autovc
autovc copied to clipboard
How to use Pretrained model for Inference?
I have a question, how we can use provided pretrained models for Inference? I know about conversion.ipynb, but I don't understand anything there, let me know how I can? like I have to do voice style transfer, I have source audio file and target audio file, how I can take my source voice style like target? so I have to follow conversion file, so where to provide these inputs?
I second this! It would help to have some more explicit guidance on finding the 'knobs' on this thing - I think a lot of people are excited about it because it is awesome, but the README reads like a reminder to the original authors.