Open perkel666 opened 1 year ago
That's precisely what "get_conditioning_latents" script does. The model isn't finetuned/trained on the voices, but rather extracts "latents" (think "voice description") as a pre-processing step, and then uses these latents "kind of" like a seed for the speech generation.
Sadly decoupling this process won't be a big time-saver, as in the current iteration generation of latents only takes a couple of seconds, however it's still a step forward.
The issue.
If I understand it right tortoise does this:
Which means each time to produce one sentence it does each time finetuning.
The solution