runtime-llamacpp-v0.1.1

KeygraphHQ/shannonruntime-llamacpp-v0.1.1Jun 21, 2026by LauraGPT

AI Summary

This release introduces prebuilt, self-contained binaries for running SenseVoice and other ASR models locally using the llama.cpp runtime. It eliminates the need for Python, builds, or PyTorch while offering strong performance in Chinese and Cantonese.

Key Highlights

Prebuilt binaries available for Linux (x64/arm64), macOS (arm64), and Windows (x64)
Support for SenseVoice, Paraformer, and Fun-ASR-Nano models
Built-in FSMN-VAD for voice activity detection
No Python, build, or PyTorch dependencies required
High accuracy with 8.01% CER (micro-avg) on SenseVoice

New Features

Local execution of SenseVoice, Paraformer, and Fun-ASR-Nano ASR models
Built-in FSMN-VAD integration
Cross-platform compatibility (Linux, macOS, Windows)
Zero-dependency runtime (no Python, torch, or compilation needed)
GGUF format model 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%.