With opensourced data you will not be able to create (from scratch) the
same quality traineddata as Google provided.
However there are some projects that fine tuned Google model successfully
e.g. (UB-Mannheim/: https://madoc.bib.uni-mannheim.de/53748/ )
Zdenko
st 21. 6. 2023 o 4:38 Duy Khanh
Hi! Do you have the answer yet? Cause I am currently looking for it :D
Vào lúc 12:27:57 UTC+7 ngày Thứ Sáu, 16 tháng 4, 2021, venkat...@gmail.com
đã viết:
> Thank you that was helpful. So is it the same training set used for
> creating the default traindeddata files available in the repo?
>
>
Hi. Is the existing eng.training_text in langdata_lstm the full text corpus
used for training the eng.traineddata? Do we have a list of fonts used for
generating the images?
--
You received this message because you are subscribed to the Google Groups
"tesseract-ocr" group.
To unsubscribe from
https://github.com/tesseract-ocr/langdata and
https://github.com/tesseract-ocr/langdata_lstm provide input data that
could be useful for tesseract training.
I am not aware of Runic traineddata released by Google or contributors =>
you will need to create it by yourself.
Zdenko
ut 20. 6. 2023 o
Please follow the official training procedure [1], read the official
docs[2], or complain to the author of the tutorial you decide to follow.
[1] https://github.com/tesseract-ocr/tesstrain
[2] https://tesseract-ocr.github.io/tessdoc/
Zdenko
ut 20. 6. 2023 o 10:39 abhilash rao napísal(a):
>
Please do not post only the last error - usually, there is a problem before
and e,g, configure output could indicate a lot of...
Make sure you check the issue tracker where are already some hints on what
to check e.g.
https://github.com/tesseract-ocr/tesseract/issues/3980
i want create Number plate reading application can you help
On Tue, 20 Jun 2023 at 14:09, abhilash rao wrote:
> Hi guys,
> So I needed a help in generating line images using tesseract's text2image
> for Hindi Language.
> Details:
> I am using python script available on this repository
>
We now tried the same script on M1 based machine, and the error is as
follows:
CXXLD libtesseract_native.la
CXXLD libtesseract_ccutil.la
CXXLD libtesseract_lstm.la
CXXLD libtesseract.la
CXXLD tesseract
Undefined symbols for architecture arm64:
"tesseract::IntSimdMatrix::intSimdMatrixNEON",
Hi,
We have the same error, did you end up finding a solution?
On Wednesday, February 16, 2022 at 12:36:31 PM UTC+2 Oskar Gargas wrote:
> Hello,
>
> I try to compile Tesseract for macOS on arm64. I use the following
> commands:
>
> ```
> export LIBS="-lz -lpng -ljpeg -ltiff"
> export
>
I am trying hard to create a training model. However, it is showing me
unrecognisable arguments errors when generating the data using
tesstrain.sh, it is not recognising my font. Could you please help me?
Thanks
Serhat
Le mardi 20 juin 2023 à 11:03:07 UTC+2, Meth Man a écrit :
> Hey all. I'm
Hey all. I'm new to tesseract and I'm trying to find Futhark Runes on an
image via OCR. I can see there are training files for runes
(Runic.unicharset) but is there also a pre-generated language file that I
can use or wiull I have to train it myself?
I cant see anything related to
Hi guys,
So I needed a help in generating line images using tesseract's text2image
for Hindi Language.
Details:
I am using python script available on this
repository https://github.com/astutejoe/tesseract_tutorial.git which
basically reads a text file and splits it into lines and saves each as
Thanks for your reply, after many more googling and build attempts, I am
not even sure if this is supposed to work - compling arm64 library on an
Intel-based mac? Can anyone who tried this confirm this or give a
suggestion how to deal with it?
Thanks!
On Sunday, June 18, 2023 at 5:02:10 PM
13 matches
Mail list logo
