PaddleOCR
PaddleOCR copied to clipboard
英文识别模型完全识别不正确
尝试使用英文识别和检测模型,发现英文识别模型无法识别出文字。 将英文识别模型更换为中文识别模型时,可以正常识别 想确认一下下面链接的英文识别模型是否有误? https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_infer.tar
dec_model: en_PP-OCRv3_dec_infer rec_model: en_PP-OCRv3_rec_infer
figure:
[2022/10/14 11:47:34] ppocr DEBUG: dt_boxes num : 5, elapse : 0.609062671661377 [2022/10/14 11:47:34] ppocr DEBUG: rec_res num : 5, elapse : 0.18146085739135742 [2022/10/14 11:47:34] ppocr DEBUG: 0 Predict time of test/eng-1.png: 0.794s [2022/10/14 11:47:34] ppocr DEBUG: 蹿3骑更, 0.556 [2022/10/14 11:47:34] ppocr DEBUG: 忖鄙忖专捌蜿炎嫉鄙, 0.798 [2022/10/14 11:47:34] ppocr DEBUG: :要地鲶鄙备关问鲶田陂月关地鄙鄙鲶0里椤鲶炎忖嫉地鲶捌月鲶问忖专问炎忖专问捌鲶蜿陂地鲶鄙月炎蜿陂鲶关地炎炎鄙, 0.973
end: 2022-10-14 11:47:34.205996
[2022/10/14 11:47:34] ppocr DEBUG: The visualized image saved in ./inference_results/eng-1.png [2022/10/14 11:47:34] ppocr INFO: The predict total time is 1.2937397956848145
这个是编码问题,要设置一下dict
解决了,非常感谢
which dict to use for english rec?
This issue has been automatically marked as stale because it has not had recent activity. It will be closed in 7 days if no further activity occurs. Thank you for your contributions.