Meta-TTS: Meta-Learning for Few-shot SpeakerAdaptive Text-to-Speech

This repository is the official implementation of "Meta-TTS: Meta-Learning for Few-shot SpeakerAdaptive Text-to-Speech".

multi-task learning	meta learning

Meta-TTS

Requirements

This is how I build my environment, which is not exactly needed to be the same:

• Sign up for Comet.ml, find out your workspace and API key via www.comet.ml/api/my/settings and fill them in config/comet.py. Comet logger is used throughout train/val/test stages.
  • Check my training logs here.
• [Optional] Install pyenv for Python version control, change to Python 3.8.6.

# After download and install pyenv:
pyenv install 3.8.6
pyenv local 3.8.6

• [Optional] Install pyenv-virtualenv as a plugin of pyenv for clean virtual environment.

# After install pyenv-virtualenv
pyenv virtualenv meta-tts
pyenv activate meta-tts

• Install requirements:

pip install -r requirements.txt

Proprocessing

First, download LibriTTS and VCTK, then change the paths in config/LibriTTS/preprocess.yaml and config/VCTK/preprocess.yaml, then run

python3 prepare_align.py config/LibriTTS/preprocess.yaml
python3 prepare_align.py config/VCTK/preprocess.yaml

for some preparations.

Alignments of LibriTTS is provided here, and the alignments of VCTK is provided here. You have to unzip the files into preprocessed_data/LibriTTS/TextGrid/ and preprocessed_data/VCTK/TextGrid/.

Then run the preprocessing script:

python3 preprocess.py config/LibriTTS/preprocess.yaml

# Copy stats from LibriTTS to VCTK to keep pitch/energy normalization the same shift and bias.
cp preprocessed_data/LibriTTS/stats.json preprocessed_data/VCTK/

python3 preprocess.py config/VCTK/preprocess.yaml

Training

To train the models in the paper, run this command:

python3 main.py -s train \
                -p config/preprocess/<corpus>.yaml \
                -m config/model/base.yaml \
                -t config/train/base.yaml config/train/<corpus>.yaml \
                -a config/algorithm/<algorithm>.yaml

To reproduce, please use 8 V100 GPUs for meta models, and 1 V100 GPU for baseline models, or else you might need to tune gradient accumulation step (grad_acc_step) setting in config/train/base.yaml to get the correct meta batch size. Note that each GPU has its own random seed, so even the meta batch size is the same, different number of GPUs is equivalent to different random seed.

After training, you can find your checkpoints under output/ckpt/<corpus>/<project_name>/<experiment_key>/checkpoints/, where the project name is set in config/comet.py.

To inference the models, run:

python3 main.py -s test \
                -p config/preprocess/<corpus>.yaml \
                -m config/model/base.yaml \
                -t config/train/base.yaml config/train/<corpus>.yaml \
                -a config/algorithm/<algorithm>.yaml \
                -e <experiment_key> -c <checkpoint_file_name>

and the results would be under output/result/<corpus>/<experiment_key>/<algorithm>/.

Evaluation

Note: The evaluation code is not well-refactored yet.

cd evaluation/ and check README.md

Pre-trained Models

Note: The checkpoints are with older version, might not capatiable with the current code. We would fix the problem in the future.

Since our codes are using Comet logger, you might need to create a dummy experiment by running:

from comet_ml import Experiment
experiment = Experiment()

then put the checkpoint files under output/ckpt/LibriTTS/<project_name>/<experiment_key>/checkpoints/.

You can download pretrained models here.

Results

Corpus	LibriTTS	VCTK
Speaker Similarity
Speaker Verification
Synthesized Speech Detection