Starstruk Logo MarkStarstruk

runtime-llamacpp-v0.1.1

QwenAudio/SenseVoiceruntime-llamacpp-v0.1.1Jun 21, 2026by LauraGPT

AI Summary

Prebuilt, self-contained binaries for running SenseVoice locally without Python, torch, or local compilation. This release emphasizes zero-dependency operation and provides performance benchmarks against whisper.cpp.

Key Highlights

  • No Python, no build, no torch required.
  • Provides CER (micro-avg) benchmark comparing SenseVoice (8.01%) to whisper.cpp small (22%).
  • Supports Linux (x64/arm64), macOS (arm64), and Windows (x64).
  • Whisper.cpp-style on-device ASR.

New Features

  • Zero-dependency binaries
  • Performance benchmarks
  • Multi-platform 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%.