kan-bayashi/ParallelWaveGAN
PyTorch implementation of neural vocoder models (Parallel WaveGAN, MelGAN, HiFi-GAN, StyleMelGAN) for real-time text-to-speech synthesis.
Not currently ranked — collecting fresh signals.
star history
This repository provides unofficial PyTorch implementations of several state-of-the-art non-autoregressive neural vocoder models for converting mel-spectrograms to audio waveforms. The models include Parallel WaveGAN, MelGAN, Multi-band MelGAN, HiFi-GAN, and StyleMelGAN. These vocoders are designed to work with TTS systems like ESPnet-TTS and can generate high-quality speech in real time when combined with a mel-spectrogram predictor.
Frequently asked
- What is kan-bayashi/ParallelWaveGAN?
- PyTorch implementation of neural vocoder models (Parallel WaveGAN, MelGAN, HiFi-GAN, StyleMelGAN) for real-time text-to-speech synthesis.
- Is ParallelWaveGAN open source?
- Yes — kan-bayashi/ParallelWaveGAN is open source, released under the MIT license.
- What language is ParallelWaveGAN written in?
- kan-bayashi/ParallelWaveGAN is primarily written in Jupyter Notebook.
- How popular is ParallelWaveGAN?
- kan-bayashi/ParallelWaveGAN has 1.6k stars on GitHub.
- Where can I find ParallelWaveGAN?
- kan-bayashi/ParallelWaveGAN is on GitHub at https://github.com/kan-bayashi/ParallelWaveGAN.