Hugging Face's logo

openbmb
/
MiniCPM-OCR-1.0

Image-Text-to-Text
Safetensors
English
Chinese
minicpm-ocr
minicpm_ocr
ocr
document-parsing
multimodal
vision-language
table-recognition
formula-recognition
conversational
Eval Results
Model card Files
xet
 Community
14

Add parsing pipeline section to model card

#13
by wunu - opened
base: refs/heads/main
←
from: refs/pr/13
Discussion Files changed
+79
-2
wunu
 OpenBMB org

Add a 'Parsing pipeline' subsection under Model architecture describing the two-stage pipeline (PP-DocLayoutV3 layout detection in the SDK environment + region recognition over HTTP to a MiniCPM-OCR 1.0 inference service), with a new assets/parsing_pipeline.svg diagram.
Add parsing pipeline section to model card351630a6
Yirany changed pull request status to merged
wunu
 OpenBMB org

Superseded by #14 (same change, updated: SDK named minicpm-ocr to match the pip package, spelling unified to American English). Please review the new PR instead.
wunu
 OpenBMB org

Clarification: #13 has been merged - thank you! #14 is a small follow-up with revised wording in the new section: SDK renamed to minicpm-ocr (matching the pip package), spelling unified (recognized / rasterized), and a clearer PDF rasterization label in the diagram.

Sign up or log in to comment