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

VibeVoice-ASR-BitNet is a compressed variant of 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
➡️ Report: VibeVoice-ASR-BitNet Technical Report
➡️ Base Model: microsoft/VibeVoice-ASR

🔥 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

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×

Evaluation

Inference Speed

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×

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

Accuracy (WER%)

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

Model Files

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)

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.

Downloads last month: -

Safetensors

Model size

0.3B params

Tensor type

F32

Paper for microsoft/VibeVoice-ASR-BitNet

VibeVoice-ASR-BitNet Technical Report

Paper • 2607.21075 • Published 1 day ago