Starstruk Logo MarkStarstruk

runtime-llamacpp-v0.1.1

Kedreamix/Linly-Talker-Streamruntime-llamacpp-v0.1.1Jun 20, 2026by github-actions[bot]

AI Summary

Provides prebuilt self-contained binaries for the llama.cpp runtime, allowing users to run SenseVoice, Paraformer, and Fun-ASR-Nano models with built-in VAD without Python dependencies.

Key Highlights

  • Prebuilt self-contained binaries for Fun-ASR-Nano, SenseVoice, and Paraformer
  • Built-in FSMN-VAD for on-device speech segmentation
  • No Python or build required to run models
  • Available for SenseVoice, Paraformer, and Nano variants

New Features

  • Prebuilt binaries
  • SenseVoice support
  • Paraformer support
  • Fun-ASR-Nano support
  • Built-in VAD

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