Davit Hovhannisyan

sound quality is very poor

and he can synthesize Russian speech?

How can I clone the voice of one audio into another? without text

what a pity, can you explain, I didn’t understand the timestep_independent function a little, what it does with the data

I want to understand architecture better

thanks for the reply: can i ask a few more questions, does get_conditioning_latents fetch the data to clone? and what does an autoregressive model do.

thank you so much