runtime-llamacpp-v0.1.1

Tencent/WeKnoraruntime-llamacpp-v0.1.1Jun 21, 2026by LauraGPT

AI Summary

A runtime release providing prebuilt binaries to run SenseVoice ASR locally using llama.cpp technology.

Key Highlights

  • Includes built-in FSMN-VAD and whisper.cpp-style on-device ASR
  • Supports Chinese and Cantonese languages
  • Offers binaries for Linux, macOS, and Windows without requiring Python or build tools

New Features

  • SenseVoice ASR support
  • FSMN-VAD
  • Cross-platform binaries

Full Release Notes

Prebuilt, self-contained binaries to run **SenseVoice** (and Paraformer / Fun-ASR-Nano) locally with the FunASR llama.cpp / GGUF runtime — built-in FSMN-VAD, whisper.cpp-style on-device ASR, strong on Chinese & Cantonese.

```bash
bash download-funasr-model.sh sensevoice ./gguf
llama-funasr-sensevoice -m ./gguf/SenseVoiceSmall-f16.gguf --vad ./gguf/fsmn-vad.gguf -a audio.wav
```

No Python, no build, no torch. Binaries for Linux (x64/arm64), macOS (arm64), Windows (x64). Docs: `runtime/llama.cpp/README.md`. CER (micro-avg): SenseVoice 8.01% vs whisper.cpp small 22%.