PrototypeCommon
HaujetZhao/Qwen3-ASR-GGUF
将 Qwen3-ASR 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: 246
- Forks
- Forks: 37
- Language
- C++
- License
- None
- 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-TTS-GGUFStars: 192PythonPrototype
Nearby in C++
All C++ repos- chiaki-ng/akiraStars: 246C++Prototype
- p3d-project/persona-3-dualStars: 246C++Prototype
- google-ai-edge/ml-driftStars: 246C++Prototype
- wallix/redemptionStars: 246C++Prototype
- adafruit/Adafruit-BMP085-LibraryStars: 246C++Prototype
- bloomberg/blpapi-nodeStars: 246C++Prototype