runtime-llamacpp-v0.1.1

zaidmukaddam/sciraruntime-llamacpp-v0.1.1Jun 21, 2026by LauraGPT

AI Summary

The initial release of the FunASR llama.cpp runtime, providing prebuilt binaries to run SenseVoice, Paraformer, and Fun-ASR-Nano locally without requiring Python or build tools.

Key Highlights

First release of the prebuilt runtime
Strong performance on Chinese & Cantonese with 8.01% CER (micro-avg)
No Python, no build, and no torch required
Supports multiple OS platforms (Linux, macOS, Windows)

New Features

Prebuilt binaries for SenseVoice, Paraformer, and Fun-ASR-Nano
Built-in FSMN-VAD and whisper.cpp-style on-device ASR

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%.