Fine Tuning with Arabic about donut HOT 5 CLOSED

As a general tip, to train a model for a new language, you need to care about the token vocabulary/tokenizer. #11 would be useful to you :)

from donut.

@gwkrsrch please any help

from donut.

Hi @Mahmuod1 , there are several options you can take. You may modify the layout/textbox generation module to make the desired RTL layout. There would be several code lines to modify, e.g., textbox, layouts.
Another option is to generate the data with your own code based on SynthDoG. The followings are the main flow of the preliminary version of SynthDoG. The first step is to draw texts on a paper texture image. The following links would also be helpful to you.

• https://www.blog.pythonlibrary.org/2021/02/02/drawing-text-on-images-with-pillow-and-python
• https://stackoverflow.com/a/50189559

And then, using a perspective transformation (or other transformations), you can embed the synthetic paper into a background. Although the idea is simple, you will see some agreeable results. You may further enhance the quality of the generated samples via various techniques, but it is optional. Hope this helps :) Feel free to reopen this or open another issue if you have anything new for sharing.

from donut.

thanks, @gwkrsrch for your detailed instructions
can you please give me instructions for the donut model configuration that will be changed as it language specific
I will use the document parsing training so please can you tell me what should care about the training configurations

from donut.

Hi, @Mahmuod1, @gwkrsrch were you able to generate images using synthdog for RTL languages such as arabic.... any suggestions will help a lot..

from donut.