runtime-llamacpp-v0.1.2

Billionmail/BillionMailruntime-llamacpp-v0.1.2Jun 21, 2026by github-actions[bot]

AI Summary

Prebuilt self-contained binaries for the FunASR llama.cpp runtime, enabling on-device ASR without Python.

Key Highlights

  • No Python or build required
  • Supports SenseVoice, Paraformer, and Fun-ASR-Nano
  • Built-in FSMN-VAD for Chinese speech recognition

New Features

  • Prebuilt binaries
  • llama.cpp runtime support
  • FSMN-VAD support

Full Release Notes

Prebuilt self-contained binaries for the FunASR llama.cpp / GGUF runtime — SenseVoice, Paraformer and Fun-ASR-Nano with built-in FSMN-VAD (a whisper.cpp-style on-device ASR, strong on Chinese). Get a model with `bash download-funasr-model.sh <sensevoice|paraformer|nano>`, then run `llama-funasr-cli` / `llama-funasr-sensevoice` / `llama-funasr-paraformer`. No Python, no build. Docs: runtime/llama.cpp/README.md