Tim von Känel

Yeah, this would be great

@lucidrains I wasn't aware of that library, looks good. I looked into [torch.Function](https://pytorch.org/docs/stable/autograd.html#torch.autograd.Function) but then one has to write the backward pass himself. Anything that takes a loop and does...

The .db file is a sqlite database file. The project is still pretty much a work in progress, it's good that you use ubuntu because I currently test on ubuntu...

[v0.1.4](https://github.com/dunky11/voicesmith/releases/tag/v0.1.4) works for me. You may need to start the app using the command line by typing "voice-smith". Otherwise it may currently not detect your conda installation.

You should try [0.2.0](https://github.com/dunky11/voicesmith/releases/tag/v0.2.0), everything python runs in Docker now, which should fix most issues, hope this one works for you ...

I tried implementing naturalspeech [here](https://github.com/dunky11/voicesmith/blob/main/backend/voice_smith/model/natural_speech.py). It pretty much contains it's architecture with a different text encoder. You can swap out the text encoder with the one from [VITS](https://github.com/jaywalnut310/vits), if you...

And you obviously also want to swap out the decoder with [HiFiGAN](https://github.com/jaywalnut310/vits/blob/main/models.py), called Generator in the file.

Hi, is that [version 0.2.0](https://github.com/dunky11/voicesmith/releases) downloaded from the releases page?

Sure :) First of all I would strongly advise against using this toolkit at the moment, it is a work in progress and filled with bugs. If you still want...

@DrAnime-byte Thanks for the issue, can you tell me what your operating system is? I also wouldn't use this software yet, it's still a work in progress and contains a...