Sealbook
Sealbook / Open source / Machine learning & data science

jik876/hifi-gan

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

deep-learningganhifi-ganpytorchspeech-synthesistext-to-speechttsvocoder
GitHub β†—

License & maintenance

MIT is a permissive license: free to use commercially with attribution.

Last code push 2 years ago.

Similar projects

RepositoryStarsLanguageLicenseActivity
1OpenBMB/VoxCPMVoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloningβ˜… 39.5kPythonApache-2.0Active
2babysor/MockingBirdπŸš€Clone a voice in 5 seconds to generate arbitrary speech in real-timeβ˜… 36.9kPythonOtherSlowing
3labmlai/annotated_deep_learning_paper_implementationsπŸ§‘β€πŸ« 60+ Implementations/tutorials of deep learning papers with side-by-side notes πŸ“; including transformers (original, xl, switch, feedback,β˜… 67.6kPythonMITSlowing
4CorentinJ/Real-Time-Voice-CloningClone a voice in 5 seconds to generate arbitrary speech in real-timeβ˜… 60.2kPythonOtherSlowing
5TencentARC/GFPGANGFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.β˜… 37.7kPythonOtherStale
6Mikoto10032/DeepLearningζ·±εΊ¦ε­¦δΉ ε…₯门教程, δΌ˜η§€ζ–‡η« , Deep Learning Tutorialβ˜… 17.8kJupyter NotebookApache-2.0Stale
7rany2/edge-ttsUse Microsoft Edge's online text-to-speech service from Python WITHOUT needing Microsoft Edgeβ˜… 12.3kPythonOtherActive
8rhasspy/piperA fast, local neural text to speech systemβ˜… 11.3kC++MITArchived