batikim09 / melgan

Unofficial PyTorch implementation of MelGAN vocoder (Training in progress)

MelGAN

Unofficial PyTorch implementation of MelGAN vocoder (training in progress)

Key Features

• MelGAN is lighter, faster, and better at generalizing to unseen speakers than WaveGlow.
• This repository use identical mel-spectrogram function from NVIDIA/tacotron2, so this can be directly used to convert output from NVIDIA's tacotron2 into raw-audio.
• TODO: Planning to publish pretrained model via PyTorch Hub.

Prerequisites

Tested on Python 3.6

pip install -r requirements.txt

Prepare Dataset

• Download dataset for training. This can be any wav files with sample rate 22050Hz. (e.g. LJSpeech was used in paper)
• preprocess: python preprocess.py -c config/default.yaml -d [data's root path]
• Edit configuration yaml file

Train & Tensorboard

• python trainer.py -c [config yaml file] -n [name of the run]
• tensorboard --logdir logs/

Inference

• python inference.py -p [checkpoint path] -i [input mel path]

Results

See audio samples at: http://swpark.me/melgan/.

The loss curve of G/D may look weird at first. TODO: add tensorboard image here

Implementation Authors

• Seungwon Park @ MINDsLab Inc. ([e-mail], [e-mail])
• Myunchul Joe @ MINDsLab Inc.
• Rishikesh @ DeepSync Technologies Pvt Ltd.

License

BSD 3-Clause License.

• utils/stft.py by Prem Seetharaman (BSD 3-Clause License)
• datasets/mel2samp.py from https://github.com/NVIDIA/waveglow (BSD 3-Clause License)
• utils/hparams.py from https://github.com/HarryVolek/PyTorch_Speaker_Verification (No License specified)

Useful resources

• How to Train a GAN? Tips and tricks to make GANs work by Soumith Chintala
• jaywalnut310/MelGAN-Pytorch by Jaehyeon Kim