I would like to know if it is possible for the model to learn the features of a custom speaker from a sample audio and use that to generate an audio with the same characteristic of the voice? I am mainly looking at fairseq and seamless to do this. I looked up the issues of these two but didn't come across anything.
If any generous person can guide me to right direction that would be amazing!
I would like to know if it is possible for the model to learn the features of a custom speaker from a sample audio and use that to generate an audio with the same characteristic of the voice? I am mainly looking at fairseq and seamless to do this. I looked up the issues of these two but didn't come across anything.
If any generous person can guide me to right direction that would be amazing!