PrototypeCommon
HaujetZhao/Qwen3-TTS-GGUF
最极速的Qwen3-TTS推理方案。将 Qwen3-TTS 的 LLM 部分导出为 GGUF，用 llama.cpp 进行加速推理。后者支持 Vulkan 和 Cuda 加速。
- Owner
- HaujetZhao (personal account)
- Stars
- Stars: 192
- Forks
- Forks: 31
- Language
- Python
- License
- MIT
- Created
- 2026
- Tier
- Prototype (100 to 249 ★) What this tier means
More repos by HaujetZhao
All 13 repos by HaujetZhao- HaujetZhao/CapsWriter-OfflineStars: 7,062PythonStable
- HaujetZhao/QuickCutStars: 2,943PythonRC
- HaujetZhao/QuickHandStars: 476PythonAlpha
- HaujetZhao/CapsWriterStars: 465PythonAlpha
- HaujetZhao/color-traceStars: 249PythonPrototype
- HaujetZhao/Qwen3-ASR-GGUFStars: 246C++Prototype
Nearby in Python
All Python repos- Soniavasseur/Wallet-Risk-ScannerStars: 192PythonPrototype
- unclebob/crapperStars: 192PythonPrototype
- linkssy2/DarkwatchDarkerEditionStars: 192PythonPrototype
- peterbe/django-staticStars: 192PythonPrototype
- marcua/tweeqlStars: 192PythonPrototype
- Spacelog/SpacelogStars: 192PythonPrototype