OCR models in `inference` and OCR models blocks in `workflows`
Open
Nobody has claimed this yet.
question
- Dominant language
- Python
- Stars
- 2.5k
- Forks
- 320
- Avg merge
- 1d 14h
- Merged PRs (30d)
- 133
Description
Search before asking
- I have searched the Inference issues and found no similar feature requests.
Question
We have OCRBlock encapsulating DocTR model, but there are other OCR models we may want to support.
This issue opens up a thread of discussion on that matter.
Additional
No response
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Begin by reading the OCRBlock implementation and the surrounding inference and workflows concepts mentioned in the issue, then compare how the existing DocTR model is encapsulated. The issue is an open discussion rather than a defined task, so a completed change would first require deciding which OCR models and workflow blocks should be supported and agreeing on acceptance criteria.
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
- 25/100