Instructions to use microsoft/VibeVoice-ASR-BitNet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use microsoft/VibeVoice-ASR-BitNet with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="microsoft/VibeVoice-ASR-BitNet",
	filename="vibeasr-lm-i2_s-embed-q6_k.gguf",
)

llm.create_chat_completion(
	messages = "\"sample1.flac\""
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use microsoft/VibeVoice-ASR-BitNet with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf microsoft/VibeVoice-ASR-BitNet:Q6_K
# Run inference directly in the terminal:
llama cli -hf microsoft/VibeVoice-ASR-BitNet:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf microsoft/VibeVoice-ASR-BitNet:Q6_K
# Run inference directly in the terminal:
llama cli -hf microsoft/VibeVoice-ASR-BitNet:Q6_K

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf microsoft/VibeVoice-ASR-BitNet:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf microsoft/VibeVoice-ASR-BitNet:Q6_K

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf microsoft/VibeVoice-ASR-BitNet:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf microsoft/VibeVoice-ASR-BitNet:Q6_K

Use Docker

docker model run hf.co/microsoft/VibeVoice-ASR-BitNet:Q6_K

LM Studio
Jan
Ollama
How to use microsoft/VibeVoice-ASR-BitNet with Ollama:
```
ollama run hf.co/microsoft/VibeVoice-ASR-BitNet:Q6_K
```

Unsloth Studio

How to use microsoft/VibeVoice-ASR-BitNet with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for microsoft/VibeVoice-ASR-BitNet to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for microsoft/VibeVoice-ASR-BitNet to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for microsoft/VibeVoice-ASR-BitNet to start chatting

Atomic Chat new
Docker Model Runner
How to use microsoft/VibeVoice-ASR-BitNet with Docker Model Runner:
```
docker model run hf.co/microsoft/VibeVoice-ASR-BitNet:Q6_K
```

Lemonade

How to use microsoft/VibeVoice-ASR-BitNet with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull microsoft/VibeVoice-ASR-BitNet:Q6_K

Run and chat with the model

lemonade run user.VibeVoice-ASR-BitNet-Q6_K

List all available models

lemonade list

VibeVoice-ASR-BitNet / README.md

frontierai

Initial model release

66e7802 verified about 23 hours ago

preview code

Raw

History Blame Contribute Delete

4.12 kB

	---
	language:
	- en
	- zh
	- fr
	- it
	- ko
	- pt
	- vi
	license: mit
	pipeline_tag: automatic-speech-recognition
	tags:
	- ASR
	- quantization
	- cpu-inference
	- gguf
	- bitnet
	- multilingual
	library_name: ggml
	---

	## VibeVoice-ASR-BitNet

	[![GitHub](https://img.shields.io/badge/GitHub-Repo-black?logo=github)](https://github.com/microsoft/VibeASR.cpp)
	[![Technical Report](https://img.shields.io/badge/arXiv-2607.21075-b31b1b?logo=arxiv)](https://arxiv.org/abs/2607.21075)
	[![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](https://opensource.org/licenses/MIT)

	VibeVoice-ASR-BitNet is a compressed variant of [VibeVoice-ASR](https://huggingface.co/microsoft/VibeVoice-ASR) optimized for real-time inference on edge CPUs — no GPU required. Through heterogeneous quantization, the model is compressed from 4.62 GB to 1.58 GB while achieving 1.6–2.3× faster inference than Whisper.cpp with real-time capability (RTF < 1) on as few as 3 CPU threads.

	➡️ Code: [microsoft/VibeASR.cpp](https://github.com/microsoft/VibeASR.cpp)<br>
	➡️ Report: [VibeVoice-ASR-BitNet Technical Report](https://arxiv.org/abs/2607.21075)<br>
	➡️ Base Model: [microsoft/VibeVoice-ASR](https://huggingface.co/microsoft/VibeVoice-ASR)<br>

	<p align="center">
	<img src="figures/report_overview.png" width="90%"/>
	</p>

	---

	## 🔥 Key Features

	- ⚡ Real-time on CPU — RTF < 1 with 3+ threads on commodity x86 (AVX2) and ARM (NEON) hardware
	- 📦 Compact — 1.58 GB total (2.9× compression from FP16), fits in edge device memory
	- 🌍 Multilingual — English, Chinese, French, Italian, Korean, Portuguese, Vietnamese, and more
	- 🔧 Custom SIMD Kernels — Fused operators within the ggml framework for both ARM and x86 platforms

