runtime-llamacpp-v0.1.2

QuentinFuxa/WhisperLiveKitruntime-llamacpp-v0.1.2Jun 21, 2026by LauraGPT

AI Summary

Release of prebuilt binaries for local ASR using llama.cpp, featuring q8 GGUF models for reduced size without accuracy loss.

Key Highlights

Prebuilt self-contained binaries for SenseVoice and Paraformer
q8 GGUF models are ~half the size of f16 with same accuracy
Built-in FSMN-VAD and whisper.cpp-style on-device ASR
No Python dependency required; cross-platform support

New Features

q8 GGUF models support (half size, same accuracy)

Full Release Notes

Prebuilt self-contained binaries for running **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.

**New:** q8 GGUF models are ~half the size of f16 with the same accuracy.

```bash
bash download-funasr-model.sh sensevoice ./gguf
llama-funasr-sensevoice -m ./gguf/sensevoice-small-q8.gguf --vad ./gguf/fsmn-vad.gguf -a audio.wav
```

No Python, no build. Linux (x64/arm64), macOS (arm64), Windows (x64). Docs: `runtime/llama.cpp/README.md`.