vhghorecha / melgan_inference

Melgan the vocoder. Making more of a package like structure for easier inference

Multi-band MelGAN and Full band MelGAN

Unofficial PyTorch implementation of Multi-Band MelGAN paper. This implementation uses Seungwon Park's MelGAN repo as a base and PQMF filters implementation from this repo.
MelGAN :
Multi-band MelGAN:

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]
  • cp config/default.yaml config/config.yaml and then edit config.yaml
  • Write down the root path of train/validation files to 2nd/3rd line.
  • Each path should contain pairs of *.wav with corresponding (preprocessed) *.mel file.
  • The data loader parses list of files within the path recursively.
  • For Multi-Band training use config/mb_melgan config file in -c
• tensorboard --logdir logs/

Pretrained model

Check out here.

Inference

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

Results

References

• Multi-band MelGAN
• MelGAN
• Pytorch implementation of melgan
• Official implementation of melgan
• Multi, Full-band melgan implementation
• Nvidia's pre-processing
• WaveRNN

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
• Official MelGAN implementation by original authors
• Reproduction of MelGAN - NeurIPS 2019 Reproducibility Challenge (Ablation Track) by Yifei Zhao, Yichao Yang, and Yang Gao
  • "replacing the average pooling layer with max pooling layer and replacing reflection padding with replication padding improves the performance significantly, while combining them produces worse results"