This is a OCR - optical character recognition engine built on Python. It has the capability to input an entire multi-line text document and separate line-from-line. Currently it is not very good at doing what it's supposed to do, but I'm working on that. It can... somewhat recognise text.
Right now: So... yes. The accuracy is definitely a WIP, but the overall model is complete. With a bit more training data and hyperparameter tuning it'll probably do better.
Detailed Docs: