Open
Description
Version
surya-ocr==0.14.5
Problem
RecognitionPredictor return text with html tag, such as <b>Abstract</b>. How to get text without html tag from RecognitionPredictor directly?
Code
predictions = recognition_predictor(images=[image], det_predictor=detection_predictor)
result = [(text_line.text, text_line.bbox) for text_line in predictions[0].text_lines]
print(result)
Metadata
Metadata
Assignees
Labels
No labels