PaddleOCR 3.5: Running OCR and Document Parsing Tasks with a Transformers Backend
β’ 31
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
Articles
Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing
-
PaddlePaddle/PaddleOCR-VL-1.5
Image-Text-to-Text β’ 1.0B β’ Updated β’ 34.5k β’ 633 -
PaddleOCR-VL-1.5 Online Demo
π»73PaddleOCR-VL-1.5_Online_Demo
-
PaddlePaddle/PP-DocLayoutV3
Image Segmentation β’ Updated β’ 22.2k β’ 75 -
PaddlePaddle/PP-DocLayoutV3_safetensors
Object Detection β’ 33.3M β’ Updated β’ 401k β’ 25
PP-StructureV3 is a SOTA document parsing solution on OmniDocBench, supporting the conversion of PDFs and do cument images to Markdown and JSON.
-
PaddlePaddle/en_PP-OCRv4_mobile_rec
Image-to-Text β’ Updated β’ 26.4k β’ 3 -
PaddlePaddle/PP-OCRv4_mobile_det
Image-to-Text β’ Updated β’ 16.7k β’ 3 -
PaddlePaddle/PP-OCRv4_mobile_rec
Image-to-Text β’ Updated β’ 6.89k β’ 2 -
PaddlePaddle/PP-OCRv4_mobile_seal_det
Image-to-Text β’ Updated β’ 1.24k
Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model
-
PaddlePaddle/PaddleOCR-VL
Image-Text-to-Text β’ 1.0B β’ Updated β’ 11k β’ 1.61k -
PaddleOCR-VL Online Demo
π243Extract text, tables, formulas, and charts from images
-
PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model
Paper β’ 2510.14528 β’ Published β’ 126 -
PaddlePaddle/PP-DocLayoutV2
Object Detection β’ Updated β’ 9.07k β’ 29
PP-OCRv5 is the latest text recognition solution, supporting Simplified Chinese, Chinese Pinyin, Traditional Chinese, English, and Japanese
-
PP-OCRv5 Online Demo
π80Universal-Scene Text Recognition Model with High-Accuracy
-
PaddlePaddle/PP-OCRv5_mobile_det
Image-to-Text β’ Updated β’ 93.3k β’ 26 -
PaddlePaddle/PP-OCRv5_mobile_rec
Image-to-Text β’ Updated β’ 32.5k β’ 14 -
PaddlePaddle/PP-OCRv5_server_det
Image-to-Text β’ Updated β’ 593k β’ 65
-
PaddlePaddle/arabic_PP-OCRv3_mobile_rec
Image-to-Text β’ Updated β’ 2.61k β’ 2 -
PaddlePaddle/chinese_cht_PP-OCRv3_mobile_rec
Image-to-Text β’ Updated β’ 63 -
PaddlePaddle/cyrillic_PP-OCRv3_mobile_rec
Image-to-Text β’ Updated β’ 1.79k -
PaddlePaddle/devanagari_PP-OCRv3_mobile_rec
Image-to-Text β’ Updated β’ 1.66k
Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing
-
PaddlePaddle/PaddleOCR-VL-1.5
Image-Text-to-Text β’ 1.0B β’ Updated β’ 34.5k β’ 633 -
PaddleOCR-VL-1.5 Online Demo
π»73PaddleOCR-VL-1.5_Online_Demo
-
PaddlePaddle/PP-DocLayoutV3
Image Segmentation β’ Updated β’ 22.2k β’ 75 -
PaddlePaddle/PP-DocLayoutV3_safetensors
Object Detection β’ 33.3M β’ Updated β’ 401k β’ 25
Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model
-
PaddlePaddle/PaddleOCR-VL
Image-Text-to-Text β’ 1.0B β’ Updated β’ 11k β’ 1.61k -
PaddleOCR-VL Online Demo
π243Extract text, tables, formulas, and charts from images
-
PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model
Paper β’ 2510.14528 β’ Published β’ 126 -
PaddlePaddle/PP-DocLayoutV2
Object Detection β’ Updated β’ 9.07k β’ 29
PP-StructureV3 is a SOTA document parsing solution on OmniDocBench, supporting the conversion of PDFs and do cument images to Markdown and JSON.
PP-OCRv5 is the latest text recognition solution, supporting Simplified Chinese, Chinese Pinyin, Traditional Chinese, English, and Japanese
-
PP-OCRv5 Online Demo
π80Universal-Scene Text Recognition Model with High-Accuracy
-
PaddlePaddle/PP-OCRv5_mobile_det
Image-to-Text β’ Updated β’ 93.3k β’ 26 -
PaddlePaddle/PP-OCRv5_mobile_rec
Image-to-Text β’ Updated β’ 32.5k β’ 14 -
PaddlePaddle/PP-OCRv5_server_det
Image-to-Text β’ Updated β’ 593k β’ 65
-
PaddlePaddle/en_PP-OCRv4_mobile_rec
Image-to-Text β’ Updated β’ 26.4k β’ 3 -
PaddlePaddle/PP-OCRv4_mobile_det
Image-to-Text β’ Updated β’ 16.7k β’ 3 -
PaddlePaddle/PP-OCRv4_mobile_rec
Image-to-Text β’ Updated β’ 6.89k β’ 2 -
PaddlePaddle/PP-OCRv4_mobile_seal_det
Image-to-Text β’ Updated β’ 1.24k
-
PaddlePaddle/arabic_PP-OCRv3_mobile_rec
Image-to-Text β’ Updated β’ 2.61k β’ 2 -
PaddlePaddle/chinese_cht_PP-OCRv3_mobile_rec
Image-to-Text β’ Updated β’ 63 -
PaddlePaddle/cyrillic_PP-OCRv3_mobile_rec
Image-to-Text β’ Updated β’ 1.79k -
PaddlePaddle/devanagari_PP-OCRv3_mobile_rec
Image-to-Text β’ Updated β’ 1.66k