buzzerstar - libraryv3 - textcat - LM - SOURCE CODE

<?php $ngrams = array (
  '_' => 800333,
  'e' => 343202,
  'i' => 174706,
  'n' => 160332,
  'a' => 160081,
  'r' => 133083,
  's' => 127619,
  'o' => 118679,
  't' => 110747,
  'd' => 106105,
  'e_' => 100250,
  'l' => 77365,
  'n_' => 65554,
  'ie' => 64031,
  'g' => 63191,
  'k' => 59088,
  'er' => 50882,
  '_d' => 45623,
  'ie_' => 45135,
  'u' => 44645,
  'an' => 43593,
  'v' => 43307,
  'm' => 42991,
  'di' => 41184,
  'en' => 37364,
  's_' => 36247,
  '_di' => 34567,
  'die' => 34166,
  'w' => 33806,
  'die_' => 32562,
  '_v' => 32129,
  '_die' => 32062,
  '_die_' => 31396,
  'in' => 31234,
  't_' => 30405,
  'h' => 30326,
  'p' => 30028,
  'b' => 29165,
  'te' => 28944,
  'ge' => 26900,
  'de' => 26475,
  'aa' => 25566,
  'r_' => 25527,
  '.' => 24122,
  '_i' => 22646,
  '._' => 22491,
  'an_' => 21310,
  'el' => 21144,
  '_s' => 20612,

... [truncated, 7955 more lines] ...

<?php $ngrams = array (
  '_' => 842435,
  'ا' => 282188,
  'ل' => 216646,
  'ي' => 156878,
  'م' => 126513,
  'ال' => 122375,
  'و' => 106517,
  '_ا' => 106168,
  'ن' => 99607,
  '_ال' => 98607,
  'ر' => 89828,
  'ت' => 84583,
  'ب' => 72736,
  'ة' => 68574,
  'ع' => 63922,
  'د' => 61184,
  'ة_' => 59823,
  'س' => 49702,
  'ف' => 49430,
  'ه' => 44028,
  'ك' => 40266,
  'ن_' => 39970,
  'ي_' => 39912,
  'ق' => 38891,
  '_م' => 37725,
  '_و' => 36582,
  'ح' => 33760,
  'أ' => 33030,
  'ج' => 28455,
  'ا_' => 25136,
  'لم' => 24901,
  '_ب' => 24654,
  '_ف' => 23278,
  'ية' => 22419,
  'م_' => 21534,
  'في' => 21345,
  'ت_' => 19578,
  'ل_' => 19506,
  '.' => 19437,
  'الم' => 19146,
  '_ع' => 18987,
  'ر_' => 18779,
  '_أ' => 18761,
  'ش' => 18271,
  '._' => 18254,
  'ية_' => 18047,
  'ان' => 18005,
  'وا' => 17879,
  'ط' => 17641,

... [truncated, 7955 more lines] ...

<?php $ngrams = array (
  '_' => 722234,
  'а' => 318815,
  'н' => 132538,
  'і' => 111661,
  'р' => 102029,
  'с' => 90959,
  'ы' => 88831,
  'к' => 81964,
  'л' => 79356,
  'е' => 76700,
  'т' => 68383,
  'о' => 66893,
  'я' => 62556,
  'д' => 62107,
  'в' => 61441,
  'м' => 57606,
  'у' => 50972,
  'а_' => 50270,
  'п' => 46872,
  'ц' => 44375,
  'з' => 44090,
  'ў' => 42393,
  'г' => 38434,
  '.' => 38230,
  'на' => 38197,
  'ра' => 37501,
  '._' => 33561,
  'і_' => 32699,
  'ка' => 31120,
  ',' => 30125,
  ',_' => 30108,
  '_п' => 28153,
  'б' => 26422,
  'ч' => 25658,
  'ва' => 24580,
  'э' => 24515,
  'й' => 24443,
  'я_' => 24079,
  'ан' => 23847,
  'ь' => 22437,
  'ар' => 22432,
  'х' => 21427,
  'та' => 21343,
  'ад' => 21071,
  'ас' => 20851,
  'ал' => 20846,
  'ы_' => 20362,
  '_с' => 20086,
  'ла' => 19006,

... [truncated, 7955 more lines] ...

