Starstruk Logo MarkStarstruk

runtime-llamacpp-v0.1.2

CvHadesSun/FLame2SMPLXruntime-llamacpp-v0.1.2Jun 21, 2026by LauraGPT

AI Summary

This release introduces prebuilt self-contained binaries for running SenseVoice locally with built-in FSMN-VAD and whisper.cpp-style ASR, supporting q8 GGUF models.

Key Highlights

  • Run SenseVoice locally with built-in FSMN-VAD
  • whisper.cpp-style on-device ASR
  • Strong performance on Chinese & Cantonese
  • q8 GGUF models are ~half the size of f16 with same accuracy

New Features

  • No Python, no build required
  • Support for Linux (x64/arm64), macOS (arm64), Windows (x64)
  • Built-in FSMN-VAD for segmented workflows

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`.