Task
Image To Text
P
PaddlePaddle/PP-OCRv3_mobile_rec
Image To Text·PaddlePaddle· 1.6K· 1
PP-OCRv3mobilerec is a text line recognition model within the PP-OCRv3rec series, developed by the PaddleOCR team. PP-OCRv3 is an upgrade over PP-OCRv2. The overall framework retains the same pipeline as PP-OCRv2, with optimizations made to the detection and recognition models. The detection module is still optimized based on the DB algorithm, while the recognition module has replaced CRNN with th
# pull & run locally
pip install mlforge-sdk && mlforge pull PaddlePaddle/PP-OCRv3_mobile_rec
pip install mlforge-sdk && mlforge pull PaddlePaddle/PP-OCRv3_mobile_rec
Model details
Provider
PaddlePaddle
Framework
PaddleOCR
Size
10 MB
License
apache-2.0
Downloads
1.6K
Likes
1
Updated
2025-07-22
About PaddlePaddle/PP-OCRv3_mobile_rec
PP-OCRv3mobilerec is a text line recognition model within the PP-OCRv3rec series, developed by the PaddleOCR team. PP-OCRv3 is an upgrade over PP-OCRv2. The overall framework retains the same pipeline as PP-OCRv2, with optimizations made to the detection and recognition models. The detection module is still optimized based on the DB algorithm, while the recognition module has replaced CRNN with the latest text recognition algorithm, SVTR, which was recently accepted at IJCAI 2022, and has been adapted for industrial applications. It supports text line recognition in general Chinese and English scenarios, but mainly focuses on Chinese. The key accuracy metrics are as follow: