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.
⚡ 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
[email protected]
.
Runs of microsoft VibeVoice-ASR-BitNet on huggingface.co
22.4K
Total runs
3.0K
24-hour runs
6.8K
3-day runs
9.5K
7-day runs
6.4K
30-day runs
More Information About VibeVoice-ASR-BitNet huggingface.co Model
VibeVoice-ASR-BitNet huggingface.co is an AI model on huggingface.co that provides VibeVoice-ASR-BitNet's model effect (), which can be used instantly with this microsoft VibeVoice-ASR-BitNet model. huggingface.co supports a free trial of the VibeVoice-ASR-BitNet model, and also provides paid use of the VibeVoice-ASR-BitNet. Support call VibeVoice-ASR-BitNet model through api, including Node.js, Python, http.
VibeVoice-ASR-BitNet huggingface.co is an online trial and call api platform, which integrates VibeVoice-ASR-BitNet's modeling effects, including api services, and provides a free online trial of VibeVoice-ASR-BitNet, you can try VibeVoice-ASR-BitNet online for free by clicking the link below.
microsoft VibeVoice-ASR-BitNet online free url in huggingface.co:
VibeVoice-ASR-BitNet is an open source model from GitHub that offers a free installation service, and any user can find VibeVoice-ASR-BitNet on GitHub to install. At the same time, huggingface.co provides the effect of VibeVoice-ASR-BitNet install, users can directly use VibeVoice-ASR-BitNet installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
VibeVoice-ASR-BitNet install url in huggingface.co: