I am looking for help to implement a machine learning algorithm that would take an invoice wav stream of a human talking, and it will convert the recording of another human talking wav to this targeted voice.
I have some sample code that works, but it takes a few hours of audio wav. I want to implement an algorithm using wavnet that would make it much easier and faster to train like in a few sentences.
August 16, 2018
I am looking for a mix of experience and value