AVSRCocktail

nguyenvulebinh/AVSRCocktail

Speech Recognition429M parameterstransformers
Tracked by OpenModelStats since September 5, 2026View on Hugging Face ↗
Downloads 30D
49
Total downloads
1,883
Gained 7D
+6(increase)
0.3%(up) vs baseline
Gained 30D
—
Likes
2
+0 in 7D
Rank · tracked models
#47,746
288(down 288 places)this week
Parameters
429M
Last source update
Jul 7, 2025
Momentum
21.8
  • AVSRCocktail gained 6 downloads during the last seven tracked days.
  • It moved from #1364 to #1378 among tracked Speech Recognition models this week.

Downloads over time

Rolling recent-window downloads as reported

Likes over time

Rank among tracked models

Lower is better

Overview

AVSRCocktail is a speech recognition model published by nguyenvulebinh. OpenModelStats has tracked the model since Sep 5, 2026, most recently observing it Oct 2, 2026.

Published
Jul 4, 2025
Last updated
Jul 7, 2025
Library
transformers
License
—
Task
Speech Recognition
Parameters
428,859,354
Spaces
0
Derivative models
—
Velocity 7D/day
1
transformerssafetensorsavhubert_avsrautomatic-speech-recognitionaudio-visual-speech-recognitionmultimodalspeech-recognitionlip-readingcocktail-partynoise-robustav-huberttransformer

Similar models