Two new languages in the same model? Excellent
#1
by
notakwithac - opened
Hi! I am a student trying to finetune my own regional languages.
I wanted to ask about datasets used (just duration, number of speakers etc.), and how were you able to introduce both languages in the same model.
As per my information, it is possible to finetune another person (with their audio and transcript (which should be in english or chinese)), but trying to finetune for each language needs to happen seperately.
Any information would be helpful for me. Thanks in advanced.