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

Pretrained models, samples and a question #1

Closed Dannynis closed 4 years ago

Dannynis commented 4 years ago

Hey, Ive found your repository very interesting and i would like to try it. are there any sample from your trained model on the VCTK data ? also is it possible to get the model you are using ? Also i've noticed that during prepossessing, you are creating evaluation and test sets but don't use then anywhere, is it currently WIP ? Thank you very much !

cyhuang-tw commented 4 years ago

Hi,

Thanks for liking my repository. I just added the link for the pre-trained model at README (at the "Inference" section). You may use the model to generate some samples.

The dev and test sets are not used in the current code, and I will fix this in the future. However, as I am working on another project, I am not able to tell when it will be done.

ghost commented 3 years ago

Hello, Thank you for the great code. I am unable to find the pre-trained models. Can you please share them? Thanks.

cyhuang-tw commented 3 years ago

Hi,

I am currently training a new model, and it will be released soon.