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.

Files

file size notes
sensevoice-small-f16.gguf 470 MB recommended (f16 matmul weights)
sensevoice-small.gguf 936 MB f32 reference

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

Downloads last month
-
GGUF
Model size
0.2B params
Architecture
sensevoice-small
Hardware compatibility
Log In to add your hardware

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support