parallel-wavegan 0.2.1.post3

Parallel WaveGAN implementation

Parallel WaveGAN implementation with Pytorch

This repository provides UNOFFICIAL Parallel WaveGAN implementation with Pytorch.

The goal of this repository is to provide the real-time neural vocoder which is compatible with ESPnet-TTS.

Source of the figure: https://arxiv.org/pdf/1910.11480.pdf

Requirements

This repository is tested on Ubuntu 16.04 with a GPU Titan V.

• Python 3.6+
• Cuda 10.0
• CuDNN 7+

All of the codes are tested on Pytorch 1.0.1, 1.1, 1.2, and 1.3.

Setup

You can select the installation method from two alternatives.

A. Use pip

$ git clone https://github.com/kan-bayashi/ParallelWaveGAN.git
$ cd ParallelWaveGAN
$ pip install -e .

B. Make virtualenv

$ git clone https://github.com/kan-bayashi/ParallelWaveGAN.git
$ cd ParallelWaveGAN/tools
$ make
$ source venv/bin/activate

Run

This repository provides Kaldi-style recipes, as the same as ESPnet.
Currently, three recipes are supported.

• CMU Arctic: English speakers
• LJSpeech: English female speaker
• JSUT: Japanese female speaker
• CSMSC: Mandarin female speaker

To run the recipe, please follow the below instruction.

# Let us move on the recipe directory
$ cd egs/ljspeech/voc1

# Run the recipe from scratch
$ ./run.sh

# You can select the stage to start and stop
$ ./run.sh --stage 2 --stop_stage 2

All of the hyperparameters is written in a single yaml format configuration file.
Please check this example in ljspeech recipe.

The training requires ~3 days with a single GPU (TITAN V).
The speed of the training is 0.5 seconds per an iteration, in total ~ 200000 sec (= 2.31 days).
You can monitor the training progress via tensorboard.

$ tensorboard --logdir exp

The decoding speed is RTF = 0.015 with TITAN V, much faster than the real-time.

[decode]: 100%|██████████| 250/250 [00:30<00:00,  8.31it/s, RTF=0.0156]
2019-11-03 09:07:40,480 (decode:127) INFO: finished generation of 250 utterances (RTF = 0.016).

Results

You can listen to the samples and download pretrained models at our google drive.

The training is still on going. Please check the latest progress at https://github.com/kan-bayashi/ParallelWaveGAN/issues/1.

References

• Parallel WaveGAN
• r9y9/wavenet_vocoder
• LiyuanLucasLiu/RAdam

Acknowledgement

The author would like to thank Ryuichi Yamamoto (@r9y9) for his great repository, paper and valuable discussions.

Author

Tomoki Hayashi (@kan-bayashi)
E-mail: hayashi.tomoki<at>g.sp.m.is.nagoya-u.ac.jp