ELDonationTracker VS EasyOCR

https://github.com/djotaku/ELDonationTracker depends on

http://djotaku.github.io/ELDonationTracker/ - for tracking donations to Extra Life and displaying when Live Streaming

Python - it’s my main language and the one in which I’m most proficient. I have written some programs used by many others (like my Extra Life Donation Tracker) and utilities that solve some problem I have (like my btrfs snapshot and backup program). By solving each problem in Python first, I allow myself to focus on the problem first instead of a syntax I’m unfamiliar with.

If you want to move to GUI programs, I recommend : Qt5 Python GUI Programming Cookbook. Using QT Designer you can GUI programs pretty quickly. I used this book to create the GUI for my Extra Life project: http://djotaku.github.io/ELDonationTracker/

not sure if this is going beyond automation, but my most complex Python program which is actually used by other folks is for generating Donation Alerts while Live-Streaming to Twitch (or wherever) - http://djotaku.github.io/ELDonationTracker/

I use JSON and a dataclass (not a literal dataclass w/ the decorator and all). See ParticipantConf class starting line 103 https://github.com/djotaku/ELDonationTracker/blob/master/eldonationtracker/utils/extralife_io.py

In my project, here are the files that QT Designer saves: https://github.com/djotaku/ELDonationTracker/tree/master/QTdesignerfiles

I wanted to be able to use the Donation API when doing the Extra Life fundraiser, so I made: https://github.com/djotaku/ELDonationTracker

I'm using it for my program as well. It's really awesome, especially if you use qt designer. https://github.com/djotaku/ELDonationTracker

PyTesseract Module [ Github ] EasyOCR Module [ Github ] PaddlePaddle OCR [ Github ]

I just uploaded my C++ implementation of EasyOCR, a well known ocr library for python. Also dusted some cobwebbs from some audio related projects as well, feel free to leave feedback or contribute! I only implemented the most salient parts, so certainly could use some community help! Cheers!

EasyOCR is a popular project if you are in an environment where you can use run Python and PyTorch (https://github.com/JaidedAI/EasyOCR). Other open source projects of note are PaddleOCR (https://github.com/PaddlePaddle/PaddleOCR) and docTR (https://github.com/mindee/doctr).

The main one was https://github.com/JaidedAI/EasyOCR, mostly because, as promised, it was pretty easy to use, and uses pytorch (which I preferred in case I wanted to tweak it). It has been updated since, but at the time it was using CRNN, which is a solid model, especially for the time - it wasn't (academic) SOTA but not far behind that. I'm sure I could've coaxed better performance than I got out of it with some retraining and hyperparameter tuning.

Anyways, you can give a shot to EasyOCR, pretty solid and flexible

The easyocr library: https://github.com/JaidedAI/EasyOCR

Not used it on a Pi but maybe a Docker version (if there is one) would run? Compose file here