I'm using paddleOcr on windows, and when it comes to the point where I have to download the det, rec and text classifier files, I get the following error.
requests.exceptions.SSLError: HTTPSConnectionPool(host='paddleocr.bj.bcebos.com', port=443): Max retries exceeded with url: /dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar (Caused by SSLError(SSLError(1, '[SSL: WRONG_VERSION_NUMBER] wrong version number (_ssl.c:1129)')))
To bypass the download step and thus this error, I managed to manually download the det and rec file from:https://github.com/PaddlePaddle/PaddleOCR/files/9230410/rec_det_models.zip
However I could not find a way to get the Chinese angle classifier model which is also necessary. The URL given in all repos is for this model is: https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar I cannot reach this file manually and it fails to get downloaded on Windows.
I would value help in either:
- Fixing the Python Requests error above OR
- Sharing the ch_ppocr_mobile_v2.0_cls_infer.tar file OR
- If you've already installed PaddleOCR on your machine, if you could share the contents in your \ch_ppocr_mobile_v2.0_cls_infer folder. On my Windows machine this folder is located at C:\Users\yumna.paddleocr\whl\cls\ch_ppocr_mobile_v2.0_cls_infer
Edit 1: I managed to bypass the Python-requests error by replacing the HTTPS with HTTP. So now I managed to download the required ch_ppocr_mobile_v2.0_cls_infer.tar file. However now I get the following error. tarfile.ReadError: file could not be opened successfully
