Skip to content

An implementation of WaveNet using PyTorch & PyTorch Lightning

License

Notifications You must be signed in to change notification settings

rpatrik96/pytorch-lightning-wavenet

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 

Repository files navigation

WaveNet in PyTorch

Author: Patrik Reizinger (MIT License)

This is an implementation of WaveNet in PyTorch using PyTorch Lightning.

Although there are several implementation, those are quite old. Thus, I have written a concise and clean version, which is well documented.

Training

For training, you need the PennTreeBank dataset, for which there are two wrapper classes in penn_dataset.py.

As PyTorch Lightning provides a super easy-to-use interface; thus, you only need to run the following:

python wavenet_lightning.py