search

padmalcom / jotts

German Text-To-Speech Engine using Tacotron and Griffin-Lim
MIT License
6 stars 1 forks source link

Missing additional information in README #5

Closed eqikkwkp25-cyber closed 2 years ago

eqikkwkp25-cyber commented 2 years ago

Typo somewhere: The readme says "The synthesizer model has been trained on my voice using Tacotron1." while the releases say "v0.1 Latest Pre-trained German synthesizer model based on tacotron2."

Can you add more hints how you trained your model(s), i.e. which base repository, data structure and how many hours of your voice you need for the current results?

padmalcom commented 2 years ago

Thank you, I fixed the tacotron version typo. You can find training information in my other repository here. As you might know, this is the synthesizer modell. When you have a pretrained model (that you can take from the repo), you need ~15 minutes of your own voice to train a model which imitates your voice well.