PP-OCRv5 Online Demo
🌍
74
Universal-Scene Text Recognition Model with High-Accuracy
PP-OCRv5
PP-OCRv5 is the latest text recognition solution, supporting Simplified Chinese, Chinese Pinyin, Traditional Chinese, English, and Japanese
-
-
PaddlePaddle/PP-OCRv5_mobile_det
Image-to-Text • Updated • 86.2k • 16 -
PaddlePaddle/PP-OCRv5_mobile_rec
Image-to-Text • Updated • 7.45k • 7 -
PaddlePaddle/PP-OCRv5_server_det
Image-to-Text • Updated • 385k • 48 -
PaddlePaddle/PP-OCRv5_server_rec
Image-to-Text • Updated • 75.5k • 16 -
PaddlePaddle/latin_PP-OCRv5_mobile_rec
Image-to-Text • Updated • 46.2k • 1 -
PaddlePaddle/eslav_PP-OCRv5_mobile_rec
Image-to-Text • Updated • 2.44k -
PaddlePaddle/korean_PP-OCRv5_mobile_rec
Image-to-Text • Updated • 5.01k • 11 -
PaddlePaddle/PP-LCNet_x1_0_doc_ori
Image-to-Text • Updated • 504k • 2 -
PaddlePaddle/PP-LCNet_x1_0_textline_ori
Image-to-Text • Updated • 238k -
PaddlePaddle/PP-LCNet_x0_25_textline_ori
Image-to-Text • Updated • 2.97k -
PaddlePaddle/UVDoc
Image-to-Text • Updated • 622k • 6 -
PaddleOCR 3.0 Technical Report
Paper • 2507.05595 • Published • 18