ROBERT MCDOWELL

1st test on my mac int OS sequoia dev machine, it works: Details ``` Processing eBook file: Против_двоемыслия.txt Using CPU Free Memory available: 3.79GB Running command: /usr/local/bin/ebook-convert /Users/workmin/repos/ebook2audiobook/tmp/proc-32dbbdfb-e305-4bef-9c59-4a7e0eecf5b5/3050a984300eb61388074bf7bfe8d1af/Против_двоемыслия.txt /Users/workmin/repos/ebook2audiobook/tmp/proc-32dbbdfb-e305-4bef-9c59-4a7e0eecf5b5/3050a984300eb61388074bf7bfe8d1af/__Против_двоемыслия.epub Conversion...

could you switch with CPU rather than GPU?

yes I just fixed the function causing phonetization of foreign words in latin languages. it's fixed and I'm going to PR once your issue is solved. so your issue comes...

ok could you try to remove this block in ./lib/classes/tts_engines/coqui.py: ``` if using_gpu and enough_vram: if devices['CUDA']['found'] or devices['ROCM']['found']: torch.cuda.set_per_process_memory_fraction(0.95) torch.backends.cudnn.enabled = True torch.backends.cudnn.benchmark = True torch.backends.cudnn.deterministic = True torch.backends.cudnn.allow_tf32...

well, even if it's not realtime it will help a lot already ;). I'm working on it for now but my biggest issue is to make a dummy device working...

oh my! sorry I just realized the link you sent is another repo. turnvoice is already a very good start indeed! about realtime, indeed only pre chunks can do the...

@KoljaB I opened a new discussion on turnvoice repo to discuss about vtt/srt import as I think it's a better repo to add an option to import SRT/VTT rather than...

@vencabot nothing to do with any plugin, it's just a non logical behavior of PT. if you don't allow upload nor signup on your instance there is no need to...

the shortest way is to fix this bug, not to create a plugin just for that. btw it sound like A.I. is behind you.

would be nice