Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model
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
spaces
6
pinned
Running
Featured
208
PaddleOCR-VL Online Demo
π
Parse and recognize text in images
Running
8
Doc2Page - Document to Webpage Converter
π
Convert docs to webpages using PaddleOCR and ERNIE
Running
75
PP-OCRv5 Online Demo
π
Universal-Scene Text Recognition Model with High-Accuracy
Running
29
PP-StructureV3 Online Demo
π
Next-Gen High-Precision Doc Parsing Solution
Running
127
PaddleOCR
β‘
Extract text from images in multiple languages
models
77
PaddlePaddle/PP-DocLayoutV2_safetensors
Updated
β’
22
PaddlePaddle/PaddleOCR-VL
Image-Text-to-Text
β’
1.0B
β’
Updated
β’
18.5k
β’
1.42k
PaddlePaddle/PP-DocLayoutV2
Updated
β’
21.9k
β’
14
PaddlePaddle/devanagari_PP-OCRv5_mobile_rec
Image-to-Text
β’
Updated
β’
721
PaddlePaddle/latin_PP-OCRv5_mobile_rec
Image-to-Text
β’
Updated
β’
46.7k
β’
1
PaddlePaddle/ta_PP-OCRv5_mobile_rec
Image-to-Text
β’
Updated
β’
151
PaddlePaddle/te_PP-OCRv5_mobile_rec
Image-to-Text
β’
Updated
β’
120
PaddlePaddle/el_PP-OCRv5_mobile_rec
Image-to-Text
β’
Updated
β’
108
PaddlePaddle/cyrillic_PP-OCRv5_mobile_rec
Image-to-Text
β’
Updated
β’
309
PaddlePaddle/arabic_PP-OCRv5_mobile_rec
Image-to-Text
β’
Updated
β’
1.5k
β’
3