|
2 years ago | |
---|---|---|
.. | ||
conf | 3 years ago | |
local | 2 years ago | |
README.md | 3 years ago | |
path.sh | 3 years ago | |
run.sh | 3 years ago |
README.md
SpeedySpeech with CSMSC
This example contains code used to train a SpeedySpeech model with Chinese Standard Mandarin Speech Copus. NOTE that we only implement the student part of the Speedyspeech model. The ground truth alignment used to train the model is extracted from the dataset using MFA.
Dataset
Download and Extract
Download CSMSC from it's Official Website.
Get MFA Result and Extract
We use MFA to get durations for SPEEDYSPEECH. You can download from here baker_alignment_tone.tar.gz, or train your MFA model reference to mfa example 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
- source path.
- preprocess the dataset.
- train the model.
- synthesize wavs.
- synthesize waveform from
metadata.jsonl
. - synthesize waveform from a text file.
- synthesize waveform from
- inference using the static model.
./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, run the following command will only preprocess the dataset.
./run.sh --stage 0 --stop-stage 0
Data Preprocessing
./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.
dump
├── dev
│ ├── norm
│ └── raw
├── test
│ ├── norm
│ └── raw
└── train
├── norm
├── raw
└── feats_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 the log magnitude of the mel spectrogram of each utterance, while the norm folder contains the normalized spectrogram. The statistics used to normalize the spectrogram are computed from the training set, which is located in dump/train/feats_stats.npy
.
Also, there is a metadata.jsonl
in each subfolder. It is a table-like file that contains phones, tones, durations, the path of the spectrogram, and the id of each utterance.
Model Training
./local/train.sh
calls ${BIN_DIR}/train.py
.
CUDA_VISIBLE_DEVICES=${gpus} ./local/train.sh ${conf_path} ${train_output_path} || exit -1
Here's the complete help message.
usage: train.py [-h] [--config CONFIG] [--train-metadata TRAIN_METADATA]
[--dev-metadata DEV_METADATA] [--output-dir OUTPUT_DIR]
[--ngpu NGPU] [--use-relative-path USE_RELATIVE_PATH]
[--phones-dict PHONES_DICT] [--tones-dict TONES_DICT]
Train a Speedyspeech model with a single speaker dataset.
optional arguments:
-h, --help show this help message and exit
--config CONFIG 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.
--use-relative-path USE_RELATIVE_PATH
whether use relative path in metadata
--phones-dict PHONES_DICT
phone vocabulary file.
--tones-dict TONES_DICT
tone vocabulary file.
--config
is a config file in yaml format to overwrite the default config, which can be found atconf/default.yaml
.--train-metadata
and--dev-metadata
should be the metadata file in the normalized subfolder oftrain
anddev
in thedump
folder.--output-dir
is the directory to save the results of the experiment. Checkpoints are saved incheckpoints/
inside this directory.--ngpu
is the number of gpus to use, if ngpu == 0, use cpu.--phones-dict
is the path of the phone vocabulary file.--tones-dict
is the path of the tone vocabulary file.
Synthesizing
We use parallel wavegan as the neural vocoder. Download pretrained parallel wavegan model from pwg_baker_ckpt_0.4.zip and unzip it.
unzip pwg_baker_ckpt_0.4.zip
Parallel WaveGAN checkpoint contains files listed below.
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 ${BIN_DIR}/../synthesize.py
, which can synthesize waveform from metadata.jsonl
.
CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh ${conf_path} ${train_output_path} ${ckpt_name}
usage: synthesize.py [-h]
[--am {speedyspeech_csmsc,fastspeech2_csmsc,fastspeech2_ljspeech,fastspeech2_aishell3,fastspeech2_vctk}]
[--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}
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 ${BIN_DIR}/../synthesize_e2e.py
, which can synthesize waveform from text file.
CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize_e2e.sh ${conf_path} ${train_output_path} ${ckpt_name}
usage: synthesize_e2e.py [-h]
[--am {speedyspeech_csmsc,fastspeech2_csmsc,fastspeech2_ljspeech,fastspeech2_aishell3,fastspeech2_vctk}]
[--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}]
[--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,fastspeech2_csmsc,fastspeech2_ljspeech,fastspeech2_aishell3,fastspeech2_vctk}
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}
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.
--am
is acoustic model type with the format {model_name}_{dataset}--am_config
,--am_checkpoint
,--am_stat
,--phones_dict
and--tones_dict
are arguments for acoustic model, which correspond to the 5 files in the speedyspeech pretrained model.--voc
is vocoder type with the format {model_name}_{dataset}--voc_config
,--voc_checkpoint
,--voc_stat
are arguments for vocoder, which correspond to the 3 files in the parallel wavegan pretrained model.--lang
is the model language, which can bezh
oren
.--test_metadata
should be the metadata file in the normalized subfolder oftest
in thedump
folder.--text
is the text file, which contains sentences to synthesize.--output_dir
is the directory to save synthesized audio files.--ngpu
is the number of gpus to use, if ngpu == 0, use cpu.
Inferencing
After synthesizing, we will get static models of speedyspeech and pwgan in ${train_output_path}/inference
.
./local/inference.sh
calls ${BIN_DIR}/inference.py
, which provides a paddle static model inference example for speedyspeech + pwgan synthesize.
CUDA_VISIBLE_DEVICES=${gpus} ./local/inference.sh ${train_output_path}
Pretrained Model
Pretrained SpeedySpeech model with no silence in the edge of audiosspeedyspeech_nosil_baker_ckpt_0.5.zip.
The static model can be downloaded here speedyspeech_nosil_baker_static_0.5.zip.
Model | Step | eval/loss | eval/l1_loss | eval/duration_loss | eval/ssim_loss |
---|---|---|---|---|---|
default | 1(gpu) x 11400 | 0.83655 | 0.42324 | 0.03211 | 0.38119 |
SpeedySpeech checkpoint contains files listed below.
speedyspeech_nosil_baker_ckpt_0.5
├── default.yaml # default config used to train speedyspeech
├── feats_stats.npy # statistics used to normalize spectrogram when training speedyspeech
├── phone_id_map.txt # phone vocabulary file when training speedyspeech
├── snapshot_iter_11400.pdz # model parameters and optimizer states
└── tone_id_map.txt # tone vocabulary file when training speedyspeech
You can use the following scripts to synthesize for ${BIN_DIR}/../sentences.txt
using pretrained speedyspeech and parallel wavegan models.
source path.sh
FLAGS_allocator_strategy=naive_best_fit \
FLAGS_fraction_of_gpu_memory_to_use=0.01 \
python3 ${BIN_DIR}/../synthesize_e2e.py \
--am=speedyspeech_csmsc \
--am_config=speedyspeech_nosil_baker_ckpt_0.5/default.yaml \
--am_ckpt=speedyspeech_nosil_baker_ckpt_0.5/snapshot_iter_11400.pdz \
--am_stat=speedyspeech_nosil_baker_ckpt_0.5/feats_stats.npy \
--voc=pwgan_csmsc \
--voc_config=pwg_baker_ckpt_0.4/pwg_default.yaml \
--voc_ckpt=pwg_baker_ckpt_0.4/pwg_snapshot_iter_400000.pdz \
--voc_stat=pwg_baker_ckpt_0.4/pwg_stats.npy \
--lang=zh \
--text=${BIN_DIR}/../sentences.txt \
--output_dir=exp/default/test_e2e \
--inference_dir=exp/default/inference \
--phones_dict=speedyspeech_nosil_baker_ckpt_0.5/phone_id_map.txt \
--tones_dict=speedyspeech_nosil_baker_ckpt_0.5/tone_id_map.txt