Different language support
Open
- Dominant language
- Python
- Stars
- 9.1k
- Forks
- 777
- PR merge metrics
- No merged PRs in 30d
Description
I attempted to recognize documents in Romanian and Russian. The results were very poor, but the table structure was recognized well. How can I tune for specific languages/fonts ? Is there a possibility to pass recognition of elements to another framework/LLMs?
Contributor guide
No contributing guide indexed for this repository
Research direction
The issue mentions poor Romanian and Russian recognition despite good table-structure recognition, but names no files, tests, or entry points. Start by locating the language and font recognition configuration, then determine whether language-specific tuning or handoff to another framework is supported; completion criteria are not defined in the issue.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100