From 2844f388dc63e1d8f00018b9888e7b9a43d8b544 Mon Sep 17 00:00:00 2001 From: TianYuan Date: Wed, 26 Jan 2022 10:23:15 +0800 Subject: [PATCH] [doc ]add tacotron2 readme (#1385) * add tacotron2 readme, test=doc * update changelog.md, test=doc --- CHANGELOG.md | 5 + examples/csmsc/tts0/README.md | 250 ++++++++++++++++++ examples/csmsc/tts3/run.sh | 4 - .../models/ds2/deepspeech2.py | 2 +- paddleaudio/CHANGELOG.md | 1 - paddlespeech/cli/st/infer.py | 4 +- paddlespeech/cli/utils.py | 2 +- 7 files changed, 259 insertions(+), 9 deletions(-) create mode 100644 examples/csmsc/tts0/README.md diff --git a/CHANGELOG.md b/CHANGELOG.md index b37fb777..3178434c 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,5 +1,10 @@ # Changelog +Date: 2022-1-19, Author: yt605155624. +Add features to: T2S: + - Add csmsc Tacotron2. + - PRLink: https://github.com/PaddlePaddle/PaddleSpeech/pull/1314 + Date: 2022-1-10, Author: Jackwaterveg. Add features to: CLI: diff --git a/examples/csmsc/tts0/README.md b/examples/csmsc/tts0/README.md new file mode 100644 index 00000000..3f3b4a39 --- /dev/null +++ b/examples/csmsc/tts0/README.md @@ -0,0 +1,250 @@ +# Tacotron2 with CSMSC +This example contains code used to train a [Tacotron2](https://arxiv.org/abs/1712.05884) model with [Chinese Standard Mandarin Speech Copus](https://www.data-baker.com/open_source.html). + +## Dataset +### Download and Extract +Download CSMSC from it's [Official Website](https://test.data-baker.com/data/index/source). + +### Get MFA Result and Extract +We use [MFA](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) to get phonemes for Tacotron2, the durations of MFA are not needed here. +You can download from here [baker_alignment_tone.tar.gz](https://paddlespeech.bj.bcebos.com/MFA/BZNSYP/with_tone/baker_alignment_tone.tar.gz), or train your MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) of our repo. + +## Get Started +Assume the path to the dataset is `~/datasets/BZNSYP`. +Assume the path to the MFA result of CSMSC is `./baker_alignment_tone`. +Run the command below to +1. **source path**. +2. preprocess the dataset. +3. train the model. +4. synthesize wavs. + - synthesize waveform from `metadata.jsonl`. + - synthesize waveform from a text file. + +```bash +./run.sh +``` +You can choose a range of stages you want to run, or set `stage` equal to `stop-stage` to use only one stage, for example, running the following command will only preprocess the dataset. +```bash +./run.sh --stage 0 --stop-stage 0 +``` +### Data Preprocessing +```bash +./local/preprocess.sh ${conf_path} +``` +When it is done. A `dump` folder is created in the current directory. The structure of the dump folder is listed below. + +```text +dump +├── dev +│ ├── norm +│ └── raw +├── phone_id_map.txt +├── speaker_id_map.txt +├── test +│ ├── norm +│ └── raw +└── train + ├── energy_stats.npy + ├── norm + ├── pitch_stats.npy + ├── raw + └── speech_stats.npy +``` +The dataset is split into 3 parts, namely `train`, `dev`, and` test`, each of which contains a `norm` and `raw` subfolder. The raw folder contains speech、pitch and energy features of each utterance, while the norm folder contains normalized ones. The statistics used to normalize features are computed from the training set, which is located in `dump/train/*_stats.npy`. + +Also, there is a `metadata.jsonl` in each subfolder. It is a table-like file that contains phones, text_lengths, speech_lengths, durations, the path of speech features, the path of pitch features, the path of energy features, speaker, and the id of each utterance. + +### Model Training +```bash +CUDA_VISIBLE_DEVICES=${gpus} ./local/train.sh ${conf_path} ${train_output_path} +``` +`./local/train.sh` calls `${BIN_DIR}/train.py`. +Here's the complete help message. +```text +usage: train.py [-h] [--config CONFIG] [--train-metadata TRAIN_METADATA] + [--dev-metadata DEV_METADATA] [--output-dir OUTPUT_DIR] + [--ngpu NGPU] [--phones-dict PHONES_DICT] + +Train a Tacotron2 model. + +optional arguments: + -h, --help show this help message and exit + --config CONFIG tacotron2 config file. + --train-metadata TRAIN_METADATA + training data. + --dev-metadata DEV_METADATA + dev data. + --output-dir OUTPUT_DIR + output dir. + --ngpu NGPU if ngpu == 0, use cpu. + --phones-dict PHONES_DICT + phone vocabulary file. +``` +1. `--config` is a config file in yaml format to overwrite the default config, which can be found at `conf/default.yaml`. +2. `--train-metadata` and `--dev-metadata` should be the metadata file in the normalized subfolder of `train` and `dev` in the `dump` folder. +3. `--output-dir` is the directory to save the results of the experiment. Checkpoints are saved in `checkpoints/` inside this directory. +4. `--ngpu` is the number of gpus to use, if ngpu == 0, use cpu. +5. `--phones-dict` is the path of the phone vocabulary file. + +### Synthesizing +We use [parallel wavegan](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/csmsc/voc1) as the neural vocoder. +Download pretrained parallel wavegan model from [pwg_baker_ckpt_0.4.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/pwgan/pwg_baker_ckpt_0.4.zip) and unzip it. +```bash +unzip pwg_baker_ckpt_0.4.zip +``` +Parallel WaveGAN checkpoint contains files listed below. +```text +pwg_baker_ckpt_0.4 +├── pwg_default.yaml # default config used to train parallel wavegan +├── pwg_snapshot_iter_400000.pdz # model parameters of parallel wavegan +└── pwg_stats.npy # statistics used to normalize spectrogram when training parallel wavegan +``` +`./local/synthesize.sh` calls `${BIN_DIR}/../synthesize.py`, which can synthesize waveform from `metadata.jsonl`. +```bash +CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh ${conf_path} ${train_output_path} ${ckpt_name} +``` +```text +usage: synthesize.py [-h] + [--am {speedyspeech_csmsc,fastspeech2_csmsc,fastspeech2_ljspeech,fastspeech2_aishell3,fastspeech2_vctk,tacotron2_csmsc}] + [--am_config AM_CONFIG] [--am_ckpt AM_CKPT] + [--am_stat AM_STAT] [--phones_dict PHONES_DICT] + [--tones_dict TONES_DICT] [--speaker_dict SPEAKER_DICT] + [--voice-cloning VOICE_CLONING] + [--voc {pwgan_csmsc,pwgan_ljspeech,pwgan_aishell3,pwgan_vctk,mb_melgan_csmsc}] + [--voc_config VOC_CONFIG] [--voc_ckpt VOC_CKPT] + [--voc_stat VOC_STAT] [--ngpu NGPU] + [--test_metadata TEST_METADATA] [--output_dir OUTPUT_DIR] + +Synthesize with acoustic model & vocoder + +optional arguments: + -h, --help show this help message and exit + --am {speedyspeech_csmsc,fastspeech2_csmsc,fastspeech2_ljspeech,fastspeech2_aishell3,fastspeech2_vctk,tacotron2_csmsc} + Choose acoustic model type of tts task. + --am_config AM_CONFIG + Config of acoustic model. Use deault config when it is + None. + --am_ckpt AM_CKPT Checkpoint file of acoustic model. + --am_stat AM_STAT mean and standard deviation used to normalize + spectrogram when training acoustic model. + --phones_dict PHONES_DICT + phone vocabulary file. + --tones_dict TONES_DICT + tone vocabulary file. + --speaker_dict SPEAKER_DICT + speaker id map file. + --voice-cloning VOICE_CLONING + whether training voice cloning model. + --voc {pwgan_csmsc,pwgan_ljspeech,pwgan_aishell3,pwgan_vctk,mb_melgan_csmsc} + Choose vocoder type of tts task. + --voc_config VOC_CONFIG + Config of voc. Use deault config when it is None. + --voc_ckpt VOC_CKPT Checkpoint file of voc. + --voc_stat VOC_STAT mean and standard deviation used to normalize + spectrogram when training voc. + --ngpu NGPU if ngpu == 0, use cpu. + --test_metadata TEST_METADATA + test metadata. + --output_dir OUTPUT_DIR + output dir. +``` +`./local/synthesize_e2e.sh` calls `${BIN_DIR}/../synthesize_e2e.py`, which can synthesize waveform from text file. +```bash +CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize_e2e.sh ${conf_path} ${train_output_path} ${ckpt_name} +``` +```text +usage: synthesize_e2e.py [-h] + [--am {speedyspeech_csmsc,speedyspeech_aishell3,fastspeech2_csmsc,fastspeech2_ljspeech,fastspeech2_aishell3,fastspeech2_vctk,tacotron2_csmsc}] + [--am_config AM_CONFIG] [--am_ckpt AM_CKPT] + [--am_stat AM_STAT] [--phones_dict PHONES_DICT] + [--tones_dict TONES_DICT] + [--speaker_dict SPEAKER_DICT] [--spk_id SPK_ID] + [--voc {pwgan_csmsc,pwgan_ljspeech,pwgan_aishell3,pwgan_vctk,mb_melgan_csmsc,style_melgan_csmsc,hifigan_csmsc}] + [--voc_config VOC_CONFIG] [--voc_ckpt VOC_CKPT] + [--voc_stat VOC_STAT] [--lang LANG] + [--inference_dir INFERENCE_DIR] [--ngpu NGPU] + [--text TEXT] [--output_dir OUTPUT_DIR] + +Synthesize with acoustic model & vocoder + +optional arguments: + -h, --help show this help message and exit + --am {speedyspeech_csmsc,speedyspeech_aishell3,fastspeech2_csmsc,fastspeech2_ljspeech,fastspeech2_aishell3,fastspeech2_vctk,tacotron2_csmsc} + Choose acoustic model type of tts task. + --am_config AM_CONFIG + Config of acoustic model. Use deault config when it is + None. + --am_ckpt AM_CKPT Checkpoint file of acoustic model. + --am_stat AM_STAT mean and standard deviation used to normalize + spectrogram when training acoustic model. + --phones_dict PHONES_DICT + phone vocabulary file. + --tones_dict TONES_DICT + tone vocabulary file. + --speaker_dict SPEAKER_DICT + speaker id map file. + --spk_id SPK_ID spk id for multi speaker acoustic model + --voc {pwgan_csmsc,pwgan_ljspeech,pwgan_aishell3,pwgan_vctk,mb_melgan_csmsc,style_melgan_csmsc,hifigan_csmsc} + Choose vocoder type of tts task. + --voc_config VOC_CONFIG + Config of voc. Use deault config when it is None. + --voc_ckpt VOC_CKPT Checkpoint file of voc. + --voc_stat VOC_STAT mean and standard deviation used to normalize + spectrogram when training voc. + --lang LANG Choose model language. zh or en + --inference_dir INFERENCE_DIR + dir to save inference models + --ngpu NGPU if ngpu == 0, use cpu. + --text TEXT text to synthesize, a 'utt_id sentence' pair per line. + --output_dir OUTPUT_DIR + output dir. +``` +1. `--am` is acoustic model type with the format {model_name}_{dataset} +2. `--am_config`, `--am_checkpoint`, `--am_stat` and `--phones_dict` are arguments for acoustic model, which correspond to the 4 files in the Tacotron2 pretrained model. +3. `--voc` is vocoder type with the format {model_name}_{dataset} +4. `--voc_config`, `--voc_checkpoint`, `--voc_stat` are arguments for vocoder, which correspond to the 3 files in the parallel wavegan pretrained model. +5. `--lang` is the model language, which can be `zh` or `en`. +6. `--test_metadata` should be the metadata file in the normalized subfolder of `test` in the `dump` folder. +7. `--text` is the text file, which contains sentences to synthesize. +8. `--output_dir` is the directory to save synthesized audio files. +9. `--ngpu` is the number of gpus to use, if ngpu == 0, use cpu. + + +## Pretrained Model +Pretrained Tacotron2 model with no silence in the edge of audios: +- [tacotron2_csmsc_ckpt_0.2.