lifeiteng / vall-e

PyTorch implementation of VALL-E(Zero-Shot Text-To-Speech), Reproduced Demo https://lifeiteng.github.io/valle/index.html
https://lifeiteng.github.io/valle/index.html
Apache License 2.0
1.99k stars 320 forks source link

Training data length problem #159

Closed yiwei0730 closed 12 months ago

yiwei0730 commented 1 year ago

May I ask if the length of the training data should be about 10-20 seconds, but currently our training data is roughly 5-10 seconds. How to lengthen the audio file (combine the two audio files) , and let the training data length becomes longer.