<?php $ngrams = array (
  '_' => 782151,
  'а' => 228319,
  'и' => 176575,
  'о' => 160461,
  'е' => 154722,
  'н' => 140014,
  'т' => 134164,
  'р' => 108962,
  'с' => 93066,
  'а_' => 86218,
  'в' => 80879,
  'л' => 66677,
  'к' => 63428,
  'д' => 56582,
  'на' => 48126,
  'п' => 47460,
  'и_' => 44696,
  'м' => 39797,
  'з' => 36863,
  '_н' => 34278,
  'е_' => 34064,
  '_с' => 33137,
  'о_' => 32591,
  'г' => 32351,
  'я' => 31599,
  'на_' => 31351,
  '.' => 30628,
  'ъ' => 29705,
  ',' => 29248,
  ',_' => 29122,
  '_п' => 28250,
  '_на' => 28241,
  '._' => 27889,
  'у' => 27796,
  'ни' => 26749,
  'та' => 25417,
  'ра' => 25092,
  'ст' => 25059,
  'то' => 24581,
  'ат' => 24080,
  'ен' => 23633,
  'б' => 22933,
  'т_' => 22710,
  '_на_' => 22374,
  '_и' => 21915,
  'ан' => 21660,
  '_в' => 20782,
  'ва' => 20111,
  'те' => 19847,

... [truncated, 7955 more lines] ...

<?php $ngrams = array (
  '_' => 697760,
  'া' => 177366,
  'র' => 162755,
  '্' => 141363,
  'ে' => 132012,
  'ি' => 113257,
  'ন' => 93886,
  'ক' => 80835,
  'ত' => 71556,
  'য' => 71098,
  'ব' => 69427,
  'স' => 60940,
  'র_' => 56221,
  'ল' => 54999,
  'ম' => 51630,
  'ে_' => 47071,
  'প' => 46145,
  '়' => 41804,
  'য়' => 37079,
  'দ' => 36661,
  'ার' => 32822,
  'ু' => 32063,
  '_স' => 30080,
  '্র' => 28832,
  'ট' => 28764,
  'হ' => 27927,
  '_প' => 27688,
  '_ক' => 27172,
  '_ব' => 26603,
  'ের' => 25571,
  'জ' => 25290,
  '।' => 25129,
  'া_' => 24926,
  '।_' => 24629,
  '্য' => 24398,
  'ের_' => 23661,
  'শ' => 23654,
  'এ' => 23136,
  '_এ' => 21432,
  'ি_' => 20406,
  'গ' => 20392,
  'ী' => 20199,
  'ন_' => 20067,
  'ো' => 20021,
  'র্' => 19041,
  'ান' => 18468,
  'ই' => 17850,
  'রে' => 17766,
  'ন্' => 17616,

... [truncated, 7955 more lines] ...

<?php $ngrams = array (
  '_' => 831126,
  'e' => 253730,
  'a' => 222192,
  'r' => 141557,
  'n' => 141167,
  'o' => 117587,
  'i' => 102203,
  't' => 88148,
  'l' => 79155,
  'u' => 68490,
  'd' => 67662,
  's' => 62178,
  'h' => 59281,
  'z' => 52108,
  '_a' => 47332,
  'e_' => 44192,
  '_e' => 44135,
  'g' => 44108,
  'an' => 43125,
  'v' => 41126,
  'a_' => 40751,
  'n_' => 40440,
  'r_' => 39905,
  'm' => 39274,
  't_' => 36389,
  'ar' => 34003,
  'en' => 33571,
  'k' => 32862,
  ',' => 29069,
  ',_' => 28989,
  'er' => 27351,
  '_d' => 27224,
  'b' => 26089,
  're' => 24872,
  'ez' => 24205,
  'c' => 24193,
  'et' => 24171,
  '.' => 22527,
  'p' => 21778,
  '-' => 21615,
  '._' => 21392,
  'ou' => 19580,
  'nt' => 19412,
  's_' => 18956,
  'et_' => 18728,
  '_e_' => 17752,
  'ha' => 17574,
  'ar_' => 16915,
  'ne' => 16897,

... [truncated, 7955 more lines] ...

