does StyleText support long inputs with spaces between words?

[Ao-Lee]

I would like to ask does StyleText support sentence inputs (document style rather than single words from street views) with spaces between them? or would you have plans on that, many thanks

[an1018]

During training, StyleText takes images of size 32×320, so if the text is too long, the effect may not be good. Thanks for your suggestion, but the version of long inputs is not planned to be developed at this stage.

[Ao-Lee]

Thank you for answering. I would like to ask, when training a recognition model, does the model learn to recognize space when feeding input images containing only one word. Would StyleText support short words with white spaces that satisfy the input resolution (32×320). Another related question is: how does ppocr (to be more precisely, how does SVTR_LCNet) learn to recognize white space? Thanks you again

[an1018]

Spaces are not supported in styleText. For space recognition, , the blank area around a single word is relatively large, and may not be good effect. You can add a space category to the training dictionary, and then add some samples with spaces for training.