runtime-llamacpp-v0.1.0
Kedreamix/Linly-Talker-Streamruntime-llamacpp-v0.1.0Jun 20, 2026by github-actions[bot]
AI Summary
Initial release of the prebuilt llama.cpp runtime binaries for FunASR, enabling on-device ASR capabilities for SenseVoice, Paraformer, and Fun-ASR-Nano models.
Key Highlights
- First release of llama.cpp runtime binaries
- Support for SenseVoice, Paraformer, and Fun-ASR-Nano
- Built-in FSMN-VAD for speech segmentation
- No Python or build required
New Features
- Prebuilt binaries
- SenseVoice support
- Paraformer support
- Fun-ASR-Nano support
- Built-in VAD
Full Release Notes
Prebuilt self-contained binaries for the FunASR llama.cpp / GGUF runtime — SenseVoice, Paraformer and Fun-ASR-Nano with built-in FSMN-VAD (a whisper.cpp-style on-device ASR, strong on Chinese). Get a model with `bash download-funasr-model.sh <sensevoice|paraformer|nano>`, then run `llama-funasr-cli` / `llama-funasr-sensevoice` / `llama-funasr-paraformer`. No Python, no build. Docs: runtime/llama.cpp/README.md