MuAViC makes it possible to use audio-visual learning for highly accurate speech translation. Using MuAViC to train our AV-HuBERT model helped us achieve results outperforming other leading translation models in noisy, challenging settings.

More ➡️ https://t.co/FUnlg2dUOq pic.twitter.com/X6sGzU8FCW

— AI at Meta (@AIatMeta) 27 mars 2023

MuAViC makes it possible to use audio-visual learning for highly accurate speech translation. Using MuAViC to train our AV-HuBERT model helped us achieve results outperforming other leading translation models in noisy, challenging settings. More https://
bit.ly/3ZNg76h

→ View original post on X — @aiatmeta,