Giters

fatchord / WaveRNN

WaveRNN Vocoder + TTS

Home Page:https://fatchord.github.io/model_outputs/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

How many clips to make a model?

RM-urb opened this issue · comments

commented

I'm trying to build my own model and spending a lot of time chopping up wavs... How many clip/transcription couples do I need to be able for train_tacotron to run properly and make a model to start testing ?