Does donut suite for document struct?

Hi, i’m newbie to donut.

I wanna know, if i have a lot of images, like Restaurant Menu or Hospital Lab Report etc,

Can donut convert such photos into well-structured text? (not only date/ total charge/ address)


or can i feed those images into pretrained “donut-base-finetuned-cord-v2” for finetuned again?

Thank thee very much!