<?php $ngrams = array (
  '_' => 672259,
  'a' => 189122,
  'i' => 161707,
  'e' => 144452,
  'o' => 140511,
  'n' => 109484,
  'r' => 87145,
  'j' => 77514,
  's' => 74969,
  't' => 72052,
  'u' => 65731,
  'l' => 59095,
  'a_' => 56400,
  'k' => 55389,
  'v' => 50492,
  'd' => 50221,
  'e_' => 47383,
  'm' => 46952,
  'p' => 44599,
  'je' => 42102,
  'i_' => 38240,
  'g' => 31783,
  '.' => 28584,
  ',' => 27809,
  ',_' => 27712,
  '._' => 27450,
  '_s' => 27195,
  'na' => 25931,
  'u_' => 25620,
  'o_' => 24028,
  'z' => 24024,
  '_p' => 23749,
  'ra' => 21084,
  'an' => 20598,
  'b' => 20551,
  'ni' => 20543,
  'je_' => 20326,
  'st' => 19184,
  '_i' => 19001,
  'c' => 18321,
  'ij' => 17404,
  '_n' => 17352,
  'ko' => 16903,
  'en' => 16109,
  '_o' => 14800,
  'in' => 14714,
  '_j' => 14667,
  'ta' => 14536,
  '_u' => 14211,

... [truncated, 7955 more lines] ...

<?php $ngrams = array (
  '_' => 862995,
  'e' => 246155,
  'a' => 243051,
  's' => 148446,
  'i' => 147861,
  'r' => 136984,
  'n' => 131541,
  'l' => 130858,
  't' => 116650,
  'o' => 98661,
  'd' => 87124,
  'a_' => 79207,
  'c' => 72687,
  'u' => 71316,
  's_' => 64595,
  'm' => 55625,
  '_d' => 55463,
  'e_' => 49206,
  'p' => 48754,
  'de' => 47341,
  'es' => 45424,
  '_de' => 40780,
  'en' => 36847,
  '_e' => 34061,
  'er' => 33479,
  '_a' => 31628,
  'l_' => 29928,
  ',' => 29467,
  ',_' => 29414,
  '_l' => 28499,
  'de_' => 28414,
  'el' => 28165,
  'v' => 28162,
  '_de_' => 28027,
  'n_' => 27658,
  'g' => 27624,
  're' => 27033,
  'b' => 26830,
  'an' => 25976,
  'la' => 25793,
  '_p' => 25125,
  '.' => 24326,
  'al' => 23466,
  'ta' => 23420,
  'nt' => 23234,
  'es_' => 23232,
  't_' => 23037,
  '._' => 23015,
  'ar' => 22745,

... [truncated, 7955 more lines] ...

<?php $ngrams = array (
  '_' => 785084,
  'o' => 162422,
  'e' => 157607,
  'a' => 147337,
  'n' => 127848,
  't' => 101660,
  'i' => 96905,
  's' => 92750,
  'r' => 91992,
  'l' => 90728,
  'v' => 82647,
  'k' => 75115,
  'd' => 64599,
  'u' => 62722,
  'm' => 57451,
  'í' => 54142,
  'p' => 53140,
  'c' => 52033,
  'h' => 45809,
  'á' => 40136,
  'a_' => 39401,
  'z' => 38517,
  'y' => 37188,
  'e_' => 36515,
  'b' => 31883,
  '.' => 30807,
  '_p' => 30597,
  'j' => 30229,
  '_s' => 29338,
  '._' => 29097,
  'st' => 27108,
  '_v' => 26626,
  ',' => 26211,
  ',_' => 26107,
  'ě' => 25415,
  'o_' => 24847,
  'í_' => 24344,
  'é' => 23497,
  'ř' => 20439,
  'ov' => 20322,
  'ro' => 20104,
  'u_' => 19876,
  '_n' => 19309,
  'ní' => 19115,
  'na' => 18388,
  'ch' => 18373,
  'en' => 18009,
  'ý' => 17501,
  '_a' => 16946,

... [truncated, 7955 more lines] ...

