|
3 years ago | |
---|---|---|
.. | ||
conf | 3 years ago | |
README.md | 3 years ago | |
inference.py | 3 years ago | |
inference.sh | 3 years ago | |
preprocess.sh | 3 years ago | |
run.sh | 3 years ago | |
synthesize.sh | 3 years ago | |
synthesize_e2e.py | 3 years ago | |
synthesize_e2e.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 the datasaet
Download CSMSC from it's Official Website.
Get MFA result of CSMSC and Extract it
We use MFA to get durations for SPEEDYSPEECH. You can download from here baker_alignment_tone.tar.gz, or train your own MFA model reference to use_mfa example of our repo.
Preprocess the dataset
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 preprocess the dataset.
./preprocess.sh
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
sub folder. The raw folder contains log magnitude of mel spectrogram of each utterances, while the norm folder contains normalized spectrogram. The statistics used to normalize the spectrogram is 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 which contains phones, tones, durations, path of spectrogram, and id of each utterance.
Train the model
./run.sh
calls ../train.py
.
./run.sh
Here's the complete help message.
usage: train.py [-h] [--config CONFIG] [--train-metadata TRAIN_METADATA]
[--dev-metadata DEV_METADATA] [--output-dir OUTPUT_DIR]
[--device DEVICE] [--nprocs NPROCS] [--verbose VERBOSE]
[--use-relative-path USE_RELATIVE_PATH]
[--phones-dict PHONES_DICT] [--tones-dict TONES_DICT]
Train a Speedyspeech model with sigle 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.
--device DEVICE device type to use.
--nprocs NPROCS number of processes.
--verbose VERBOSE verbose.
--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 save incheckpoints/
inside this directory.--device
is the type of the device to run the experiment, 'cpu' or 'gpu' are supported.--nprocs
is the number of processes to run in parallel, note that nprocs > 1 is only supported when--device
is 'gpu'.--phones-dict
is the path of the phone vocabulary file.--tones-dict
is the path of the tone vocabulary file.
Pretrained Model
Pretrained SpeedySpeech model with no silence in the edge of audios. speedyspeech_nosil_baker_ckpt_0.5.zip
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
Synthesize
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
synthesize.sh
calls ../synthesize.py
, which can synthesize waveform from metadata.jsonl
.
./synthesize.sh
usage: synthesize.py [-h] [--speedyspeech-config SPEEDYSPEECH_CONFIG]
[--speedyspeech-checkpoint SPEEDYSPEECH_CHECKPOINT]
[--speedyspeech-stat SPEEDYSPEECH_STAT]
[--pwg-config PWG_CONFIG]
[--pwg-checkpoint PWG_CHECKPOINT] [--pwg-stat PWG_STAT]
[--phones-dict PHONES_DICT] [--tones-dict TONES_DICT]
[--test-metadata TEST_METADATA] [--output-dir OUTPUT_DIR]
[--inference-dir INFERENCE_DIR] [--device DEVICE]
[--verbose VERBOSE]
Synthesize with speedyspeech & parallel wavegan.
optional arguments:
-h, --help show this help message and exit
--speedyspeech-config SPEEDYSPEECH_CONFIG
config file for speedyspeech.
--speedyspeech-checkpoint SPEEDYSPEECH_CHECKPOINT
speedyspeech checkpoint to load.
--speedyspeech-stat SPEEDYSPEECH_STAT
mean and standard deviation used to normalize
spectrogram when training speedyspeech.
--pwg-config PWG_CONFIG
config file for parallelwavegan.
--pwg-checkpoint PWG_CHECKPOINT
parallel wavegan generator parameters to load.
--pwg-stat PWG_STAT mean and standard deviation used to normalize
spectrogram when training speedyspeech.
--phones-dict PHONES_DICT
phone vocabulary file.
--tones-dict TONES_DICT
tone vocabulary file.
