Starstruk Logo MarkStarstruk

runtime-llamacpp-v0.1.1

tursodatabase/tursoruntime-llamacpp-v0.1.1Jun 21, 2026by LauraGPT

AI Summary

The initial release of the FunASR llama.cpp runtime, providing prebuilt binaries for running local speech recognition (SenseVoice) without the need for Python or Torch.

Key Highlights

  • Prebuilt, self-contained binaries for Linux, macOS, and Windows.
  • No Python or Torch required.
  • Built-in FSMN-VAD and whisper.cpp-style on-device ASR.
  • Strong performance specifically for Chinese and Cantonese.

New Features

  • Prebuilt self-contained binaries
  • Built-in FSMN-VAD
  • whisper.cpp-style on-device ASR
  • SenseVoice and Fun-ASR-Nano support

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%.