fatchord/WaveRNN

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

2190 stars · 686 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A PyTorch implementation of DeepMind's WaveRNN neural vocoder plus a Tacotron text-to-speech system, trained on LJSpeech. It supports training custom models and generating speech from text with pretrained weights.

Use cases

• synthesize speech from text with a neural vocoder
• train a WaveRNN vocoder on my own dataset
• run Tacotron TTS with pretrained LJSpeech models
• generate high-quality audio from mel spectrograms
• experiment with efficient neural audio synthesis

When to choose

• you want a lightweight, efficient neural vocoder in PyTorch
• you need a complete Tacotron + WaveRNN TTS pipeline with pretrained models
• you want to train a vocoder on LJSpeech or custom audio

When to avoid

• you need actively maintained code or modern TTS architectures
• you want production-grade, multi-speaker or multilingual TTS
• you lack a CUDA GPU for reasonable generation speed

Facets

library · maturity maintenance

tts machine-learning deep-learning audio-processing speech-processing machine-learning deep-learning python cross-platform wavernn vocoder tacotron speech-synthesis pytorch ljspeech neural-vocoder audio gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="fatchord/WaveRNN")