I'm working on a project that involves text extraction from images using the EasyOCR library in Python. I've been using the library's default detection and recognition models, but now I want to integrate my own custom detector and transformer-based recognition models. I'm struggling to understand how to properly implement this feature.
custom_detector_model = ... # Load custom detector model here
custom_recognition_model = ... # Load custom recognition model here
reader = easyocr.Reader(lang_list=['en'], detector=custom_detector_model, recognizer=custom_recognition_model)
However, I'm unsure if I'm following the correct approach or if I need to make additional adjustments to ensure compatibility with EasyOCR's framework. Could someone please guide me through the correct process of using custom detection and recognition models with the EasyOCR library? Any insights would be greatly appreciated.