Omer

You dont have to use square brackets when writing the section name i.e [16W1EMS1]. simply write 'sudo isw -w 16W1EMSI'. Same applies if you plan to use it as a...

can you please give the whole trace when using **sudo**. Also did you make any changes to the etc/isw.config file at all?

At a complete loss here but... A long shot, but can you confirm whether the **/etc/isw.conf** file exists in your systems directory. The ConfigParser doesn't give any logs if a...

You have removed the MSI_ADDRESS_DEFAULT section which is used to look up addresses in the EC. You have also removed other sections like cooler boost which you may need later....

I assume u r training just the recognition model, not detection model. Just some points from my side( I think number 2 maybe the most pertinent) - Please reconfirm whether...

Yes it worked fine for me on my custom.non English set- Thai dataset Like I mentioned above, I believe a better way, without looking at code( as the issue with...

You may use this doc provided by author for your reference : https://github.com/JaidedAI/EasyOCR/blob/master/custom_model.md

From my observations and understanding, having a lower train loss but with no boxes/worse precision /recall is quite understandable as the model is still training + I see from the...

> Dear @JaidedTeam > > I would like to fine-tune the EASY OCR in the handwritten Korean language, I am assuming that the pre-trained model is already trained in Korean...

is 6.67 the accuracy or some loss value ? seems like loss as 6.67 % accuracy itself is extremely low. There can be many things potentially to be done not...