CoolFace
Modelpublic

FunAudioLLM/SenseVoiceSmall-GGUF-audiocpp

sourceHugging Faceapache-2.0updated 1mo agoView on Hugging Face
4likes27kdownloads
Model Card

SenseVoiceSmall GGUF for audio.cpp

This repository contains a self-contained Q80 export of [SenseVoiceSmall](https://huggingface.co/FunAudioLLM/SenseVoiceSmall) for the [audio.cpp](https://github.com/0xShug0/audio.cpp) spec-backed runtime. The GGUF embeds the `senseasr schema-v1 model specification, SenseVoice metadata, SentencePiece vocabulary, CMVN tensors, and 919 model tensors. It loads directly without --model-spec-override`.

File

FileSizeSHA256
sensevoice-small-q8-audiocpp-v1.gguf254,211,200 bytes4dedf169f625437fb336f2959674f399819729a765e184128c0e25a6e16ff0ec

Usage

bash
audiocpp_cli --task asr --family sense_asr \
  --model sensevoice-small-q8-audiocpp-v1.gguf \
  --backend cpu --audio zh.wav \
  --request-option audio_chunk_mode=none

The integration is tracked in audio.cpp pull request #218.

Reproducibility

The model was exported from FunAudioLLM/SenseVoiceSmall revision 3847d57b6bdf2dd8875cb1508d2af43d80a16bf7 with the official runtime/llama.cpp/export_sensevoice_gguf.py exporter using --wtype q8_0 and --model-spec.

On the official 5.616-second Mandarin sample, direct CPU inference produced:

text
开饭时间早上9点至下午5点。

The text exactly matched the original Q8 model loaded with an external model specification.

Links