This is a program for Optical Character Recognition(OCR), made using pytesseract (https://pypi.org/project/pytesseract/)
I expect this to be cross platfrom though I didn't test this on linux, But should work IDK.
I made a shitty GUI with Tkinter which can process single files or multiple files in a folder.
Though The GUI has the "ben" option for Bengali character recognition you'll need to download Bengali traineddata from here as ben.traineddata and copy it into the tessdata folder of your tesseract installation folder.
i) Install the packages in the setup/requirements.txt file
ii) Install Tesseract
Direct Links for Noobs like me :
Windows
Linux :
sudo apt-get install tesseract-ocr && sudo apt-get install tesseract-dev
I'll Be Very Happy If this is of Any use to you. Peace