search

KimythAnly / AGAIN-VC

This is the official implementation of the paper AGAIN-VC: A One-shot Voice Conversion using Activation Guidance and Adaptive Instance Normalization.
https://kimythanly.github.io/AGAIN-VC-demo/index
MIT License
111 stars 19 forks source link

is it non-parallel? #6

Closed chikiuso closed 3 years ago

chikiuso commented 3 years ago

hi, could I train it with non-parallel datasets? thanks.

KimythAnly commented 3 years ago

If you are referring to a dataset without transcription, then yes. BTW, the dataset we use is VCTK, which is a non-parallel dataset.