<?php $ngrams = array (
  '_' => 721882,
  'a' => 157631,
  'e' => 139206,
  'd' => 137938,
  'n' => 134752,
  'r' => 124788,
  'y' => 120279,
  'i' => 108837,
  'o' => 95473,
  'l' => 86056,
  'w' => 57661,
  'g' => 54508,
  'n_' => 53452,
  'h' => 53355,
  'f' => 50273,
  't' => 49447,
  's' => 48603,
  '_y' => 43242,
  'u' => 40852,
  'd_' => 38426,
  'r_' => 37769,
  'dd' => 36590,
  'yn' => 34223,
  'c' => 33692,
  'm' => 32346,
  '_a' => 31459,
  'an' => 23278,
  '.' => 21897,
  'yn_' => 21757,
  'yd' => 21000,
  '._' => 20877,
  '_g' => 20324,
  ',' => 20021,
  ',_' => 19976,
  'b' => 19910,
  '_yn' => 19253,
  'ed' => 19132,
  'l_' => 18691,
  'ar' => 17978,
  'dd_' => 17579,
  'i_' => 17217,
  '_yn_' => 17113,
  'wy' => 16855,
  'ae' => 16840,
  'y_' => 16827,
  '\'' => 16411,
  'a_' => 16092,
  'er' => 16083,
  'th' => 16060,

... [truncated, 7955 more lines] ...

<?php $ngrams = array (
  '_' => 808234,
  'e' => 309485,
  'r' => 174235,
  'n' => 160281,
  't' => 136678,
  'a' => 134623,
  'i' => 129070,
  's' => 121559,
  'd' => 112553,
  'l' => 105388,
  'o' => 104255,
  'g' => 77006,
  'er' => 66489,
  'm' => 61766,
  'e_' => 60963,
  'k' => 59846,
  'en' => 54463,
  'de' => 52200,
  'f' => 49032,
  'r_' => 46671,
  'v' => 44423,
  'n_' => 42798,
  't_' => 39578,
  'u' => 38835,
  'b' => 34607,
  'h' => 31599,
  'an' => 30442,
  'er_' => 29683,
  '.' => 29048,
  'p' => 28917,
  'en_' => 28566,
  're' => 28425,
  '_s' => 28169,
  'et' => 27981,
  'te' => 27929,
  '._' => 26959,
  ',' => 26113,
  ',_' => 26035,
  'nd' => 25289,
  'st' => 23885,
  'g_' => 23677,
  '_d' => 23531,
  '_o' => 23286,
  '_f' => 23048,
  'or' => 22905,
  '_a' => 22891,
  'le' => 22655,
  'in' => 21972,
  'ge' => 21125,

... [truncated, 7955 more lines] ...

<?php $ngrams = array (
  '_' => 736432,
  'e' => 317006,
  'n' => 187184,
  'i' => 162176,
  'r' => 161893,
  't' => 124668,
  'a' => 122465,
  's' => 116118,
  'd' => 88957,
  'u' => 78660,
  'l' => 78023,
  'h' => 77844,
  'er' => 76294,
  'o' => 67244,
  'en' => 61084,
  'n_' => 60447,
  'c' => 54276,
  'g' => 53375,
  'm' => 49685,
  'e_' => 46862,
  'ch' => 45182,
  'r_' => 45050,
  'de' => 42353,
  '_d' => 37569,
  'b' => 35064,
  'er_' => 34941,
  'te' => 34704,
  'en_' => 33651,
  'in' => 32828,
  'ei' => 32456,
  '.' => 29871,
  'ie' => 29750,
  'f' => 29537,
  '._' => 28270,
  's_' => 26081,
  't_' => 24927,
  'nd' => 24731,
  ',' => 24214,
  ',_' => 24196,
  'k' => 23981,
  'un' => 23266,
  '_de' => 23020,
  'ge' => 22421,
  'w' => 21698,
  'z' => 21363,
  'st' => 20779,
  'an' => 20342,
  'S' => 19327,
  'es' => 19272,

... [truncated, 7955 more lines] ...

