_data.py b/utils/format_data.py index 682dbfdbc8809fed85190fc42249cc9423f7723e..6fe36997a6513121e2878a00306e9d09018af47c 100755 --- a/utils/format_data.py +++ b/utils/format_data.py @@ -17,11 +17,11 @@ import argparse import functools import json -from deepspeech.frontend.featurizer.text_featurizer import TextFeaturizer -from deepspeech.frontend.utility import load_cmvn -from deepspeech.frontend.utility import read_manifest -from deepspeech.utils.utility import add_arguments -from deepspeech.utils.utility import print_arguments +from paddlespeech.s2t.frontend.featurizer.text_featurizer import TextFeaturizer +from paddlespeech.s2t.frontend.utility import load_cmvn +from paddlespeech.s2t.frontend.utility import read_manifest +from paddlespeech.s2t.utils.utility import add_arguments +from paddlespeech.s2t.utils.utility import print_arguments parser = argparse.ArgumentParser(description=__doc__) add_arg = functools.partial(add_arguments, argparser=parser) diff --git a/utils/format_triplet_data.py b/utils/format_triplet_data.py index f3dd7ca4a3410d798d9b3aea9cf006b67f4d4b76..79b3d2cb2dd8b4cb2edea6f055b109d35dc0cae7 100755 --- a/utils/format_triplet_data.py +++ b/utils/format_triplet_data.py @@ -17,11 +17,11 @@ import argparse import functools import json -from deepspeech.frontend.featurizer.text_featurizer import TextFeaturizer -from deepspeech.frontend.utility import load_cmvn -from deepspeech.frontend.utility import read_manifest -from deepspeech.utils.utility import add_arguments -from deepspeech.utils.utility import print_arguments +from paddlespeech.s2t.frontend.featurizer.text_featurizer import TextFeaturizer +from paddlespeech.s2t.frontend.utility import load_cmvn +from paddlespeech.s2t.frontend.utility import read_manifest +from paddlespeech.s2t.utils.utility import add_arguments +from paddlespeech.s2t.utils.utility import print_arguments parser = argparse.ArgumentParser(description=__doc__) add_arg = functools.partial(add_arguments, argparser=parser) diff --git a/utils/merge_scp2json.py b/utils/merge_scp2json.py index b724a7dd988a9726da33808f69121a46a8a3f5c1..650e46698046465e384eae4e21a880a7279802c5 100755 --- a/utils/merge_scp2json.py +++ b/utils/merge_scp2json.py @@ -8,7 +8,7 @@ import sys from distutils.util import strtobool from io import open -from deepspeech.utils.cli_utils import get_commandline_args +from paddlespeech.s2t.utils.cli_utils import get_commandline_args PY2 = sys.version_info[0] == 2 sys.stdin = codecs.getreader("utf-8")(sys.stdin if PY2 else sys.stdin.buffer)