BetaRare
Soul-AILab/SoulX-FlashTalk
SoulX-FlashTalk is the first 14B model to achieve sub-second start-up latency (0.87s) while maintaining a real-time throughput of 32 FPS on an 8xH800 node.
- Owner
- Soul-AILab (organization)
- Stars
- Stars: 1,561
- Forks
- Forks: 146
- Language
- Python
- License
- Apache-2.0
- Created
- 2025
- Tier
- Beta (700 to 1,999 ★) What this tier means
More repos by Soul-AILab
All 8 repos by Soul-AILab- Soul-AILab/SoulX-PodcastStars: 3,640PythonRC
- Soul-AILab/SoulX-LiveActStars: 1,229PythonBeta
- Soul-AILab/SoulX-FlashHeadStars: 1,174PythonBeta
- Soul-AILab/SoulX-SingerStars: 1,046PythonBeta
- Soul-AILab/SoulX-DuplugStars: 331PythonAlpha
- Soul-AILab/SoulX-TranscriberStars: 305PythonAlpha
Nearby in Python
All Python repos- longcw/yolo2-pytorchStars: 1,561PythonBeta
- FinanceData/FinanceDataReaderStars: 1,561PythonBeta
- TgCatUB/catuserbotStars: 1,561PythonBeta
- wntrblm/noxStars: 1,560PythonBeta