JY9087

Found the problem. It's surya that causes the memory leak. In the suyra/recognition.py file, within the batch_recognition() function, there's a line: processed_batches = processor(text=[""] * len(images), images=images, lang=languages) This line...

You would find equation_regions = [l.bbox for l in page.layout.bboxes if l.label in ["Formula"]] in equations.py, and replace it with equation_regions = [l.bbox for l in page.layout.bboxes if l.label in...