End-to-end-ASR-Pytorch icon indicating copy to clipboard operation
End-to-end-ASR-Pytorch copied to clipboard

Published 20 hours ago • verified publisher icon Alexander-H-Liu

Step 0 : text encoding

Open taylerpauls opened this issue 4 years ago • 1 comments

Can we use the subword models in the sample data folder for most datasets? Also, if we train the ASR, do we need to train the LM ?

taylerpauls avatar Jul 24 '20 21:07 taylerpauls

you can train the ASR and LM respectively,and you can use the LM during the decoding

durian1023 avatar Feb 04 '21 08:02 durian1023