Hello all,
if you are interesting in downloading only some language of traineddata
from repositories (or different tagged version) have a look at
tessdata_downloader[1] .
I just released version 1.0 [2] . I created this script in python, but also
I was able to create windows 64bit "frozen" app
> I used the tessdata_fast file for English - are these different from
tessdata-ocr-eng that comes with Ubuntu?
The ppa has traineddata files from tessdata_fast. Ubuntu 18.04 will have
the same.
Older versions of ubuntu (wihout ppa) will have traineddata files for
tesseract 3.0x.
You can try
Hi George,
The OpenCL engine of tesseract is currently being renewed for improved
accuracy. The part that you are working with will not make it much faster
anymore, as the cost of small kernel launches outwheighs the cost of using
AVX2 or related instruction sets.
Be patient, OpenCL for
3 matches
Mail list logo