<?php $ngrams = array (
  '_' => 770247,
  'α' => 176637,
  'ο' => 164738,
  'τ' => 159551,
  'ι' => 128555,
  'ν' => 117873,
  'ε' => 115655,
  'ρ' => 89432,
  'σ' => 80366,
  'κ' => 78349,
  'η' => 72502,
  'ς' => 69836,
  'π' => 66409,
  'υ' => 64973,
  'μ' => 60750,
  'ς_' => 59866,
  '_τ' => 56915,
  'λ' => 55542,
  'ί' => 47776,
  'το' => 42602,
  'ό' => 41423,
  'ά' => 39184,
  'ου' => 39155,
  'α_' => 38185,
  'ν_' => 37827,
  'έ' => 32865,
  'ι_' => 32820,
  'γ' => 32380,
  'ο_' => 31492,
  'δ' => 30616,
  'τη' => 29695,
  'ή' => 27038,
  '_το' => 27026,
  '_σ' => 26658,
  'ω' => 26503,
  '_π' => 25434,
  'στ' => 25101,
  '_κ' => 24903,
  '_α' => 24392,
  ',' => 24011,
  '.' => 23751,
  ',_' => 23743,
  'αι' => 23713,
  'τα' => 23589,
  'κα' => 22620,
  'υ_' => 22389,
  'ου_' => 22257,
  'ικ' => 22062,
  '._' => 20726,

... [truncated, 7955 more lines] ...

<?php $ngrams = array (
  '_' => 865079,
  'e' => 244002,
  'a' => 178205,
  't' => 164922,
  'n' => 152918,
  'i' => 152690,
  'o' => 149569,
  'r' => 135200,
  's' => 124789,
  'h' => 90481,
  'l' => 85701,
  'd' => 76123,
  'e_' => 69499,
  'c' => 60909,
  'u' => 52893,
  '_t' => 48981,
  'm' => 48447,
  's_' => 46219,
  'he' => 43736,
  'th' => 43350,
  'f' => 41756,
  'n_' => 40571,
  '_a' => 40440,
  'd_' => 39243,
  'in' => 38946,
  'p' => 37409,
  'g' => 36730,
  'er' => 34990,
  'an' => 34486,
  '_th' => 33407,
  'he_' => 32109,
  'y' => 31834,
  'the' => 30691,
  'w' => 29919,
  '_the' => 28150,
  'on' => 28111,
  ',' => 27980,
  ',_' => 27779,
  'b' => 27060,
  't_' => 26574,
  'the_' => 25484,
  '_the_' => 25395,
  '_o' => 25077,
  '.' => 25024,
  're' => 24944,
  '._' => 22372,
  'r_' => 22039,
  '_i' => 21845,
  'at' => 21838,

... [truncated, 7955 more lines] ...

<?php $ngrams = array (
  '_' => 811396,
  'a' => 247925,
  'o' => 190357,
  'e' => 188593,
  'i' => 163620,
  'n' => 145232,
  'r' => 126928,
  'l' => 111625,
  't' => 110942,
  's' => 106272,
  'k' => 72248,
  'a_' => 68597,
  'd' => 68126,
  'u' => 61128,
  'j' => 57399,
  'o_' => 54661,
  'm' => 52275,
  'p' => 44683,
  'e_' => 43748,
  'la' => 42280,
  '_l' => 37561,
  'n_' => 35188,
  's_' => 34349,
  'j_' => 33901,
  '_d' => 32760,
  '_k' => 32489,
  'de' => 31847,
  'an' => 31490,
  'en' => 31410,
  '_e' => 31138,
  '_la' => 30221,
  'la_' => 30061,
  'ta' => 28935,
  'st' => 28560,
  'v' => 27903,
  'g' => 27678,
  '_la_' => 27613,
  ',' => 27491,
  ',_' => 27436,
  'on' => 26411,
  'is' => 26404,
  '_de' => 26034,
  '.' => 25258,
  'c' => 25222,
  'er' => 24807,
  'de_' => 24520,
  '._' => 23934,
  'aj' => 23929,
  '_de_' => 23187,

... [truncated, 7955 more lines] ...

