How to use PaddlePaddle/PaddleOCR-VL-1.5 with PaddleOCR:
# See https://www.paddleocr.ai/latest/version3.x/pipeline_usage/PaddleOCR-VL.html to installation from paddleocr import PaddleOCRVL pipeline = PaddleOCRVL(pipeline_version="v1.5") output = pipeline.predict("path/to/document_image.png") for res in output: res.print() res.save_to_json(save_path="output") res.save_to_markdown(save_path="output")
ProblemThe PaddleOCR-VL-1.5 model DOES NOT WORK due to architecture incompatibility:
Uses custom Ernie 4.5 with rope_type='default'Transformers 4.48-5.8 do not support this configurationError: KeyError: 'default' in ROPE_INIT_FUNCTIONS
· Sign up or log in to comment
