hifi-gan is an open-source speech and audio tool published on GitHub by jik876. The repository has collected 2.4k stars and 560 forks; the latest push was in July 2024. Related topics: deep-learning, gan and hifi-gan.
“HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis”
— jik876, project description on GitHub
Details
| Category | Speech & Audio |
|---|---|
| GitHub stars | 2,377 |
| Forks | 560 |
| Language | Python |
| License | MIT |
| Last updated | |
| Owner | jik876 |
| Repository | jik876/hifi-gan |
Tags
deep-learningganhifi-ganpytorchspeech-synthesistext-to-speechttsvocoder
Repository facts from the GitHub public API, refreshed October 18, 2026. The quoted tagline is written by the project owner; the summary above is generated from public facts.