search

jasonppy / VoiceCraft

Zero-Shot Speech Editing and Text-to-Speech in the Wild
Other
7.51k stars 739 forks source link

About masking when training TTS enhanced model #129

Open WoBuChiTang opened 4 months ago

WoBuChiTang commented 4 months ago

Hello, thanks for this excellent work!

I am training a TTS model and would like to ask if it is necessary to add any terminator to Y in the prepare_input_target function? Like eog or eos? Can you share the code of TTS model training?

Your answer will help me a lot! Thank you so much!

jasonppy commented 4 months ago

TTS training is just removing the causal masking part of the code. I'm a bit busy right now so not sure when the code will be pushed

xiangkanghuang commented 2 months ago

TTS training is just removing the causal masking part of the code. I'm a bit busy right now so not sure when the code will be pushed

I'm really looking forward to TTS training code