" is an integer (fast) model":
use the traineddata from https://github.com/tesseract-ocr/tessdata_best
repo.
On Friday, March 8, 2024 at 5:12:52 PM UTC+3 sct.pyt...@gmail.com wrote:
> Warning: LSTMTrainer deserialized an LSTMRecognizer!
> Error, data/eng/eng_num_vert.lstm is an integer (fast) m
You can give MODEL_NAME any value.
For specifying the path to data directory use:
DATA_DIR Data directory for output files, proto model, start model, etc.
Default: data
for example:
if MODEL_NAME=abc and DATA_DIR=data
you need to put the ground truth files (box, gt.txt & tif) in
'data/abc-groun
This might be
helpful: https://tesseract-ocr.github.io/tessdoc/tess4/Make-Box-Files.html
And also some details
in:
https://tesseract-ocr.github.io/tessdoc/tess4/TrainingTesseract-4.00.html#making-box-files
On Thursday, September 5, 2024 at 6:41:50 PM UTC+3 Danny wrote:
> Hi Zdenko,
> Thanks f
*Background*
I'm trying to use tesseract 5.3.3 on scanned old books written in Amharic
(which uses Ethiopic script).
*Major Shortcomings of amh.traineddata from tesseract*
*Difference in type of Ethiopic script:* there are Ethiopic script
characters in old Amharic texts that are not used in the
use in the third
> countries ( electric blackouts)
>
> Dear Menilik, we might need to put out hands together on this.
>
> On Sat, Jan 13, 2024, 11:21 AM Menelik Berhan wrote:
>
>> *Background*
>> I'm trying to use tesseract 5.3.3 on scanned old books written in Amhari
gt; perform better. Are u using linux?
>>
>> On Sat, Jan 13, 2024, 4:08 PM Menelik Berhan
>> wrote:
>>
>>> Thanks for your swift reply. It would be my pleasure to collaborate with
>>> you.
>>>
>>> I've noticed that there is are exten
And yes I'm using Ubuntu 20.04 on windows with WSL.
On Sun, Jan 14, 2024 at 4:06 PM Menelik Berhan
wrote:
> Yes I'm In addis.
> My pc is not that powerful either. But I could find a couple of good
> desktop PCs for the training.
>
> It would be my pleasure to meet in pe
7 matches
Mail list logo
