unable to open Cube language model params for hindi Language in tesseract

Question

Tesseract unable to read cube language model. tesseract 1.png output.txt -l hin After above command execution following error occur.

Cube ERROR (CubeRecoContext::Load): unable to read cube language model params from /usr/share/tesseract-ocr/tessdata/hin.cube.lm
Cube ERROR (CubeRecoContext::Create): unable to init CubeRecoContext object
init_cube_objects(false, &tessdata_manager):Error:Assert failed:in file tessedit.cpp, line 207
Segmentation fault

Where I get hin.cube.lm file and how to deal with that file?

I am also facing the same issue, Have you found any solutions? I just copied github hin files from tessedata to my local folder. — mridul, Oct 10 '16 at 14:07
@mridul I also do same thing. copy files to local folder, its work. — Madhav Nikam, Oct 16 '16 at 16:02

score 2 · Accepted Answer · answered Mar 28 '17 at 07:30

2

I fixed this error by installing the correct versions of the below files:

hin.cube.bigrams
hin.cube.fold
hin.cube.lm
hin.cube.nn
hin.cube.params
hin.cube.word-freq
hin.tesseract_cube.nn

Along with the correct versions of the Hindi AND English training data.

All above files are available at: https://github.com/tesseract-ocr/tesseract/wiki/Data-Files#data-files-for-version-304305

I put these files under: /usr/local/share/tessdata

This is on CentOS 7.2

answered Mar 28 '17 at 07:30

Vipul Swarup

323
3
17

where did you find those file ?? i managed to find only traineddata on github :( – Md. Sulayman Aug 10 '18 at 10:31
https://github.com/tesseract-ocr/tesseract/wiki/Data-Files#cube-data-files-for-version-304305 – Vipul Swarup Aug 12 '18 at 08:50
can you tell me where can i find cube data for other language like japan ?? i have found this one and thanks for your reply – Md. Sulayman Aug 13 '18 at 04:41

unable to open Cube language model params for hindi Language in tesseract

1 Answers1