epam / epam/badgerdoc

Tables, list, sub-/superscripts extractions support in OCRs

Open
#1,071 0 comments 0 reactions 0 assignees View on GitHub
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.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.