Python · Apache-2.0
QwenAudio/CosyVoice
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
★ 24.3k
Stars
2.8k forks · 645 open issues
+16/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
39.5
Momentum / 100
see the breakdown below
2y ago
Created
last push 5mo ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 23.7 | +16/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 1.7 | last week ran 1.11× the monthly pace |
| Freshness | 15 | 1.4 | last push 5mo ago; decays to zero at 180 days |
| Scale | 15 | 12.7 | 24.3k stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 39.5 | sum of the above |
Detail
| Topics | audio-generationcantonesechatbotchatgptchinesecosyvoicecross-lingualenglishfine-grainedfine-tuninggpt-4ojapanesekoreanmulti-lingualnatural-language-generationpythontext-to-speechttsvoice-cloning |
| Matched on | LLM & Inference (fine-tuning) |
| Short window | +115 stars over 7 days = 16.4/day |
| Long window | +384 stars over 26 days = 14.8/day |
| Lifetime average | 28.41 stars/day over 855 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |