From 050d766915c01a59fd4880dfb263dbc30605944f Mon Sep 17 00:00:00 2001 From: tianhao zhang <15600919271@163.com> Date: Wed, 19 Oct 2022 05:31:18 +0000 Subject: [PATCH] fix u2pp model --- docs/source/released_model.md | 2 +- paddlespeech/cli/asr/infer.py | 4 ++-- paddlespeech/resource/model_alias.py | 1 - paddlespeech/resource/pretrained_models.py | 26 +++------------------- 4 files changed, 6 insertions(+), 27 deletions(-) diff --git a/docs/source/released_model.md b/docs/source/released_model.md index a2456f1f..586f17c3 100644 --- a/docs/source/released_model.md +++ b/docs/source/released_model.md @@ -9,7 +9,7 @@ Acoustic Model | Training Data | Token-based | Size | Descriptions | CER | WER | [Ds2 Online Aishell ASR0 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr0/asr0_deepspeech2_online_aishell_fbank161_ckpt_0.2.1.model.tar.gz) | Aishell Dataset | Char-based | 491 MB | 2 Conv + 5 LSTM layers | 0.0666 |-| 151 h | [D2 Online Aishell ASR0](../../examples/aishell/asr0) | onnx/inference/python | [Ds2 Offline Aishell ASR0 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr0/asr0_deepspeech2_offline_aishell_ckpt_1.0.1.model.tar.gz)| Aishell Dataset | Char-based | 1.4 GB | 2 Conv + 5 bidirectional LSTM layers| 0.0554 |-| 151 h | [Ds2 Offline Aishell ASR0](../../examples/aishell/asr0) | inference/python | [Conformer Online Wenetspeech ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/wenetspeech/asr1/asr1_chunk_conformer_wenetspeech_ckpt_1.0.0a.model.tar.gz) | WenetSpeech Dataset | Char-based | 457 MB | Encoder:Conformer, Decoder:Transformer, Decoding method: Attention rescoring| 0.11 (test\_net) 0.1879 (test\_meeting) |-| 10000 h |- | python | -[Conformer U2PP Online Wenetspeech ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/wenetspeech/asr1/asr1_chunk_conformer_u2pp_wenetspeech_ckpt_1.1.4.model.tar.gz) | WenetSpeech Dataset | Char-based | 476 MB | Encoder:Conformer, Decoder:BiTransformer, Decoding method: Attention rescoring| 0.047198 (aishell test\_-1) 0.059212 (aishell test\_16) |-| 10000 h |- | python | +[Conformer U2PP Online Wenetspeech ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/wenetspeech/asr1/asr1_chunk_conformer_u2pp_wenetspeech_ckpt_1.3.0.model.tar.gz) | WenetSpeech Dataset | Char-based | 476 MB | Encoder:Conformer, Decoder:BiTransformer, Decoding method: Attention rescoring| 0.047198 (aishell test\_-1) 0.059212 (aishell test\_16) |-| 10000 h |- | python | [Conformer Online Aishell ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr1/asr1_chunk_conformer_aishell_ckpt_0.2.0.model.tar.gz) | Aishell Dataset | Char-based | 189 MB | Encoder:Conformer, Decoder:Transformer, Decoding method: Attention rescoring| 0.0544 |-| 151 h | [Conformer Online Aishell ASR1](../../examples/aishell/asr1) | python | [Conformer Offline Aishell ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr1/asr1_conformer_aishell_ckpt_1.0.1.model.tar.gz) | Aishell Dataset | Char-based | 189 MB | Encoder:Conformer, Decoder:Transformer, Decoding method: Attention rescoring | 0.0460 |-| 151 