Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model
AI & ML interests
Deep Learning Framework
Recent 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
6
pinned
Running
Featured
213
PaddleOCR-VL Online Demo
📈
Parse and recognize text in images
Sleeping
8
Doc2Page - Document to Webpage Converter
🏄
Convert docs to webpages using PaddleOCR and ERNIE
Running
76
PP-OCRv5 Online Demo
🌍
Universal-Scene Text Recognition Model with High-Accuracy
Running
31
PP-StructureV3 Online Demo
📊
Next-Gen High-Precision Doc Parsing Solution
Running
131
PaddleOCR
⚡
Extract text from images in multiple languages
models
77
PaddlePaddle/PP-DocLayoutV2_safetensors
Updated
•
49
•
2
PaddlePaddle/PaddleOCR-VL
Image-Text-to-Text
•
1.0B
•
Updated
•
12.4k
•
1.47k
PaddlePaddle/PP-DocLayoutV2
Updated
•
21.1k
•
18
PaddlePaddle/devanagari_PP-OCRv5_mobile_rec
Image-to-Text
•
Updated
•
531
PaddlePaddle/latin_PP-OCRv5_mobile_rec
Image-to-Text
•
Updated
•
36.7k
•
1
PaddlePaddle/ta_PP-OCRv5_mobile_rec
Image-to-Text
•
Updated
•
103
PaddlePaddle/te_PP-OCRv5_mobile_rec
Image-to-Text
•
Updated
•
72
PaddlePaddle/el_PP-OCRv5_mobile_rec
Image-to-Text
•
Updated
•
80
PaddlePaddle/cyrillic_PP-OCRv5_mobile_rec
Image-to-Text
•
Updated
•
250
PaddlePaddle/arabic_PP-OCRv5_mobile_rec
Image-to-Text
•
Updated
•
1.54k
•
3