TensorFlowASR icon indicating copy to clipboard operation
TensorFlowASR copied to clipboard

Published 20 hours ago • verified publisher icon TensorSpeech

Extracting phonems from audio

Open jkViswanadham opened this issue 3 years ago • 1 comments

Can this be modified to extract Phonems with their start and end time stamps in audio file?

jkViswanadham avatar Jul 30 '21 23:07 jkViswanadham

I believe we can, since all we need to do is making a custom version of the ASRDataset, Speech Featurizer, Text Featurizer and feed the dataset into models with phonemes classes.

nglehuy avatar Aug 01 '21 17:08 nglehuy