MSP-VSR

MahmoodAnaam/MSP-VSR

Speech Recognition325M parameterstransformersLicense: apache-2.0
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
Downloads 30D
91
Total downloads
841
Gained 7D
+32(increase)
Gained 30D
—
Likes
1
+1 in 7D
Rank · tracked models
#36,159
5792(down 5792 places)this week
Parameters
325M
Last source update
Sep 1, 2026
  • MSP-VSR gained 32 downloads during the last seven tracked days.
  • It moved from #907 to #1203 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

MSP-VSR is a speech recognition model published by MahmoodAnaam. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it Sep 28, 2026.

Published
Aug 18, 2026
Last updated
Sep 1, 2026
Library
transformers
License
apache-2.0
Task
Speech Recognition
Parameters
325,178,504
Spaces
—
Derivative models
—
Velocity 7D/day
5
transformerssafetensorsmsp_visualautomatic-speech-recognitioncustom_codevisual-speech-recognitionlip-readingctcVSRendataset:nguyenvulebinh/AVYTdataset:nguyenvulebinh/AVCocktail

Publisher

MahmoodAnaamView publisher statistics →

Derived from MahmoodAnaam/avhubert_encoder_large_noise_pt_noise_ft_433h (reported by the source; parent not yet tracked).

Similar models

MahmoodAnaam/MSP-VSR — Downloads, Growth & Stats | OpenModelStats