Aamir3d

This issue wasn't present in 1.6, I'm seeing this in 1.7 - Local install on Windows with an Nvidia 3060. Checkpoints start filling up all available system RAM. I know...

> @Aamir3d Install docs updated it may be what you're looking for, it was doing the same thing for me. But not when switching models, it would at each generation...

Thanks @rsxdalv , appreciate this!

Here's another project https://github.com/aedocw/epub2tts This is based off https://github.com/coqui-ai/TTS The assumption is that we can get long form TTS working with different voices.

Thanks for the explanation @rsxdalv !! Looks like the Piper model might work with the GUI. Thinking beyond only epubs, is there (possibly) a way to export PDF, WORD, RTF...

You have two great ideas here! The ideal would be to start a batch, and have it finish and show the generations below in a row format (like in your...

From the end user's perspective, as long as there's a good GUI, the back end development should not be an issue. Whatever is easier for you and I know you're...

> Hopefully this resolves it: #281 Thank you - I'm looking to test this out over the weekend! Will share updates.

> Added for bark. I tested and managed to reclaim some of the GPU memory, but not all of it (for example, I saw 4.5gb -> 1.3 gb drop). But...

I just tested with the latest update. After clicking Unload Models, the memory usage goes down by only 2 GB. Not sure why the remaining memory isn't cleared.  ...