fairseq/criterions/join_speech_and_text_loss.py · d946bc3bb60503f3f16e1960a5c3e43687cee05f · xuchen / Fairseq-S2T · GitLab

Blame History Permalink

implement the dual speech-to-text (need to optimize) and CTC loss for MT · 5fb50cc3
xuchen committed Mar 10, 2022

5fb50cc3

join_speech_and_text_loss.py 5.71 KB