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
View all activity
Organization Card
PaddlePaddle on the Huggingface Hub
spaces
4
Running
24
PP-OCRv5 Online Demo
🌍
Universal-Scene Text Recognition Model with High-Accuracy
Running
18
PP-StructureV3 Online Demo
📊
Next-Gen High-Precision Doc Parsing Solution
Running
96
PaddleOCR
⚡
Extract text from images in multiple languages
Running
1
Paddlepaddle Meets LLM
💬
When PaddlePaddle meets LLM
models
66
PaddlePaddle/PP-OCRv3_server_det
Image-to-Text
•
Updated
•
42
PaddlePaddle/PP-OCRv3_mobile_det
Image-to-Text
•
Updated
•
2.13k
PaddlePaddle/PP-Chart2Table
Image-to-Text
•
Updated
•
6.82k
•
1
PaddlePaddle/eslav_PP-OCRv5_mobile_rec
Image-to-Text
•
Updated
•
502
PaddlePaddle/korean_PP-OCRv5_mobile_rec
Image-to-Text
•
Updated
•
1.16k
PaddlePaddle/latin_PP-OCRv5_mobile_rec
Image-to-Text
•
Updated
•
5.43k
PaddlePaddle/PP-OCRv5_mobile_rec
Image-to-Text
•
Updated
•
11k
•
2
PaddlePaddle/PP-OCRv5_server_rec
Image-to-Text
•
Updated
•
51.7k
•
5
PaddlePaddle/PP-OCRv4_server_rec_doc
Image-to-Text
•
Updated
•
1.03k
PaddlePaddle/en_PP-OCRv4_mobile_rec
Image-to-Text
•
Updated
•
1.19k