Various scripts that together create a pipeline, which can take images of book pages and turn them into CoNLLU files

Currently in development, so if you want to use these files then feel free but keep in mind that I've not made this with other setups in mind.

Trankit does not run on python 3.11 ->, so use this in an environment with Python 3.10 (Numpy needs to be 1.x, 2.y won't work)