runtime-llamacpp-v0.1.1

datalab-to/markerruntime-llamacpp-v0.1.1Jun 20, 2026by github-actions[bot]

AI Summary

Prebuilt self-contained binaries for FunASR llama.cpp runtime. Provides on-device ASR capabilities for SenseVoice, Paraformer, and Fun-ASR-Nano models with built-in FSMN-VAD.

Key Highlights

  • Self-contained binaries requiring no Python or build
  • Support for SenseVoice, Paraformer, and Fun-ASR-Nano models
  • Built-in FSMN-VAD for speech segmentation
  • One-command model download and execution
  • No Python runtime required

New Features

  • llama-funasr-cli command line interface
  • llama-funasr-sensevoice specialized command
  • llama-funasr-paraformer specialized command
  • bash download-funasr-model.sh script
  • Built-in VAD for speech activity detection

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