PP-OCRv6 on Hugging Face: 50-Language OCR from 1.5M to 34.5M Parameters
• 32
AI & ML interests
Deep Learning Framework
Recent Activity
Papers
HPD-Parsing: Hierarchical Parallel Document Parsing
PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training
Articles
Organization Card
PaddlePaddle on the Huggingface Hub
From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks
-
PaddlePaddle/PP-OCRv6_medium_det_safetensors
Image-to-Text • 22M • Updated • 2.43k • 129 -
PaddlePaddle/PP-OCRv6_small_det_safetensors
Image-to-Text • 2.48M • Updated • 475 • 26 -
PaddlePaddle/PP-OCRv6_tiny_det_safetensors
Image-to-Text • 438k • Updated • 106 • 27 -
PaddlePaddle/PP-OCRv6_medium_rec_safetensors
Image-to-Text • 19.2M • Updated • 1.54k • 25
Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training
-
PaddlePaddle/PaddleOCR-VL-1.6
Image-Text-to-Text • 1.0B • Updated • 37.8k • 433 -
PaddleOCR-VL-1.6 Online Demo
😻47PaddleOCR-VL-1.6_Online_Demo
-
PaddlePaddle/PP-DocLayoutV3
Image Segmentation • Updated • 17.7k • 108 -
PaddlePaddle/PP-DocLayoutV3_safetensors
Object Detection • 33.3M • Updated • 750k • 39
From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks
-
PaddlePaddle/PP-OCRv6_medium_det_safetensors
Image-to-Text • 22M • Updated • 2.43k • 129 -
PaddlePaddle/PP-OCRv6_small_det_safetensors
Image-to-Text • 2.48M • Updated • 475 • 26 -
PaddlePaddle/PP-OCRv6_tiny_det_safetensors
Image-to-Text • 438k • Updated • 106 • 27 -
PaddlePaddle/PP-OCRv6_medium_rec_safetensors
Image-to-Text • 19.2M • Updated • 1.54k • 25
Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training
-
PaddlePaddle/PaddleOCR-VL-1.6
Image-Text-to-Text • 1.0B • Updated • 37.8k • 433 -
PaddleOCR-VL-1.6 Online Demo
😻47PaddleOCR-VL-1.6_Online_Demo
-
PaddlePaddle/PP-DocLayoutV3
Image Segmentation • Updated • 17.7k • 108 -
PaddlePaddle/PP-DocLayoutV3_safetensors
Object Detection • 33.3M • Updated • 750k • 39
spaces 11
pinned
Running
Agents
Featured
256
PaddleOCR-VL Online Demo
📈
Extract text, tables, formulas, and charts from images
Running on Zero
MCP
6
HPD-Parsing
📄
Hierarchical parallel document parsing with a 1B VLM
Running
19
PP-OCRv6 Online Demo
📄
PP-OCRv6 OCR with ONNX Runtime CPU backend
Running
Agents
Featured
47
PaddleOCR-VL-1.6 Online Demo
😻
PaddleOCR-VL-1.6_Online_Demo
Running on Zero
Agents
9
Paddleocr 3.5 Transformers Demo
👁
Run OCR & Doc-Parsing with PaddleOCR 3.5 and Transforformers
Running
Agents
Featured
77
PaddleOCR-VL-1.5 Online Demo
😻
PaddleOCR-VL-1.5_Online_Demo
models 164
PaddlePaddle/PaddleOCR-VL-1.5
Image-Text-to-Text • 1.0B • Updated • 13k • 662
PaddlePaddle/PaddleOCR-VL
Image-Text-to-Text • 1.0B • Updated • 8.44k • 1.65k
PaddlePaddle/PaddleOCR-VL-1.6
Image-Text-to-Text • 1.0B • Updated • 37.8k • 433
PaddlePaddle/HPD-Parsing
Image-Text-to-Text • 1B • Updated • 9.01k • 98
PaddlePaddle/korean_PP-OCRv5_mobile_rec
Image-to-Text • Updated • 4.85k • 17
PaddlePaddle/PP-DocLayoutV3_safetensors
Object Detection • 33.3M • Updated • 750k • 39
PaddlePaddle/PP-DocLayoutV3
Image Segmentation • Updated • 17.7k • 108
PaddlePaddle/PP-OCRv6_tiny_rec_onnx
Image-to-Text • Updated • 2.91k • 19
PaddlePaddle/PP-OCRv6_small_rec_onnx
Image-to-Text • Updated • 9.04k • 20
PaddlePaddle/PP-OCRv6_medium_rec_onnx
Image-to-Text • Updated • 57.5k • 24
datasets 6
PaddlePaddle/Real5-OmniDocBench
Benchmark • Updated • 8.62k • 36
PaddlePaddle/GraphNet
Updated • 12 • 3
PaddlePaddle/PaddleOCR-VL_demo
Viewer • Updated • 23 • 12.3k • 2
PaddlePaddle/GSM8K_distilled_zh
Viewer • Updated • 8.79k • 145 • 2
PaddlePaddle/dureader_robust
Updated • 320 • 6
PaddlePaddle/duconv
Viewer • Updated • 36.9k • 105 • 3