Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model
PaddlePaddle
company
Verified
AI & ML interests
Deep Learning Framework
Recent Activity
View all activity
Papers
GraphNet: A Large-Scale Computational Graph Dataset for Tensor Compiler Research
PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model
Organization Card
PaddlePaddle on the Huggingface Hub
spaces
5
pinned
Running
159
PaddleOCR-VL Online Demo
📈
Recognize text and elements in images
Running
68
PP-OCRv5 Online Demo
🌍
Universal-Scene Text Recognition Model with High-Accuracy
Running
24
PP-StructureV3 Online Demo
📊
Next-Gen High-Precision Doc Parsing Solution
Running
127
PaddleOCR
⚡
Extract text from images in multiple languages
models
76
PaddlePaddle/PaddleOCR-VL
Image-Text-to-Text
•
1.0B
•
Updated
•
24.6k
•
1.18k
PaddlePaddle/PP-DocLayoutV2
Updated
•
11.5k
•
5
PaddlePaddle/devanagari_PP-OCRv5_mobile_rec
Image-to-Text
•
Updated
•
195
PaddlePaddle/latin_PP-OCRv5_mobile_rec
Image-to-Text
•
Updated
•
38.8k
•
1
PaddlePaddle/ta_PP-OCRv5_mobile_rec
Image-to-Text
•
Updated
•
74
PaddlePaddle/te_PP-OCRv5_mobile_rec
Image-to-Text
•
Updated
•
64
PaddlePaddle/el_PP-OCRv5_mobile_rec
Image-to-Text
•
Updated
•
137
PaddlePaddle/cyrillic_PP-OCRv5_mobile_rec
Image-to-Text
•
Updated
•
116
PaddlePaddle/arabic_PP-OCRv5_mobile_rec
Image-to-Text
•
Updated
•
569
PaddlePaddle/th_PP-OCRv5_mobile_rec
Image-to-Text
•
Updated
•
2.16k