bkutasi

In my opinion this is one most important features of a tts so would love to see this integrated,

This looks like a way too long prompt, I would do 1 prompt/sentence at most.

@ai-bits Hallo Günter and greetings from Tirol! So I think we won't be able to ever generate minutes long audios ever, but maybe if we get chucks or some kind...

Great work! I love to see speed bumps. Will try to test out today and report back. How is cross-platform support? I presume win and Linux are both supported? What...

I have to report that I have a compilation error when trying to get this to run/setup. ///https://github.com/sterlind/GPTQ-for-LLaMa works like a breeze/// partially completes, doesnt work after all. I'm on...

I added xfromers into `oobabooga_windows/text-generation-webui/requrments.txt` and it installed the latest xfromers, but I get a triton error when I use the --xformer parameter. First 4 lines at launch: `Gradio HTTP...

Hey there, great work! Some suggestions: Why not use venv instead of conda? (python -m venv c:\path\to\myenv) Maybe package miniconda with the project.

I think this would be an excellent feature. The installation of AICoverGen is much easier and streamlined than anything I've come across. Maybe just an api would be enough to...

I feel like this is the best model that is small enough and accurate enough to become widespread while being pretty accurate. Definitely better than oasst in the same parameter...

I have encountered with this issue when trying to load large models into my multi-gpu setup. Increasing the amount of paged memory on my drives helped it, but I could...