Request : add arabic recognition model for v5

[elkizana]

Please add model that recognize Arabic characters like in V3 and V4. Thanks

[liuhongen1234567]

Hello, the Arabic recognition model is actually supported in v5; however, the current version does not allow specification through the lang parameter. You can refer to the code below.

from paddleocr import PaddleOCR

ocr = PaddleOCR(
use_doc_orientation_classify=False, # Disables document orientation classification model via this parameter
use_doc_unwarping=False, # Disables text image rectification model via this parameter
use_textline_orientation=False, # Disables text line orientation classification model via this parameter
text_recognition_model_name="arabic_PP-OCRv3_mobile_rec",
)
result = ocr.predict("arabic.png")
for res in result:
res.print()
res.save_to_img("output")
res.save_to_json("output")