fairseq/data/audio/speech_to_text_dataset.py · master · xuchen / Fairseq-S2T · GitLab

Blame History Permalink

Cumulative updates. · 6e37ffba
```
implement mix-speech and optimize the ctc entropy loss
```
xuchen committed Oct 25, 2022
6e37ffba

speech_to_text_dataset.py 21.9 KB