PaddlePaddle/PaddleOCR-VL
Image-Text-to-Text
•
Updated
•
3.82k
•
651
PaddleOCR-VL
Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model
Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model