search

cyhuang-tw / AdaIN-VC

An unofficial implementation of the paper "One-shot Voice Conversion by Separating Speaker and Content Representations with Instance Normalization".
115 stars 20 forks source link

vocoder #6

Closed pavelxx1 closed 3 years ago

pavelxx1 commented 3 years ago

I need to train vocoder on my own dataset(non-English) or can use your pretrained vocoder.pt? thx

cyhuang-tw commented 3 years ago

Hi,

The provided vocoder was trained on English datasets only, so I am not sure how it performs in different languages. For additional information about cross-lingual performance, please refer to this paper.