diff --git a/docling/models/tesseract_ocr_cli_model.py b/docling/models/tesseract_ocr_cli_model.py index 91b4555..33ca0c1 100644 --- a/docling/models/tesseract_ocr_cli_model.py +++ b/docling/models/tesseract_ocr_cli_model.py @@ -249,7 +249,7 @@ class TesseractOcrCliModel(BaseOcrModel): cell = TextCell( index=ix, text=str(text), - orig=text, + orig=str(text), from_ocr=True, confidence=conf / 100.0, rect=BoundingRectangle.from_bounding_box(