Starstruk Logo MarkStarstruk

runtime-llamacpp-v0.1.1

netbirdio/netbirdruntime-llamacpp-v0.1.1Jun 21, 2026by LauraGPT

AI Summary

A prebuilt, self-contained binary release of the FunASR llama.cpp runtime designed to run SenseVoice and other ASR models locally without requiring Python, build tools, or PyTorch.

Key Highlights

  • Cross-platform support for Linux, macOS, and Windows
  • No Python, build, or PyTorch dependencies required
  • Built-in FSMN-VAD for voice activity detection
  • High accuracy (8.01% CER) for SenseVoice
  • Support for GGUF model format

New Features

  • Local SenseVoice ASR execution
  • Paraformer and Fun-ASR-Nano model support
  • Voice activity detection (VAD)
  • Self-contained binaries
  • GGUF model format 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%.