Giters
tesseract-ocr
/
tessdata_best
Best (most accurate) trained LSTM models.
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
1165
Watchers:
60
Issues:
56
Forks:
370
tesseract-ocr/tessdata_best Issues
How does Tesseract OCR fuse results from multiple models?
Updated
3 months ago
Tesseract can not detect @ sign in Turkish language
Updated
8 months ago
Comments count
1
Portuguese trained data fails to recognize @
Updated
8 months ago
Comments count
3
unclear/ambiguous language code notation
Updated
8 months ago
Comments count
10
Update all datasets that are older than 6 years and increase accuracy of the LSTM models
Closed
9 months ago
Comments count
7
Still getting extra spacing in between characters for jpn
Updated
a year ago
Poor results combining scripts
Updated
a year ago
convert eng training to h5 model
Updated
a year ago
Comments count
3
I'm encountered an obvious recognition error when using best eng model
Updated
a year ago
Ara language is showing "empty page!!" on one laptop and gives the answer on another
Closed
a year ago
Comments count
4
Segment error (core dumped)
Closed
a year ago
Comments count
2
Source of scripts/Fraktur etc.
Closed
a year ago
Comments count
8
old russian / church slavonic glyphs?
Updated
a year ago
Comments count
13
can you recommend the best traineddata for numbers and latin letters
Closed
a year ago
Comments count
4
Fine tuning training for a mix language tessdata
Closed
a year ago
Comments count
6
jpn.traineddata often interprets large もs as るs
Closed
a year ago
Comments count
1
best and fast should have the same config file
Updated
a year ago
Using tessdata_best files leads to error
Closed
2 years ago
Comments count
5
Hebrew david font support
Updated
a year ago
`chi_tra` does not recognize vertical text as the doc says
Updated
a year ago
finetune tesseract on 2 languages
Updated
2 years ago
Comments count
1
Invalid symlink makes tar fail
Closed
2 years ago
Comments count
3
Which language file should be downloaded?
Closed
2 years ago
Comments count
2
Ara language is showing "empty page!!" on one laptop and gives the answer on another
Closed
2 years ago
confusing on results of ARABIC COMMA (u060C) for fas.traineddata
Closed
3 years ago
Comments count
31
[ISSUE] (OSD) orientation script detection not supported using Tesseract best
Closed
3 years ago
Comments count
2
CHI_SIM molde load error
Closed
3 years ago
Comments count
1
Performance post Fine-Tuning
Updated
4 years ago
Fine Tuning
Closed
4 years ago
Comments count
1
eng.traineddata from tessdata_best on Android gives initialization error
Closed
4 years ago
Comments count
1
Can't use ita.traineddata
Closed
4 years ago
Comments count
2
"§" symbol is not recognized in German language models
Closed
4 years ago
Comments count
6
Not able to download the zip or clone this repo.
Closed
4 years ago
Comments count
1
Digit mixed up
Closed
4 years ago
Comments count
1
fra.traineddata corrupted ?
Closed
5 years ago
Comments count
3
Tesseract fails to recognize % sign in Hungarian language texts
Updated
5 years ago
Comments count
8
Fail to load standalone number or some words in Vietnamese
Closed
5 years ago
Comments count
1
tessdata_best failed loading language
Closed
5 years ago
Comments count
3
Polytonic characters on Greek trained data files
Updated
5 years ago
Wrong text recognition when there is a mix of numbers and characters
Updated
5 years ago
Comments count
1
request to add new fonts for Telugu language
Closed
6 years ago
Comments count
2
Add kur with Arabic unicharset (similar to old tessdata)
Updated
6 years ago
Comments count
3
Telugu unicode ambiguities
Updated
6 years ago
Comments count
5
Failed loading language 'eng'
Closed
6 years ago
Comments count
1
Failed to write core dump. Core dumps have been disabled. To enable core dumping, try "ulimit -c unlimited" before starting Java again
Closed
6 years ago
Comments count
1
Lao.traineddata and lao.traineddata names conflict on macOS filesystem
Closed
6 years ago
Comments count
4
Wrong encoding of accented characters in grc.traineddata
Closed
6 years ago
File Error Reporting: The Chi_Tra file is actually a Chi_Tra_vert file
Updated
6 years ago
Comments count
1
What's the difference between 'chi_sim.traineddata' and 'chi_sim_vert.traineddata'?
Closed
6 years ago
Comments count
2
Failed loading language 'Armenian' and 'hye'
Closed
7 years ago
Comments count
4
Previous
Next