<?php $ngrams = array (
  '_' => 884819,
  'e' => 261466,
  'a' => 241755,
  'o' => 170256,
  'n' => 150148,
  'i' => 142074,
  'r' => 137484,
  's' => 137232,
  'l' => 117270,
  'd' => 109258,
  't' => 94663,
  'c' => 87807,
  'u' => 78747,
  'e_' => 73173,
  'a_' => 72645,
  's_' => 54643,
  'de' => 54373,
  'm' => 52717,
  '_d' => 52703,
  'p' => 48206,
  'o_' => 47071,
  '_de' => 45544,
  '_e' => 44300,
  'n_' => 44150,
  'en' => 42517,
  'de_' => 36454,
  'es' => 34500,
  '_de_' => 34147,
  'la' => 31153,
  '_l' => 31051,
  'er' => 29331,
  'l_' => 29262,
  ',' => 27316,
  ',_' => 27265,
  '_c' => 26663,
  'os' => 26197,
  'b' => 25462,
  'ra' => 25343,
  '_p' => 25339,
  'ar' => 24862,
  'g' => 24850,
  '.' => 24792,
  'on' => 24704,
  'el' => 24695,
  '_a' => 24220,
  'nt' => 23679,
  'an' => 23227,
  're' => 22650,
  '._' => 22455,

... [truncated, 7955 more lines] ...

<?php $ngrams = array (
  '_' => 678624,
  'a' => 260412,
  'i' => 214399,
  'e' => 213643,
  's' => 176401,
  't' => 139385,
  'l' => 129718,
  'n' => 111939,
  'u' => 108975,
  'o' => 98577,
  'r' => 89699,
  'k' => 87717,
  'd' => 74685,
  'm' => 70757,
  'a_' => 46108,
  'v' => 41691,
  'g' => 38897,
  'st' => 37895,
  'e_' => 37417,
  'is' => 34189,
  'p' => 33965,
  'i_' => 33915,
  's_' => 33299,
  'se' => 33232,
  'h' => 32660,
  'j' => 32365,
  '.' => 29846,
  'li' => 29422,
  '_k' => 29409,
  'as' => 29104,
  ',' => 29044,
  ',_' => 28983,
  '._' => 28770,
  'al' => 27965,
  'ta' => 25483,
  'es' => 24397,
  'us' => 24162,
  'te' => 23489,
  'el' => 23303,
  'd_' => 22871,
  'in' => 21770,
  'ja' => 21531,
  'aa' => 20468,
  'an' => 20380,
  'ä' => 20101,
  'ri' => 19930,
  'ma' => 19858,
  'on' => 19836,
  '_s' => 19822,

... [truncated, 7955 more lines] ...

<?php $ngrams = array (
  '_' => 592523,
  'a' => 288752,
  'e' => 241623,
  'i' => 169785,
  'n' => 155022,
  'r' => 152550,
  't' => 138797,
  'o' => 106780,
  'k' => 96331,
  'z' => 84637,
  'u' => 84152,
  'en' => 68027,
  'l' => 61763,
  'n_' => 59253,
  'd' => 57126,
  'a_' => 54623,
  's' => 51965,
  'b' => 46991,
  '_e' => 41949,
  'an' => 40155,
  'ar' => 37689,
  'g' => 36965,
  're' => 36360,
  'ta' => 36250,
  'ak' => 33459,
  'er' => 33197,
  'en_' => 32701,
  '_z' => 31597,
  'ko' => 31346,
  'o_' => 30576,
  'et' => 30149,
  ',' => 27861,
  ',_' => 27794,
  '.' => 27748,
  'm' => 26850,
  '._' => 26789,
  'k_' => 25740,
  'zi' => 25088,
  'ra' => 24891,
  'at' => 24886,
  'te' => 24728,
  'ia' => 24395,
  '_b' => 23836,
  'p' => 23129,
  'ri' => 22785,
  'h' => 21970,
  'ze' => 21638,
  'eta' => 21161,
  'rr' => 21031,

... [truncated, 7955 more lines] ...

