SenseVoiceSmall · GGUF (FunASR llama.cpp runtime)

GGUF build of SenseVoiceSmall (SAN-M encoder + CTC) for the zero-Python, CPU/edge FunASR llama.cpp runtime — multilingual ASR with language / emotion / event tags, ~20× real-time on CPU.

Get it running (no Python, no build)

These are GGUF weights for the FunASR llama.cpp runtime — a whisper.cpp-style, single self-contained binary for CPU / edge. Grab a prebuilt binary, then fetch this model and run:

• Prebuilt binaries (Linux / macOS / Windows) → GitHub Releases (tag runtime-llamacpp-v*)
• One-page quickstart & benchmarks → funasr.com/llama-cpp

bash download-funasr-model.sh sensevoice ./gguf
llama-funasr-sensevoice -m ./gguf/sensevoice-small-q8.gguf --vad ./gguf/fsmn-vad.gguf -a audio.wav
# → 欢迎大家来体验达摩院推出的语音识别模型

Files

Usage

The binary prints transcription text directly (no Python detok). --ids for raw ids / --keep-tags for the lang/emotion tags.

# 1. get the VAD too (for long audio): huggingface-cli download FunAudioLLM/fsmn-vad-GGUF
llama-funasr-sensevoice -m sensevoice-small-f16.gguf -a audio.wav --vad fsmn-vad.gguf

On CPU (8 threads) this reaches 8.01 % CER on the 184-clip Mandarin benchmark — vs whisper.cpp 22–31 %. See the benchmark.

Links

• 🧩 Runtime & build: SenseVoice · runtime/llama.cpp — ⭐ Star SenseVoice!
• Source model: FunAudioLLM/SenseVoiceSmall