OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformer.
Yifan PengJinchuan TianWilliam ChenSiddhant AroraBrian YanYui SudoMuhammad ShakeelKwanghee ChoiJiatong ShiXuankai ChangJee-weon JungShinji WatanabePublished in: CoRR (2024)