What should I do to fine-tune in Korean?

[soohyoen]

I'm going to fine-tune the OCR model in Korean.

I'm trying to ocr the floor plan data.
But there is a lack of text detection, so fine-tuning is needed.

But in the official documentation, you can see how to speak only English and Chinese.
https://www.paddleocr.ai/latest/en/version2.x/ppocr/model_train/detection.html#21-start-training

What should I do to make it Korean?

[liuhongen1234567]

Hello, the training process for a Korean text detection model is similar to that for Chinese and English. You just need to prepare the corresponding data according to the sample data requirements. For more details, you can refer to the documentation https://www.paddleocr.ai/latest/en/version3.x/module_usage/text_detection.html#411-prepare-dataset.