I have a bunch of medical records that I have to input manually. I would like to automate this but all of the records are in different formats. What is the best strategy to build a deep learning model to extract this information automatically? Does it make sense to use something like YOLO to recognize specific parts of the image and then Tesseract to actually perform OCR? A bit of guidance would be much appreciated. Also, I have seen things like Amazon Textract but am looking for something I can build and run locally without depending on another service. Thanks!