<?php $ngrams = array (
  '_' => 933252,
  'ا' => 270512,
  'ی' => 187803,
  'ر' => 155607,
  'ن' => 129060,
  'د' => 124893,
  'و' => 107257,
  'ه' => 106947,
  'م' => 94839,
  'ت' => 91556,
  'ب' => 76877,
  'س' => 70795,
  'ی_' => 60645,
  '_ا' => 59843,
  'ه_' => 54193,
  'ل' => 53618,
  'ک' => 52915,
  'ش' => 47623,
  'ر_' => 47005,
  '_ب' => 46853,
  'ان' => 44495,
  'ن_' => 43746,
  '_م' => 41201,
  '_د' => 40576,
  'ز' => 38517,
  'ای' => 36448,
  '‌' => 30602,
  '_و' => 27408,
  'ار' => 26769,
  'گ' => 26041,
  'د_' => 25302,
  'ست' => 24829,
  'ف' => 24749,
  'را' => 24548,
  'در' => 24513,
  'ت_' => 24430,
  'ا_' => 24132,
  'و_' => 23020,
  '_ک' => 22992,
  '_در' => 21948,
  '.' => 21882,
  'ع' => 21210,
  '._' => 20602,
  'اس' => 20323,
  'در_' => 19989,
  'ان_' => 19750,
  '_در_' => 19237,
  'خ' => 19221,
  'ین' => 18168,

... [truncated, 7955 more lines] ...

<?php $ngrams = array (
  '_' => 605122,
  'a' => 259898,
  'i' => 231668,
  'n' => 188542,
  't' => 177516,
  'e' => 171485,
  's' => 161657,
  'l' => 124246,
  'o' => 122901,
  'u' => 110184,
  'k' => 100164,
  'n_' => 80532,
  'ä' => 67468,
  'r' => 66547,
  'm' => 62205,
  'a_' => 59533,
  'en' => 44732,
  'v' => 43494,
  'j' => 41006,
  'in' => 40395,
  'ta' => 37357,
  'h' => 36993,
  'is' => 36451,
  'p' => 36068,
  'y' => 34885,
  'an' => 34679,
  'st' => 30303,
  '.' => 29271,
  '._' => 28429,
  'si' => 27392,
  'i_' => 27324,
  'en_' => 26629,
  'd' => 24352,
  'al' => 23935,
  '_k' => 23612,
  'tt' => 23272,
  'li' => 23262,
  'sa' => 22515,
  'aa' => 21773,
  'it' => 21720,
  'on' => 21598,
  'ja' => 21292,
  'ti' => 20969,
  '_j' => 20918,
  'll' => 20873,
  'se' => 20850,
  'la' => 20753,
  'ka' => 20575,
  'te' => 20374,

... [truncated, 7955 more lines] ...

<?php $ngrams = array (
  '_' => 883537,
  'e' => 298601,
  'a' => 162166,
  'n' => 154015,
  'i' => 153903,
  's' => 150457,
  'r' => 144508,
  't' => 141893,
  'l' => 116615,
  'o' => 115548,
  'e_' => 113371,
  'u' => 109667,
  'd' => 85934,
  'c' => 64275,
  's_' => 63832,
  '_d' => 60377,
  'm' => 53971,
  'p' => 53331,
  'é' => 47740,
  'es' => 45177,
  't_' => 43502,
  'de' => 41748,
  '_l' => 40766,
  'en' => 35709,
  '_de' => 35460,
  'le' => 34000,
  'on' => 33741,
  'n_' => 32193,
  're' => 30826,
  ',' => 30429,
  'es_' => 30249,
  ',_' => 30071,
  'nt' => 29770,
  '_e' => 29204,
  'de_' => 28550,
  'an' => 27361,
  '_p' => 26900,
  '_de_' => 25975,
  'g' => 24671,
  'v' => 24568,
  'er' => 22556,
  'r_' => 22107,
  'a_' => 22042,
  'h' => 21972,
  '_s' => 21964,
  '_c' => 21560,
  '.' => 21117,
  'f' => 20561,
  'ti' => 20484,

... [truncated, 7955 more lines] ...

