runtime-llamacpp-v0.1.0

datalab-to/markerruntime-llamacpp-v0.1.0Jun 20, 2026by github-actions[bot]

AI Summary

Initial release of FunASR llama.cpp runtime binaries. Provides on-device ASR capabilities for Chinese-focused models with built-in speech segmentation.

Key Highlights

  • First release of llama.cpp runtime binaries
  • Self-contained execution environment
  • Chinese-optimized ASR models
  • No build dependencies required
  • One-command setup and execution

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 FSMN-VAD for speech segmentation

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