higgs-audio-v3-8b-stt-v2

bosonai/higgs-audio-v3-8b-stt-v2

Speech Recognition8.9B parametersLicense: apache-2.0
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
Downloads 30D
3,117
Total downloads
25.5K
Gained 7D
+223(increase)
1.0%(up) vs baseline
Gained 30D
—
Likes
15
+1 in 7D
Rank · tracked models
#15,597
1936(down 1936 places)this week
Parameters
8.9B
Last source update
May 22, 2026
Momentum
60.7
  • higgs-audio-v3-8b-stt-v2 gained 223 downloads during the last seven tracked days.
  • It moved from #445 to #487 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

higgs-audio-v3-8b-stt-v2 is a speech recognition model published by bosonai. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it Oct 5, 2026.

Published
Apr 27, 2026
Last updated
May 22, 2026
Library
—
License
apache-2.0
Task
Speech Recognition
Parameters
8,905,965,568
Spaces
—
Derivative models
—
Velocity 7D/day
32
safetensorshiggs_audio_3automatic-speech-recognitionhf-asr-leaderboardwhisperqwencustom_codeenlicense:apache-2.0model-indexregion:us

Similar models

Models similar to higgs-audio-v3-8b-stt-v2
ModelDL 30D
VibeVoice-ASRmicrosoft723K
VibeVoice-ASR-Streaming-7Bmicrosoft6,371
granite-speech-3.3-8bibm-granite26.7K
granite-speech-3.2-8bibm-granite48.9K
VibeVoice-ASR-Streaming-7B-4bitmlx-community258
VibeVoice-ASR-Streaming-7B-bf16mlx-community209
bosonai/higgs-audio-v3-8b-stt-v2 — Downloads, Growth & Stats | OpenModelStats