[fab1an]

amazing work!

Curious how you cloned the voices - tortoise? I've previously tried Herzog, but couldn't quite train the German accent...

[jamez]

I haven't tried Tortoise, thanks for pointing me to it. The voices were cloned by fine tuning a VITS model with coqui.ai. I used about two hours of speech for each speaker. With more time and resources, I'm certain it's possible to make those voices considerably better.

[OgAstorga]

Can I get an invite link?

[jamez]

No need to be invited. Between their GitHub[1] page and the documentation[2], you'll find everything you need to get started.

[1] https://github.com/coqui-ai/TTS [2] https://tts.readthedocs.io/en/latest/

[forgingahead]

How long did you train the models for each speaker, and what hardware were you using?

[jamez]

It was fine tuning, so the process was a lot faster than I originally anticipated. I'd say it was between 36 and 72 hours for each voice. I have been working on a gradient notebook provided by Paperspace, which guaranteed me A6000 instances (48GB GPU RAM) at a reasonable flat rate. I discovered them after being repeatedly frustrated by the random allocation of GPUs on colabs pro+ plan.

[hanselot]

How much input audio would you need to produce audiobook quality? Hint Hint...

[blueberrychpstx]

https://coqui.ai?referralCode=q8jfhfs&refSource=copy help us move up the list!

[biztos]

I don’t know if this is useful, but Herzog has a distinctly Bavarian accent. And of course has spent most of his adult life far from there, so it’s not quite Bavarian either.

Training a Herzogbot on recordings/transcriptions of, say, Kinski would be a waste of time accent-wise.