self-supervised-speech-recognition icon indicating copy to clipboard operation
self-supervised-speech-recognition copied to clipboard

Published 20 hours ago • verified publisher icon mailong25

how to train from scratch wav2vec + wav2letter

Open tranmanhdat opened this issue 4 years ago • 0 comments

i have 2 questions, First, is wav2vec lastest model you implement better than wav2vec + wav2letter ( for example in wer, recognition in reality?) Second, can you provide tutorial for training from scratch wav2vec+wav2letter?

tranmanhdat avatar Jun 03 '21 13:06 tranmanhdat