Hi Shree,
I replaced the line:
merge_unicharsets $(TESSDATA)/$(CONTINUE_FROM).lstm-unicharset
$(TRAIN)/my.unicharset "$@"
with:
cp "$(TRAIN)/my.unicharset" "data/unicharset"
(I write this in case someone else is following this thread).
And now I have a fine tuned brand new model with only
Many thanks. Downloaded and using.
Will wait for next ver.
On Sunday, July 1, 2018 at 12:21:19 AM UTC+5:30, shree wrote:
>
> I have uploaded a new version of traineddata file at
>
> https://github.com/Shreeshrii/tessdata_shreetest/blob/master/iast-layer-18003.traineddata
>
> Attached is the
in my opinion error is for font-type, for some font there is no error but
for some other fonts there is error
On Mon, Jul 2, 2018 at 9:15 AM, john wrote:
> I use tesseract 4.0.0-beta.1. downloaded from this link (UB mannheim)
>
Thx. you're right.
On Sunday, July 1, 2018 at 10:02:55 PM UTC+4:30, shree wrote:
>
> The font being used does not support English.
>
> On Sun, Jul 1, 2018 at 10:06 PM Zohreh Khosrobeygi > wrote:
>
>> Hi,
>> I have been training the text:
>>
>> 272-135031- BECAUSE YOU WERE SLEEPING INSTEAD
I have also updated the image to have everything as the same font/size/etc,
but still, tesseract just says "Error during processing." with seemingly
zero information as to why.
Has anyone ever experienced this? If I can't find anything else out, I
guess I'll just have to step through the page
also see https://github.com/tesseract-ocr/tesseract/issues/549
On Mon, Jul 2, 2018 at 7:45 PM Shree Devi Kumar
wrote:
> You can use find_fonts with your training_text to locate the fonts to use.
>
> Modify the following command to match your directory setup and try
>
> echo "## FIND FONTS
Great question, I'm stuck too with this just with Hebrew OCR.
Any suggestion?
On Tuesday, March 13, 2018 at 7:13:50 PM UTC+2, Harshit Dohare wrote:
>
> Hi,
>
> As far as I have looked into Tesseract, cube files are only available for
> Hindi and Arabic language.
> Check here -
It seems with all languages and revisions, people (including me) tend to
search a lot for answers here in the group.
So I have a suggestion,
Can the group administrator pin a message with a spreadsheet, which
consists the state of each revision with the corresponding language this
way it
Hi there,
I want to see the actual input images processed by tesseract usingthe
command -c tesseract and I used tessedit_write_images=TRUE.
However, when I pass multi-layer (mutiple pages) .tiff image to tesseract
the output tessinput.tif image only contains one layer, which is the last
Wrong filename format. The box should be named `eng.dmd.exp0.box`.
On Monday, July 2, 2018 at 7:40:26 AM UTC-5, James Lipham wrote:
>
> I have also updated the image to have everything as the same
> font/size/etc, but still, tesseract just says "Error during processing."
> with seemingly zero
You can use find_fonts with your training_text to locate the fonts to use.
Modify the following command to match your directory setup and try
echo "## FIND FONTS ##"
# Find fonts which can render your training_text. Run `fc-cache -vf` to
refresh cache.
# You can change the minimum
11 matches
Mail list logo
