fatchord/WaveRNN
A PyTorch implementation of Deepmind's WaveRNN neural vocoder paired with Tacotron for neural text-to-speech synthesis.
Not currently ranked — collecting fresh signals.
star history
This repository provides a complete TTS pipeline using two deep learning models: Tacotron converts text into mel-spectrograms, and WaveRNN generates raw audio waveforms from those spectrograms using efficient neural synthesis. Users can train custom models on datasets like LJSpeech, generate speech via a quick-start script, or integrate the vocoder separately for inference.
Frequently asked
- What is fatchord/WaveRNN?
- A PyTorch implementation of Deepmind's WaveRNN neural vocoder paired with Tacotron for neural text-to-speech synthesis.
- Is WaveRNN open source?
- Yes — fatchord/WaveRNN is open source, released under the MIT license.
- What language is WaveRNN written in?
- fatchord/WaveRNN is primarily written in Python.
- How popular is WaveRNN?
- fatchord/WaveRNN has 2.2k stars on GitHub.
- Where can I find WaveRNN?
- fatchord/WaveRNN is on GitHub at https://github.com/fatchord/WaveRNN.