PP-StructureV3 is a SOTA document parsing solution on OmniDocBench, supporting the conversion of PDFs and do cument images to Markdown and JSON.
PaddlePaddle
company
Verified
AI & ML interests
Deep Learning Framework
Recent Activity
Organization Card
PaddlePaddle on the Huggingface Hub
spaces
4
Running
14
PP-StructureV3 Online Demo
📊
Next-Gen High-Precision Doc Parsing Solution
Running
15
PP-OCRv5 Online Demo
🌍
Universal-Scene Text Recognition Model with High-Accuracy
Running
89
PaddleOCR
⚡
Extract text from images in multiple languages
Running
1
Paddlepaddle Meets LLM
💬
When PaddlePaddle meets LLM
models
63
PaddlePaddle/PP-Chart2Table
Updated
PaddlePaddle/PP-DocBee-2B
Image-to-Text
•
Updated
•
30
PaddlePaddle/PP-DocLayout-S
Image-to-Text
•
Updated
•
76
PaddlePaddle/PP-LCNet_x0_25_textline_ori
Image-to-Text
•
Updated
•
9
PaddlePaddle/PP-OCRv4_server_rec
Image-to-Text
•
Updated
•
409
PaddlePaddle/PP-DocLayout_plus-L
Image-to-Text
•
Updated
•
4.43k
PaddlePaddle/PP-DocBlockLayout
Image-to-Text
•
Updated
•
3.91k
PaddlePaddle/PicoDet-S_layout_3cls
Image-to-Text
•
Updated
•
18
PaddlePaddle/PP-FormulaNet-S
Image-to-Text
•
Updated
•
13
PaddlePaddle/japan_PP-OCRv3_mobile_rec
Image-to-Text
•
Updated
•
258