	---

	## Quantization Strategy

	<div align="center">

	\| Component \| FP16 \| Quantized \| Method \| Compression \|
	\|:-:\|:-:\|:-:\|:-:\|:-:\|
	\| VAE Tokenizer \| 1.31 GB \| 0.65 GB \| I8\_S \| 2.0× \|
	\| LM Decoder \| 3.32 GB \| 0.92 GB \| I2\_S + Q6\_K \| 3.6× \|
	\| Total \| 4.62 GB \| 1.58 GB \| — \| 2.9× \|

	</div>

	---

	## Evaluation

	### Inference Speed

	<div align="center">

	\| Threads \| 1 \| 2 \| 3 \| 4 \| 6 \| 8 \|
	\|:-:\|:-:\|:-:\|:-:\|:-:\|:-:\|:-:\|
	\| RTF \| 1.98 \| 1.08 \| 0.77 \| 0.63 \| 0.49 \| 0.42 \|
	\| vs. Whisper.cpp \| 2.28× \| 2.12× \| 1.86× \| 1.86× \| 1.71× \| 1.55× \|

	</div>

	> Benchmarked on AMD EPYC 7V13 (AVX2+FMA) with 20s audio. Bold = RTF < 1 (real-time).

	### Accuracy (WER%)

	<div align="center">

	\| Benchmark \| VibeVoice-ASR-7B \| VibeVoice-ASR-BitNet \| Parakeet \| Whisper \| SenseVoice \| FunASR \|
	\|:-:\|:-:\|:-:\|:-:\|:-:\|:-:\|:-:\|
	\| MLC-EN \| 7.82 \| 8.25 \| 8.40 \| 13.57 \| 12.39 \| 11.36 \|
	\| MLC-FR \| 16.03 \| 17.41 \| — \| — \| — \| — \|
	\| MLC-IT \| 15.67 \| 17.23 \| — \| — \| — \| — \|
	\| MLC-KO \| 9.83 \| 11.15 \| — \| — \| — \| — \|
	\| MLC-PT \| 22.41 \| 24.87 \| — \| — \| — \| — \|
	\| MLC-VI \| 20.15 \| 22.38 \| — \| — \| — \| — \|
	\| AISHELL4 \| 19.83 \| 27.45 \| — \| — \| 22.52 \| 20.41 \|
	\| AMI-ihm \| 17.42 \| 21.36 \| 21.92 \| 27.07 \| 30.81 \| 32.07 \|
	\| AMI-sdm \| 24.18 \| 25.87 \| 26.33 \| 36.92 \| 48.11 \| 40.17 \|
	\| AliMeeting \| 36.21 \| 40.58 \| — \| — \| 38.75 \| 39.27 \|
	\| Fleurs-en \| 4.73 \| 5.21 \| 4.09 \| 3.99 \| 6.84 \| 4.93 \|
	\| Fleurs-zh \| 7.92 \| 8.35 \| — \| — \| 5.56 \| 7.00 \|
	\| Libri-clean \| 2.17 \| 2.41 \| 1.49 \| 1.98 \| 2.78 \| 1.58 \|
	\| Libri-other \| 5.84 \| 6.27 \| 3.13 \| 3.60 \| 6.81 \| 4.01 \|
	\| VoxPopuli \| 4.92 \| 5.18 \| 5.26 \| 7.19 \| 8.63 \| 6.46 \|

	</div>

	---

	## Model Files

	<div align="center">

	\| File \| Size \| Description \|
	\|:-:\|:-:\|:-:\|
	\| `vibeasr-vae-encoder-i8_s.gguf` \| 0.65 GB \| VAE tokenizer, I8\_S quantized (ready to use) \|
	\| `vibeasr-lm-i2_s-embed-q6_k.gguf` \| 0.92 GB \| LM decoder, I2\_S quantized (ready to use) \|
	\| `model-*.safetensors` \| 10.7 GB \| Original SafeTensors (for conversion) \|

	</div>

	---

	## License

	This project is licensed under the MIT License.

	## Contact

	This project was conducted by members of Microsoft Research. If you have suggestions, questions, or observe unexpected behavior, please contact us at VibeVoice@microsoft.com.