You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
PaddleSpeech/examples/csmsc/tts2
TianYuan 7d3985bff9
update table
3 years ago
..
conf refactor parakeet examples 3 years ago
local change nprocs to ngpu, add aishell3/voc1 3 years ago
README.md update table 3 years ago
path.sh merge deepspeech, parakeet and text_processing into paddlespeech 3 years ago
run.sh fix readme 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 own MFA model reference to use_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

  1. source path.
  2. preprocess the dataset.
  3. train the model.
  4. synthesize wavs.
    • synthesize waveform from metadata.jsonl.
    • synthesize waveform from text file.
  5. inference using 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 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.

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] [--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.
  --ngpu NGPU           if ngpu == 0, use cpu.
  --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.
  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 save 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.
  6. --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] [--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] [--ngpu NGPU]
                     [--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
  --ngpu NGPU           if ngpu == 0, use cpu.
  --verbose VERBOSE     verbose

./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] [--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] [--verbose VERBOSE]
                         [--ngpu NGPU]

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
  --verbose VERBOSE     verbose
  --ngpu NGPU           if ngpu == 0, use cpu.
  1. --speedyspeech-config, --speedyspeech-checkpoint, --speedyspeech-stat are arguments for speedyspeech, which correspond to the 3 files in the speedyspeech pretrained model.
  2. --pwg-config, --pwg-checkpoint, --pwg-stat are arguments for parallel wavegan, which correspond to the 3 files in the parallel wavegan pretrained model.
  3. --text is the text file, which contains sentences to synthesize.
  4. --output-dir is the directory to save synthesized audio files.
  5. --inference-dir is the directory to save exported model, which can be used with paddle infernece.
  6. --ngpu is the number of gpus to use, if ngpu == 0, use cpu.
  7. --phones-dict is the path of the phone vocabulary file.
  8. --tones-dict is the path of the tone vocabulary file.

Inferencing

After Synthesize, 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.

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 ${BIN_DIR}/synthesize_e2e.py \
  --speedyspeech-config=speedyspeech_nosil_baker_ckpt_0.5/default.yaml \
  --speedyspeech-checkpoint=speedyspeech_nosil_baker_ckpt_0.5/snapshot_iter_11400.pdz \
  --speedyspeech-stat=speedyspeech_nosil_baker_ckpt_0.5/feats_stats.npy \
  --pwg-config=pwg_baker_ckpt_0.4/pwg_default.yaml \
  --pwg-checkpoint=pwg_baker_ckpt_0.4/pwg_snapshot_iter_400000.pdz \
  --pwg-stat=pwg_baker_ckpt_0.4/pwg_stats.npy \
  --text=${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