Hello Wincent,
Thanks for the new version of package.
No errors regarding font now and not slow either.
Tested on Ubuntu.
On Mon, Feb 10, 2020 at 12:28 AM Wincent Balin
wrote:
> Hello Shree,
>
> I just uploaded new version of the package. About the fixes:
>
> 1. --fonts_dir: I added the
Re: max threads, please see
https://github.com/tesseract-ocr/tesseract/issues/263#issuecomment-455614504
I will test the new scripts later and report back
On Mon, Feb 10, 2020 at 12:28 AM Wincent Balin
wrote:
> Hello Shree,
>
> I just uploaded new version of the package. About the fixes:
>
>
Hello Shree,
I just uploaded new version of the package. About the fixes:
1. --fonts_dir: I added the default value of the fonts directory on
different platforms.
2. Amount of threads: I also capped the maximal amount of threads to the
number of CPUs.
Would you like to re-test it, please?
>
> By the way, I added a create_ground_truth utility, which creates .gt.txt
> files as well as the associated .tif files for every specified font, to
> the package. I think it could be useful for anyone who does not have a
> ground truth collection yet.
>
> Thanks, I tried it with latest
Thanks, Wincent.
I will try out the tools added by you.
I found a Unicode version of the ISRI evaluation tools at
https://github.com/eddieantonio/ocreval which handles the high range
Unicodepoints also. See
Hi Shree,
I am glad you find the package already useful :-) .
As to your question: I did not use the ocr-evaluation tools, only the
language_metrics utility. So, regrettably, I cannot help you here. But
maybe you could try the same utility too?
By the way, I added a create_ground_truth
Hi Wincent,
Thank you for sharing these tools. I find create-dictdata to be very useful.
I wanted to know if you have modified any ocr-evaluation tools to handle
the high unicode range such as for Akkadian language.
I was trying to test regarding Modi script (*Range*: U+11600..U+1165F;
(96
7 matches
Mail list logo
