# vincentherrmann/pytorch-wavenet

An implementation of WaveNet with fast generation

Repository: https://github.com/vincentherrmann/pytorch-wavenet
Canonical: https://ross.abutalabs.com/products/pytorch-wavenet
Language: Jupyter Notebook
License: MIT
License Family: permissive
Last push: 2020-09-17T15:50:34+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3423, "days_push": 2176, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1029, forks 231 (observed 2026-08-28T04:03:17.652797+00:00)

## What it is
A PyTorch implementation of the WaveNet neural audio generation architecture with fast generation support. It includes dataset creation from audio files, multithreaded data loading, and TensorBoard logging.

## Use cases
- generate audio with a wavenet model in pytorch
- train a wavenet on my own wav files
- fast wavenet audio sample generation
- learn how wavenet works with a demo notebook
- implement autoregressive audio synthesis

## When to choose
- you want a simple, readable WaveNet implementation in PyTorch
- you need fast generation via the fast Wavenet technique
- you want a Jupyter-based demo to learn from

## When to avoid
- you need production-grade, actively maintained audio synthesis
- you require modern PyTorch versions or recent Python support
- you need text-to-speech with pretrained voices

## Facets
- artifact type: library
- maturity: maintenance
- function: deep-learning, audio-processing, machine-learning
- domain: deep-learning, machine-learning
- platform: python
- tags: wavenet, pytorch, audio-generation, neural-audio, research-code, audio

## Member repositories
- vincentherrmann/pytorch-wavenet (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:17.652797+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:07:41.602858+00:00, confidence not recorded.
  - readme: https://github.com/vincentherrmann/pytorch-wavenet (fetched 2026-08-28T04:03:17.652797+00:00, sha 23c4319cdb02)
- Data as of 2026-08-30T08:39:29.467469+00:00.