Store › model › Speech

VibeVoice-ASR-Streaming-7B-GGUF

Name: VibeVoice-ASR-Streaming-7B-GGUF
Author: audio-cpp

by audio-cpp · source Hugging Face · updated 2026-09-09

mit9.2 GB~12 GB RAMsource aliveunlabeled

VibeVoice ASR Streaming 7B GGUF for audio.cpp

Add to LogiShell Open in the web IDE

The button opens LogiShell with this card; nothing installs from a link by itself. Inside the app the install goes through lsh models install hf:audio-cpp/VibeVoice-ASR-Streaming-7B-GGUF and its progress lives in the Resource Center.

Source and license

Source: https://huggingface.co/audio-cpp/VibeVoice-ASR-Streaming-7B-GGUF
License: mit
Requirements: about 12 GB of RAM, 9.2 GB on disk (estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models). Runs with whisper.cpp.
Tags: gguf audio.cpp asr streaming speaker-attributed-transcription automatic-speech-recognition en zh es pt de ja ko fr ru it

Numbers

68,227 downloads on Hugging Face
3 likes
license mit
9.2 GB for vibevoice-asr-streaming-7b-q8_0.gguf
15,195 npm downloads a week for nodejs-whisper
latest nodejs-whisper@0.3.1

Numbers as of 2026-10-02 20:59 UTC, from the source API.

Summary

Summary not ready yet: the numbers are here, the text is not. It is written by the collector through the LogiShell model facade when a provider key is present.

Reviews

No reviews yet. Reviews are written inside LogiShell: open this card in the app.

Files

file	quant	size
`vibevoice-asr-streaming-7b-bf16.gguf`	BF16	16 GB
`vibevoice-asr-streaming-7b-q4_k.gguf`	Q4_K	5.5 GB
`vibevoice-asr-streaming-7b-q8_0.gguf`	Q8_0	9.2 GB

From the source README

VibeVoice ASR Streaming 7B GGUF for audio.cpp

This repository contains audio.cpp-native GGUF builds of
`microsoft/VibeVoice-ASR-Streaming-7B`.

Use with audio.cpp

Install the recommended Q8_0 package through the audio.cpp model manager:

python3 tools/model_manager_v2.py install vibevoice_asr_streaming_7b_q8_0

Run offline ASR:

build/debug/bin/audiocpp_cli \
  --task asr \
  --family vibevoice_asr_streaming \
  --model models/VibeVoice-ASR-Streaming-7B-GGUF/vibevoice-asr-streaming-7b-q8_0.gguf \
  --backend cuda \
  --threads 8 \
  --audio input.wav \
  --text-out transcript.txt \
  --metrics \
  --log

Run the server with the model loaded:

{
  "host": "127.0.0.1",
  "port": 8080,
  "backend": "cuda",
  "threads": 8,
  "models": [
    {
      "id": "vibevoice-streaming-7b",
      "family": "vibevoice_asr_streaming",
      "path": "models/VibeVoice-ASR-Streaming-7B-GGUF/vibevoice-asr-streaming-7b-q8_0.gguf",
      "task": "asr",
      "mode": "streaming"
    }
  ]
}

Then start the server:

build/debug/bin/audiocpp_server --config server.json --log

For live streaming, send 16 kHz mono signed 16-bit PCM to the live endpoint:

Card id model:hf:audio-cpp/VibeVoice-ASR-Streaming-7B-GGUF · collected 2026-10-02 20:59 UTC · JSON