VibeVoice-ASR

microsoft/VibeVoice-ASR

Speech Recognition8.7B parameterstransformersLicense: mit
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
Downloads 30D
727.9K
Total downloads
5.7M
Gained 7D
+185.8K(increase)
3.6%(up) vs baseline
Gained 30D
—
Likes
1,302
+6 in 7D
Rank · tracked models
#547
17(up 17 places)this week
Parameters
8.7B
Last source update
Jan 27, 2026
Momentum
93.1
  • VibeVoice-ASR gained 185.8K downloads during the last seven tracked days.
  • It moved from #58 to #43 among tracked Speech Recognition models this week.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

VibeVoice-ASR is a speech recognition model published by microsoft. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it Oct 2, 2026.

Published
Jan 21, 2026
Last updated
Jan 27, 2026
Library
transformers
License
mit
Task
Speech Recognition
Parameters
8,674,021,857
Spaces
—
Derivative models
4
Velocity 7D/day
26.5K
transformerssafetensorsvibevoiceASRTranscriptoinDiarizationSpeech-to-Textautomatic-speech-recognitionenzhespt

Model family

Based on base-model relationships reported by the source's metadata.

Similar models

Models similar to VibeVoice-ASR
ModelDL 30D
VibeVoice-ASR-Streaming-7Bmicrosoft7,048
granite-speech-3.3-8bibm-granite29.3K
granite-speech-3.2-8bibm-granite49.9K
higgs-audio-v3-8b-stt-v2bosonai5,060
VibeVoice-ASR-Streaming-7B-4bitmlx-community237
VibeVoice-ASR-Streaming-7B-bf16mlx-community194
microsoft/VibeVoice-ASR — Downloads, Growth & Stats | OpenModelStats