62 Super Compressed Tesseract 4.0 OCR languages pack
by MisterGrizzly
Description
This pack contains 62 languages compatible with tesseract 4.0 only. Each language is maximally compressed, this has not negatively influenced the character recognition, but has only benefits.
This pack contains can be used to recognize images, PDF documents, business cards, numbers, digits
Benefits of this pack:
Shrink space in your App Store application using Tesseract languages 2410 times
You can upload all the pack on your app bundle and upload to App Store – 85 MB in total
You can reuse the languages given on several platforms such as: iOS, Android, Flutter, Cordova, Phone Gap, macOS and Linux App, web, desktop etc, wherever you use tesseract 4.0, just add this tessdata folder with these languages
A total of 62 OCR languages for tesseract 4.0
No hosting needed/li>
Compatible with: iOS, Android, Crossplatform like Flutter or Cordova or React Native, windows platforms
How to use:
1. Unzip main_files.zip
2. Unzip each language from .tar.gz to .traineddata
3. Drag and drop to your own tessdata
4. use
Full languages list:
1. Afrikaans
2. Albanian
3. Arabic
4. Azerbaijani
5. Bangli
6. Basque
7. Belarusian
8. Bulgarian
9. Catalan
10. Cherokee
11. Chinese, Simplified
12. Chinese, Traditional
13. Croatian
14. Czech
15. Danish
16. Dutch
17. English
18. Esperanto
19. Estonian
20. Finnish
21. French
22. Galician
23. German
24. Greek, Modern
25. Greek, Ancient
26. Hebrew
27. Hindi
28. Hungarian
29. Icelandic
30. Indonesian
31. Italian
32. Japanese
33. Kannada
34. Korean
35. Latvian
36. Lithuanian
37. Macedonian
38. Malay
39. Malayalam
40. Maltese
41. Middle English
42. Middle French
43. Norwegian Bokmål
44. Persian
45. Polish
46. Portuguese
47. Romanian
48. Russian
49. Serbian
50. Slovak
51. Slovenian
52. Spanish
53. Swahili
54. Swedish
55. Tagalog
56. Tamil
57. Telugu
58. Thai
59. Turkish
60. Ukrainian
61. Urdu
62. Vietnamese
Join the discussion
No comment for this product yet be the first who discuss with @
Comment
Ask on GitHub0 сomments