MA Previous - Official Trailer

Watch the Official trailer​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​ from ...

Maati - Official Trailer

Watch the Official trailer​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​ from ...

Meta’s Omnilingual ASR Covers 1,600 Languages, Including Rare Indian Dialects

Meta releases Omnilingual ASR and wav2vec 2.0 models supporting 1,600+ languages, 500 low-resource tongues and long-tail ...
GitHub

A deep learning library for video understanding research.

A PyTorchVideo-accelerated X3D model running on a Samsung Galaxy S10 phone. The model runs ~8x faster than real time, requiring roughly 130 ms to process one second of video. A PyTorchVideo-based ...