[GH-ISSUE #133] 是否可以用来做PDF OCR? #101

Open
opened 2026-10-26 21:12:08 +00:00 by bsakaguchi · 2 comments
Owner

Originally created by @williamswang23 on GitHub (Feb 3, 2025).
Original GitHub issue: https://github.com/deepseek-ai/Janus/issues/133

请教,这个模型是否可以用来对PDF进行OCR,包括公式和表格的识别?谢谢

Originally created by @williamswang23 on GitHub (Feb 3, 2025). Original GitHub issue: https://github.com/deepseek-ai/Janus/issues/133 请教,这个模型是否可以用来对PDF进行OCR,包括公式和表格的识别?谢谢
Author
Owner

@yunkchen commented on GitHub (Feb 6, 2025):

不太合适,输入分辨率限制是384*384

<!-- gh-comment-id:2639200664 --> @yunkchen commented on GitHub (Feb 6, 2025): 不太合适,输入分辨率限制是384*384
Author
Owner

@thiner commented on GitHub (Feb 8, 2025):

建议用qwen2.5-VL-7b.

<!-- gh-comment-id:2644744332 --> @thiner commented on GitHub (Feb 8, 2025): 建议用qwen2.5-VL-7b.
Sign in to join this conversation.
No labels
pull-request
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
deepseek-ai/Janus#101
No description provided.