h | [Conformer Offline Aishell ASR1](../../examples/aishell/asr1) | python | [Transformer Aishell ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr1/asr1_transformer_aishell_ckpt_0.1.1.model.tar.gz) | Aishell Dataset | Char-based | 128 MB | Encoder:Transformer, Decoder:Transformer, Decoding method: Attention rescoring | 0.0523 || 151 h | [Transformer Aishell ASR1](../../examples/aishell/asr1) | python | diff --git a/paddlespeech/cli/asr/infer.py b/paddlespeech/cli/asr/infer.py index 437f6463..00414336 100644 --- a/paddlespeech/cli/asr/infer.py +++ b/paddlespeech/cli/asr/infer.py @@ -52,7 +52,7 @@ class ASRExecutor(BaseExecutor): self.parser.add_argument( '--model', type=str, - default='conformer_u2pp_wenetspeech', + default='conformer_u2pp_online_wenetspeech', choices=[ tag[:tag.index('-')] for tag in self.task_resource.pretrained_models.keys() @@ -470,7 +470,7 @@ class ASRExecutor(BaseExecutor): @stats_wrapper def __call__(self, audio_file: os.PathLike, - model: str='conformer_u2pp_wenetspeech', + model: str='conformer_u2pp_online_wenetspeech', lang: str='zh', sample_rate: int=16000, config: os.PathLike=None, diff --git a/paddlespeech/resource/model_alias.py b/paddlespeech/resource/model_alias.py index f5ec655b..8e9ecc4b 100644 --- a/paddlespeech/resource/model_alias.py +++ b/paddlespeech/resource/model_alias.py @@ -25,7 +25,6 @@ model_alias = { "deepspeech2online": ["paddlespeech.s2t.models.ds2:DeepSpeech2Model"], "conformer": ["paddlespeech.s2t.models.u2:U2Model"], "conformer_online": ["paddlespeech.s2t.models.u2:U2Model"], - "conformer_u2pp": ["paddlespeech.s2t.models.u2:U2Model"], "conformer_u2pp_online": ["paddlespeech.s2t.models.u2:U2Model"], "transformer": ["paddlespeech.s2t.models.u2:U2Model"], "wenetspeech": ["paddlespeech.s2t.models.u2:U2Model"], diff --git a/paddlespeech/resource/pretrained_models.py b/paddlespeech/resource/pretrained_models.py index efd6bb3f..df50a6a9 100644 --- a/paddlespeech/resource/pretrained_models.py +++ b/paddlespeech/resource/pretrained_models.py @@ -68,32 +68,12 @@ asr_dynamic_pretrained_models = { '', }, }, - "conformer_u2pp_wenetspeech-zh-16k": { - '1.1': { - 'url': - 'https://paddlespeech.bj.bcebos.com/s2t/wenetspeech/asr1/asr1_chunk_conformer_u2pp_wenetspeech_ckpt_1.1.3.model.tar.gz', - 'md5': - '662b347e1d2131b7a4dc5398365e2134', - 'cfg_path': - 'model.yaml', - 'ckpt_path': - 'exp/chunk_conformer_u2pp/checkpoints/avg_10', - 'model': - 'exp/chunk_conformer_u2pp/checkpoints/avg_10.pdparams', - 'params': - 'exp/chunk_conformer_u2pp/checkpoints/avg_10.pdparams', - 'lm_url': - '', - 'lm_md5': - '', - }, - }, "conformer_u2pp_online_wenetspeech-zh-16k": { - '1.1': { + '1.3': { 'url': - 'https://paddlespeech.bj.bcebos.com/s2t/wenetspeech/asr1/asr1_chunk_conformer_u2pp_wenetspeech_ckpt_1.1.4.model.tar.gz', + 'https://paddlespeech.bj.bcebos.com/s2t/wenetspeech/asr1/asr1_chunk_conformer_u2pp_wenetspeech_ckpt_1.3.0.model.tar.gz', 'md5': - '3100fc1eac5779486cab859366992d0b', + '62d230c1bf27731192aa9d3b8deca300', 'cfg_path': 'model.yaml', 'ckpt_path': -- GitLab