docling-project / docling-project/docling
pdf processing with OCR is stuck
- Dominant language
- Python
- Stars
- 66.4k
- Forks
- 4.8k
- Avg merge
- 2d 21h
- Merged PRs (30d)
- 84
Description
### Question
I am processing single pdf of 4 MB with the below OCR options ,
pipeline_options = PdfPipelineOptions()
pipeline_options.do_ocr = True
pipeline_options.do_table_structure = True
pipeline_options.table_structure_options.do_cell_matching = True
ocr_options = TesseractCliOcrOptions(force_full_page_ocr=True)
pipeline_options.ocr_options = ocr_options
Process is running indefinitely for hours , I am not sure whether its something to do with files , its pptx file converted to pdf , use-case is to extract the complex tables
I tried using accelarator options, tried both CPU and GPU , it doesnt help too.
accelerator_options = AcceleratorOptions(
num_threads=8, device=AcceleratorDevice.CPU
)
How do I address this issue ? Is there a way to process pages within PDF in-parallel ?
...
Contributor guide
Assessment
This issue has not been assessed yet.