Tables, list, sub-/superscripts extractions support in OCRs
- Dominant language
- Python
- Stars
- 44
- Forks
- 52
- PR merge metrics
- No merged PRs in 30d
Description
Currently, Badgerdoc 2 supports the following VLM-based OCRs:
DeepSeek OCR 2
MinerU
Paddle
Dots OCR
Each OCR workflow is responsible for preparing data in hOCR format. This task involves adapting OCR outputs to support tables, lists, and sub-/superscripts, where such extractions are supported by the VLM.
### Acceptance Criteria
**DeepSeek OCR 2**
- [x] Tables formatted in hOCR
- [ ] Sub-/superscripts formatted in hOCR
- [ ] Lists formatted in hOCR
**MinerU**
- [x] Tables formatted in hOCR
- [ ] Sub-/superscripts formatted in hOCR
- [ ] Lists formatted in hOCR
**Paddle**
- [ ] Tables formatted in hOCR
- [ ] Sub-/superscripts formatted in hOCR
- [ ] Lists formatted in hOCR
**Dots OCR**
- [ ] Tables formatted in hOCR
- [ ] Sub-/superscripts formatted in hOCR
- [ ] Lists formatted in hOCR
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.