unirec-0.1b training for korean, japanese and other dataset

[youcando9021-cmd]

@Topdu
Could you please let me know how I can train it for multiple datasets at once?

[Topdu]

You need to train a tokenizer on your own multilingual data. Replace the tokenizer-related files in the PATH vlm_ocr_config: &vlm_ocr_config ./configs/rec/unirec/unirec-0.1b with your own. Also, update the vocab_size in ./configs/rec/unirec/unirec-0.1b/config.json to match the vocabulary size of your tokenizer. For information on dataset creation, refer to https://github.com/Topdu/OpenOCR/blob/main/docs/unirec.md#finetuning-on-custom-dataset