docling-project / docling-project/docling
The model recognizes the cell contents in the table incorrectly
- Dominant language
- Python
- Stars
- 66.4k
- Forks
- 4.8k
- Avg merge
- 2d 21h
- Merged PRs (30d)
- 84
Description
### Bug
The model recognizes the cell contents in the table incorrectly, especially when the contents of adjacent cells are mixed together or some cell contents are not fully recognized.
**bug 1: cell contents are not fully recognized.**
**bug 2: the contents of adjacent cells are mixed together**
### Steps to reproduce
docling --ocr --force-ocr --ocr-engine rapidocr --from pdf --to html --debug-visualize-cells --debug-visualize-tables tmpqn2gklzq.pdf
### Docling version
Docling version: 2.28.4
Docling Core version: 2.25.0
Docling IBM Models version: 3.4.1
Docling Parse version: 4.0.1
Python: cpython-312 (3.12.9)
Platform: Linux-6.14.1-arch1-1-x86_64-with-glibc2.41
### Python version
Python 3.12.9
Contributor guide
Assessment
This issue has not been assessed yet.