Skip to content

[Feature]: Support the new SOTA model glm-OCR in the backend #1628

@MyButtermilk

Description

@MyButtermilk

Describe the proposed feature

https://docs.z.ai/guides/vlm/glm-ocr
https://huggingface.co/zai-org/GLM-OCR

A new strong OCR model called glm-ocr was released . It tops a lot of benchmarks and would be worthwhile to be supported by OCRmyPDF. Here are some benchmarks:

Image

Metadata

Metadata

Assignees

Labels

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions