Dataset used for training paddle OCR on Japanese text .

[amandhapola]

Hi,

I am interested in learning more about the datasets used to train the detection and recognition models of PaddleOCR for the Japanese language. Additionally, I am curious if it is possible to access these datasets so that I can examine the data firsthand. This would help me better understand the training process and potentially improve the model's performance for my specific use case.

Thanks.

[GreatV]

The training data is proprietary.