flexthink

Answers to comments that are questions: 11 - the other option is "speechbrain", using the standard text encoder 13 - basic_cleaners, transliteration_cleaners (see text_to_sequence) 17: This is needed to identify...

+1

+1

> Hello @flexthink, > > Could you please have a look at the recipe tests of the AudioMNIST dataset? They are all failing. I tried to fix the first three...

I have a fix https://github.com/speechbrain/speechbrain/pull/2540 @Adel-Moumen @mravanelli