PIP package

[fakerybakery]

Hi, are you planning to allow us to install this via pip by creating a setup.py file?

[yl4579]

This repo serves as a research's project, but if it needed surely I can make a pip package. Do you need it for training or for inference?

[fakerybakery]

Mostly for inference. I was planning to make a Gradio demo, but I can also do that by just cloning the repo. (Might make a PR later if that's ok.)

[yl4579]

Yes, please do so if you can. Thanks for your contribution.

[fakerybakery]

This will require a restructuring of the files (putting them all in one folder) and may break the demos, so I'll work on it in a fork for now.

[fakerybakery]

I've got a very hacky fork that should be pip installable here (still need to create setup.py), however the training scripts + config files have been removed.

[lxe]

Thanks for this, and the demo, @fakerybakery

Would be nice to have inference.py commited and mainlined.

[fakerybakery]

Hi @lxe, by inference.py do you mean a importable script? I'm planning to make a PR to merge the demo + script soon after I clean up the code.

I'm going to delete my pip fork because it breaks training, config, etc. Personally, I think it would be better to have an external "wrapper" repository that's pip-installable to keep the training scripts, similar to how VoiceFixer has the VoiceFixer pip installable package and the VoiceFixer main repository with training scripts, etc.

[fakerybakery]

@yl4579 would you mind adding this to the "todo" list in the README?

[yl4579]

My main concern of this is it could contain phonemizer and change the license of the repo. I use notebook intentionally so it doesn't contain any non-MIT libraries. Even if I add it to TODO it probably wouldn't be a part of this repo anyway.

[fakerybakery]

OK, please see the other comment about the fork

[lxe]

I was able to wrangle around the inability to import this in my own package:

https://github.com/lxe/tts-server

Here's what I needed to do:

• styletts2 is a git submodule
• needed to add this to make some submodules work https://github.com/lxe/tts-server/blob/4903b4a14828549b78676cb9927e0242695d5a06/setup.py#L4-L6
• also needed this to make other impotrs inside styletts work: https://github.com/lxe/tts-server/blob/4903b4a14828549b78676cb9927e0242695d5a06/tts_server/tts.py#L20-L23

I think a lot of this styletts code needs some relative module imports and some other cleanup

[yl4579]

I think I can move this to discussion now, as making a pip package would inevitably ruin the current MIT license status unless we have a good MIT licensed phonemizer alternative.