Hacker News new | ask | show | jobs
by OgAstorga 1320 days ago
Can I get an invite link?
2 comments
jamez 1320 days ago
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/

link
forgingahead 1320 days ago
How long did you train the models for each speaker, and what hardware were you using?
link
jamez 1319 days ago
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.
link
hanselot 1320 days ago
How much input audio would you need to produce audiobook quality? Hint Hint...
link
blueberrychpstx 1320 days ago
https://coqui.ai?referralCode=q8jfhfs&refSource=copy help us move up the list!
link