Starstruk Logo MarkStarstruk

runtime-llamacpp-v0.1.1

krillinai/OpenCreatorruntime-llamacpp-v0.1.1Jun 21, 2026by LauraGPT

AI Summary

This release provides prebuilt, self-contained binaries for running SenseVoice and other FunASR models locally via the llama.cpp runtime. It includes built-in FSMN-VAD and supports Chinese and Cantonese, offering superior performance compared to whisper.cpp.

Key Highlights

  • Prebuilt binaries for Linux, macOS, and Windows (x64/arm64)
  • Runs SenseVoice, Paraformer, and Fun-ASR-Nano locally
  • Built-in FSMN-VAD for voice activity detection
  • Strong performance on Chinese and Cantonese (CER 8.01%)
  • whisper.cpp-style on-device ASR

New Features

  • Self-contained binary distribution (no Python/build/torch required)
  • Support for SenseVoice, Paraformer, and Fun-ASR-Nano models
  • Integrated FSMN-VAD for real-time audio processing
  • Cross-platform compatibility including Linux, macOS, and Windows
  • High accuracy on Chinese and Cantonese speech recognition

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%.