ivanvovk/WaveGrad
PyTorch implementation of Google Brain's WaveGrad diffusion vocoder for high-fidelity text-to-speech synthesis.
Not currently ranked — collecting fresh signals.
star history
This repository provides a full implementation of WaveGrad, a probabilistic vocoder that uses a diffusion probabilistic model to generate high-quality speech waveforms from mel-spectrograms. The implementation includes support for multi-iteration inference (6 to 1000 iterations), mixed-precision and distributed training, parallel grid search for optimal noise schedules, and pretrained checkpoints for the LJSpeech dataset.
Frequently asked
- What is ivanvovk/WaveGrad?
- PyTorch implementation of Google Brain's WaveGrad diffusion vocoder for high-fidelity text-to-speech synthesis.
- Is WaveGrad open source?
- Yes — ivanvovk/WaveGrad is open source, released under the BSD-3-Clause license.
- What language is WaveGrad written in?
- ivanvovk/WaveGrad is primarily written in Jupyter Notebook.
- How popular is WaveGrad?
- ivanvovk/WaveGrad has 409 stars on GitHub.
- Where can I find WaveGrad?
- ivanvovk/WaveGrad is on GitHub at https://github.com/ivanvovk/WaveGrad.