Go to file
Gašper Spagnolo 797ba0afea
Add the docs parsing, basically prediciton of new docs
2023-08-04 13:20:56 +02:00
dataset Add some more shit 2023-08-02 16:23:35 +02:00
ocr_test_db Add some more shit 2023-08-02 16:23:35 +02:00
.gitignore Add some more shit 2023-08-02 16:23:35 +02:00
README.md pk 2023-07-31 12:33:32 +02:00
dl.py LEts use multilingual model 2023-08-01 13:50:29 +02:00
ft.py Add the docs parsing, basically prediciton of new docs 2023-08-04 13:20:56 +02:00
generate_docs.py Add the docs parsing, basically prediciton of new docs 2023-08-04 13:20:56 +02:00
requirements.txt Add requirements.txt 2023-07-28 10:24:52 +02:00
run.py Add some more shit 2023-08-02 16:23:35 +02:00

README.md

{
  "e": 8223193,
  "n": 5007028,
  "a": 4617384,
  "i": 4617298,
  "r": 3806902,
  "o": 3506777,
  "s": 3286940,
  "t": 2994776,
  "d": 2877282,
  "l": 2330763,
  "u": 1676899,
  "h": 1566659,
  "g": 1525408,
  "m": 1402339,
  "v": 1304891,
  "k": 1268507,
  "c": 1191632,
  "j": 1138996,
  "b": 1102296,
  "p": 1097955,
  "z": 927699,
  "f": 467568,
  "č": 443139,
  ".": 438490,
  "w": 399028,
  "š": 290995,
  "ž": 250267,
  "ü": 212082,
  "S": 194575,
  "A": 192510,
  "ä": 169917,
  "1": 157447,
  "0": 145954,
  "B": 141047,
  "L": 137980,
  "D": 135820,
  "P": 135278,
  "G": 130277,
  "ß": 125683,
  "V": 116265,
  "K": 94573,
  "I": 90586,
  "H": 83761,
  "8": 82531,
  "W": 79459,
  "2": 79382,
  "E": 77487,
  "R": 70841,
  "ö": 70604,
  "M": 70215,
  "T": 68813,
  "N": 62789,
  ":": 59231,
  "3": 58524,
  ")": 58035,
  "(": 57753,
  "F": 56410,
  "5": 55914,
  "Z": 53670,
  "—": 52400,
  "4": 50003,
  "9": 49362,
  "6": 47439,
  "J": 45832,
  "O": 43816,
  "7": 41612,
  "U": 39562,
  "§": 24163,
  "C": 23519,
  "!": 14133,
  ",": 12041,
  "Ž": 10802,
  "„": 10249,
  "Š": 9210,
  "Č": 7467,
  "y": 6853,
  "'": 5763,
  "x": 5667,
  "%": 5265,
  "X": 4657,
  "©": 4404,
  "q": 3761,
  "“": 3749,
  "»": 3394,
  "«": 3270,
  "°": 2976,
  "/": 2151,
  ";": 1889,
  "Ü": 1693,
  "Q": 1521,
  "Ä": 1293,
  "?": 1107,
  "=": 1099,
  "-": 1063,
  "®": 1045,
  "■": 806,
  "\"": 791,
  "£": 695,
  "": 694,
  "|": 589,
  "•": 560,
  "_": 460,
  "Ö": 427,
  "": 306,
  "í": 304,
  "é": 297,
  "¿": 259,
  "\\": 193,
  "™": 164,
  "Y": 138,
  "]": 122,
  "á": 91,
  "[": 79,
  "ì": 72,
  "è": 61,
  "Ì": 53,
  "ó": 51,
  "□": 50,
  "à": 46,
  "¡": 46,
  "~": 45,
  "É": 34,
  "ò": 29,
  "+": 27,
  "đ": 22,
  "Í": 20,
  "€": 18,
  "}": 18,
  "ï": 16,
  "Ê": 15,
  "ê": 15,
  "î": 13,
  "а": 13,
  "б": 13,
  "{": 13,
  "È": 12,
  "ÿ": 11,
  "Î": 9,
  "â": 9,
  "”": 9,
  "ú": 7,
  "±": 6,
  "ù": 6,
  "।": 5,
  "♦": 5,
  "ë": 5,
  "À": 4,
  "Ć": 4,
  "Ï": 4,
  "Æ": 4,
  "Đ": 3,
  "Ç": 3,
  "ñ": 3,
  "Ó": 2,
  "Ò": 2,
  "ć": 2,
  "►": 2,
  "Û": 2,
  "Á": 2,
  "Ù": 1,
  "✓": 1,
  "Â": 1,
  "Ú": 1,
  "Ë": 1,
  "æ": 1,
  "œ": 1,
  "¥": 1,
  "ô": 1
}