https://github.com/vincentherrmann/pytorch-wavenet

An implementation of WaveNet with fast generation
https://github.com/vincentherrmann/pytorch-wavenet

Last synced: about 2 months ago
JSON representation

An implementation of WaveNet with fast generation

• Host: GitHub
• URL: https://github.com/vincentherrmann/pytorch-wavenet
• Owner: vincentherrmann
• License: mit
• Created: 2017-04-19T21:29:22.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2020-09-17T15:50:34.000Z (over 4 years ago)
• Last Synced: 2024-08-04T00:11:32.151Z (5 months ago)
• Language: Jupyter Notebook
• Homepage:
• Size: 263 MB
• Stars: 956
• Watchers: 30
• Forks: 225
• Open Issues: 31
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• Awesome-pytorch-list-CNVersion - pytorch-wavenet
• Awesome-pytorch-list - pytorch-wavenet

README

        
# pytorch-wavenet

This is an implementation of the WaveNet architecture, as described in the [original paper](https://arxiv.org/abs/1609.03499).

## Features

- Automatic creation of a dataset (training and validation/test set) from all sound files (.wav, .aiff, .mp3) in a directory

- Efficient multithreaded data loading

- Logging to TensorBoard (Training loss, validation loss, validation accuracy, parameter and gradient histograms, generated samples)

- Fast generation, as introduced [here](https://arxiv.org/abs/1611.09482)

## Requirements

- python 3

- pytorch 0.3

- numpy

- librosa

- jupyter

- tensorflow for TensorBoard logging

## Demo

For an introduction on how to use this model, take a look at the [WaveNet demo notebook](https://github.com/vincentherrmann/pytorch-wavenet/blob/master/WaveNet_demo.ipynb). 

You can find audio clips generated by a simple trained model in the [generated samples directory](https://github.com/vincentherrmann/pytorch-wavenet/tree/master/generated_samples)