<?php $ngrams = array (
  '_' => 833266,
  'a' => 298168,
  'i' => 192208,
  'n' => 159815,
  'h' => 146329,
  'r' => 117824,
  'e' => 112142,
  's' => 97132,
  't' => 88852,
  'l' => 80068,
  'c' => 76932,
  'o' => 76642,
  '_a' => 72085,
  'd' => 59852,
  'g' => 57024,
  'a_' => 55881,
  'n_' => 54259,
  'u' => 46384,
  'an' => 43404,
  'm' => 43255,
  'ai' => 42934,
  'ch' => 42689,
  'í' => 35142,
  'r_' => 35002,
  's_' => 34988,
  'in' => 34602,
  'ea' => 34549,
  'b' => 34134,
  'h_' => 34113,
  'á' => 33844,
  'ar' => 31522,
  'e_' => 30970,
  'na' => 29543,
  'ir' => 28819,
  '_s' => 27514,
  'é' => 26768,
  'ha' => 26246,
  ',' => 25269,
  ',_' => 25223,
  'ac' => 24402,
  'th' => 22690,
  '_c' => 22598,
  '.' => 22564,
  '_i' => 22508,
  'an_' => 21986,
  '_n' => 21927,
  '._' => 21818,
  'ach' => 21291,
  'is' => 21207,

... [truncated, 7955 more lines] ...

<?php $ngrams = array (
  '_' => 757063,
  'ા' => 204922,
  'ે' => 122487,
  'ર' => 111065,
  '્' => 105814,
  'ન' => 101097,
  'મ' => 82632,
  'ી' => 78536,
  'ત' => 72866,
  'ક' => 71913,
  'વ' => 71163,
  'ં' => 61273,
  'સ' => 52831,
  'ો' => 51646,
  'પ' => 49297,
  'લ' => 48564,
  'ય' => 47525,
  'િ' => 45848,
  'ે_' => 45111,
  'ી_' => 44064,
  'ા_' => 42848,
  'ુ' => 40106,
  'જ' => 36677,
  'ં_' => 34619,
  'મા' => 32870,
  'ાં' => 29861,
  '_પ' => 29345,
  'ગ' => 29263,
  'ટ' => 26315,
  '_સ' => 25481,
  '_ક' => 25128,
  'ના' => 24674,
  'દ' => 24417,
  'ાં_' => 24262,
  '.' => 23953,
  'આ' => 23871,
  'હ' => 23081,
  'માં' => 23025,
  '્ય' => 22992,
  '_મ' => 22940,
  '_આ' => 22490,
  '્ર' => 21767,
  'માં_' => 21459,
  'શ' => 21329,
  '._' => 21295,
  '_ત' => 20652,
  ',' => 20356,
  'છ' => 20286,
  ',_' => 19958,

... [truncated, 7955 more lines] ...

<?php $ngrams = array (
  '_' => 896669,
  'י' => 230408,
  'ו' => 228364,
  'ה' => 173092,
  'ל' => 129759,
  'ר' => 127855,
  'ת' => 113738,
  'ב' => 113231,
  'מ' => 103194,
  'א' => 95779,
  'ש' => 88053,
  '_ה' => 85078,
  'נ' => 73827,
  'ת_' => 60386,
  '_ב' => 54083,
  'ע' => 53139,
  'ם' => 53018,
  'ד' => 52213,
  'ה_' => 50464,
  'ק' => 50101,
  'פ' => 46547,
  'ח' => 45968,
  'ם_' => 43990,
  'ס' => 43570,
  'כ' => 39405,
  '_מ' => 36543,
  '_ש' => 35500,
  'ג' => 33689,
  '_ל' => 33668,
  'ים' => 33396,
  ',' => 33048,
  ',_' => 32921,
  'ות' => 32864,
  'ל_' => 32462,
  'ט' => 32388,
  '_א' => 31641,
  'ר_' => 28090,
  'י_' => 27595,
  'ן' => 27594,
  'ים_' => 26634,
  'צ' => 26489,
  '.' => 26280,
  '._' => 25121,
  '_ו' => 22513,
  'ן_' => 22502,
  'ו_' => 22431,
  'ות_' => 22153,
  'ני' => 20868,
  'רי' => 19801,

... [truncated, 7955 more lines] ...