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/tacotron2/tacotron2_csmsc_ckpt_0.2.0.zip) + + +Model | Step | eval/loss | eval/l1_loss | eval/mse_loss | eval/bce_loss| eval/attn_loss +:-------------:| :------------:| :-----: | :-----: | :--------: |:--------:|:---------: +default| 1(gpu) x 30600|0.57185|0.39614|0.14642|0.029|5.8e-05| + +Tacotron2 checkpoint contains files listed below. +```text +tacotron2_csmsc_ckpt_0.2.0 +├── default.yaml # default config used to train Tacotron2 +├── phone_id_map.txt # phone vocabulary file when training Tacotron2 +├── snapshot_iter_30600.pdz # model parameters and optimizer states +└── speech_stats.npy # statistics used to normalize spectrogram when training Tacotron2 +``` +You can use the following scripts to synthesize for `${BIN_DIR}/../sentences.txt` using pretrained Tacotron2 and parallel wavegan models. +```bash +source path.sh + +FLAGS_allocator_strategy=naive_best_fit \ +FLAGS_fraction_of_gpu_memory_to_use=0.01 \ +python3 ${BIN_DIR}/../synthesize_e2e.py \ + --am=tacotron2_csmsc \ + --am_config=tacotron2_csmsc_ckpt_0.2.0/default.yaml \ + --am_ckpt=tacotron2_csmsc_ckpt_0.2.0/snapshot_iter_30600.pdz \ + --am_stat=tacotron2_csmsc_ckpt_0.2.0/speech_stats.npy \ + --voc=pwgan_csmsc \ + --voc_config=pwg_baker_ckpt_0.4/pwg_default.yaml \ + --voc_ckpt=pwg_baker_ckpt_0.4/pwg_snapshot_iter_400000.pdz \ + --voc_stat=pwg_baker_ckpt_0.4/pwg_stats.npy \ + --lang=zh \ + --text=${BIN_DIR}/../sentences.txt \ + --output_dir=exp/default/test_e2e \ + --inference_dir=exp/default/inference \ + --phones_dict=tacotron2_csmsc_ckpt_0.2.0/phone_id_map.txt +``` diff --git a/examples/csmsc/tts3/run.sh b/examples/csmsc/tts3/run.sh index 8f06e933..5c394c9f 100755 --- a/examples/csmsc/tts3/run.sh +++ b/examples/csmsc/tts3/run.sh @@ -36,7 +36,3 @@ if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize_e2e.sh ${conf_path} ${train_output_path} ${ckpt_name} || exit -1 fi -if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then - # inference with static model - CUDA_VISIBLE_DEVICES=${gpus} ./local/inference.sh ${train_output_path} || exit -1 -fi diff --git a/examples/other/1xt2x/src_deepspeech2x/models/ds2/deepspeech2.py b/examples/other/1xt2x/src_deepspeech2x/models/ds2/deepspeech2.py index 59be4222..f6e185ff 100644 --- a/examples/other/1xt2x/src_deepspeech2x/models/ds2/deepspeech2.py +++ b/examples/other/1xt2x/src_deepspeech2x/models/ds2/deepspeech2.py @@ -169,7 +169,7 @@ class DeepSpeech2Model(nn.Layer): eouts, eouts_len = self.encoder(audio, audio_len) probs = self.decoder.softmax(eouts) batch_size = probs.shape[0] - self.decoder.reset_decoder(batch_size = batch_size) + self.decoder.reset_decoder(batch_size=batch_size) self.decoder.next(probs, eouts_len) trans_best, trans_beam = self.decoder.decode() return trans_best diff --git a/paddleaudio/CHANGELOG.md b/paddleaudio/CHANGELOG.md index 4dc68c6f..825c32f0 100644 --- a/paddleaudio/CHANGELOG.md +++ b/paddleaudio/CHANGELOG.md @@ -1,2 +1 @@ # Changelog - diff --git a/paddlespeech/cli/st/infer.py b/paddlespeech/cli/st/infer.py index 1276424c..cb973502 100644 --- a/paddlespeech/cli/st/infer.py +++ b/paddlespeech/cli/st/infer.py @@ -173,8 +173,8 @@ class STExecutor(BaseExecutor): self.config.decode.decoding_method = "fullsentence" with UpdateConfig(self.config): - self.config.cmvn_path = os.path.join( - res_path, self.config.cmvn_path) + self.config.cmvn_path = os.path.join(res_path, + self.config.cmvn_path) self.config.spm_model_prefix = os.path.join( res_path, self.config.spm_model_prefix) self.text_feature = TextFeaturizer( diff --git a/paddlespeech/cli/utils.py b/paddlespeech/cli/utils.py index 63b670c8..d11178df 100644 --- a/paddlespeech/cli/utils.py +++ b/paddlespeech/cli/utils.py @@ -24,11 +24,11 @@ from typing import Any from typing import Dict import paddle -import paddleaudio import requests import yaml from paddle.framework import load +import paddleaudio from . import download from .. import __version__ from .entry import commands -- GitLab