PaddlePaddle
Multi Language support of Paddle OCR3.0
🔎 Search before asking
- [x] I have searched the PaddleOCR Docs and found no similar bug report.
- [x] I have searched the PaddleOCR Issues and found no similar bug report.
- [x] I have searched the PaddleOCR Discussions and found no similar bug report.
🐛 Bug (问题描述)
I noticed that the PaddleOCR 3.0 recognition model (PP-OCRv5_server_rec) supports four languages:
-
Chinese
-
English
-
Traditional Chinese
-
Japanese
However, the supported languages for the PP-OCRv5_server_det (detection model) are not clearly specified. In previous versions, there were three separate detection models: one for English, one for Chinese, and a third for multilingual detection.
🏃♂️ Environment (运行环境)
OS： win11 IDE: VS2022
🌰 Minimal Reproducible Example (最小可复现问题的Demo)
from paddleocr import TextDetection model = TextDetection(model_name="PP-OCRv5_server_det") output = model.predict("general_ocr_001.png", batch_size=1) for res in output: res.print() res.save_to_img(save_path="./output/") res.save_to_json(save_path="./output/res.json")
Hello, the PP-OCRv5_server_det model has good support for many languages and can be used directly. If you encounter detection issues with specific languages or character sets, feel free to submit an issue to give us feedback.
Hi，feel free to submit your request directly in this issue: 👉 PaddleOCR Multilingual Support Request #15617
The issue has no response for a long time and will be closed. You can reopen or new another issue if are still confused.
From Bot