--test-metadata TEST_METADATA
test metadata
--output-dir OUTPUT_DIR
output dir
--inference-dir INFERENCE_DIR
dir to save inference models
--device DEVICE device type to use
--verbose VERBOSE verbose
synthesize_e2e.sh
calls synthesize_e2e.py
, which can synthesize waveform from text file.
./synthesize_e2e.sh
usage: synthesize_e2e.py [-h] [--speedyspeech-config SPEEDYSPEECH_CONFIG]
[--speedyspeech-checkpoint SPEEDYSPEECH_CHECKPOINT]
[--speedyspeech-stat SPEEDYSPEECH_STAT]
[--pwg-config PWG_CONFIG]
[--pwg-checkpoint PWG_CHECKPOINT]
[--pwg-stat PWG_STAT] [--text TEXT]
[--phones-dict PHONES_DICT] [--tones-dict TONES_DICT]
[--output-dir OUTPUT_DIR]
[--inference-dir INFERENCE_DIR] [--device DEVICE]
[--verbose VERBOSE]
Synthesize with speedyspeech & parallel wavegan.
optional arguments:
-h, --help show this help message and exit
--speedyspeech-config SPEEDYSPEECH_CONFIG
config file for speedyspeech.
--speedyspeech-checkpoint SPEEDYSPEECH_CHECKPOINT
speedyspeech checkpoint to load.
--speedyspeech-stat SPEEDYSPEECH_STAT
mean and standard deviation used to normalize
spectrogram when training speedyspeech.
--pwg-config PWG_CONFIG
config file for parallelwavegan.
--pwg-checkpoint PWG_CHECKPOINT
parallel wavegan checkpoint to load.
--pwg-stat PWG_STAT mean and standard deviation used to normalize
spectrogram when training speedyspeech.
--text TEXT text to synthesize, a 'utt_id sentence' pair per line
--phones-dict PHONES_DICT
phone vocabulary file.
--tones-dict TONES_DICT
tone vocabulary file.
--output-dir OUTPUT_DIR
output dir
--inference-dir INFERENCE_DIR
dir to save inference models
--device DEVICE device type to use
--verbose VERBOSE verbose
--speedyspeech-config
,--speedyspeech-checkpoint
,--speedyspeech-stat
are arguments for speedyspeech, which correspond to the 3 files in the speedyspeech pretrained model.--pwg-config
,--pwg-checkpoint
,--pwg-stat
are arguments for parallel wavegan, which correspond to the 3 files in the parallel wavegan pretrained model.--text
is the text file, which contains sentences to synthesize.--output-dir
is the directory to save synthesized audio files.--inference-dir
is the directory to save exported model, which can be used with paddle infernece.--device
is the type of device to run synthesis, 'cpu' and 'gpu' are supported. 'gpu' is recommended for faster synthesis.--phones-dict
is the path of the phone vocabulary file.--tones-dict
is the path of the tone vocabulary file.
You can use the following scripts to synthesize for ../sentences.txt
using pretrained speedyspeech and parallel wavegan models.
FLAGS_allocator_strategy=naive_best_fit \
FLAGS_fraction_of_gpu_memory_to_use=0.01 \
python3 synthesize_e2e.py \
--speedyspeech-config=speedyspeech_nosil_baker_ckpt_0.5/default.yaml \
--speedyspeech-checkpoint=speedyspeech_nosil_baker_ckpt_0.5/snapshot_iter_11400.pdz \
--speedyspeech-stat=speedyspeech_nosil_baker_ckpt_0.5/feats_stats.npy \
--pwg-config=pwg_baker_ckpt_0.4/pwg_default.yaml \
--pwg-checkpoint=pwg_baker_ckpt_0.4/pwg_snapshot_iter_400000.pdz \
--pwg-stat=pwg_baker_ckpt_0.4/pwg_stats.npy \
--text=../sentences.txt \
--output-dir=exp/default/test_e2e \
--inference-dir=exp/default/inference \
--device="gpu" \
--phones-dict=speedyspeech_nosil_baker_ckpt_0.5/phone_id_map.txt \
--tones-dict=speedyspeech_nosil_baker_ckpt_0.5/tone_id_map.txt