diff options
Diffstat (limited to 'libtextcat/data/new_fingerprints/lm/scots.lm')
-rw-r--r-- | libtextcat/data/new_fingerprints/lm/scots.lm | 400 |
1 files changed, 400 insertions, 0 deletions
diff --git a/libtextcat/data/new_fingerprints/lm/scots.lm b/libtextcat/data/new_fingerprints/lm/scots.lm new file mode 100644 index 000000000000..7aac457075f6 --- /dev/null +++ b/libtextcat/data/new_fingerprints/lm/scots.lm @@ -0,0 +1,400 @@ +_ 11688 +e 3223 +a 2469 +t 2269 +i 1928 +n 1903 +r 1414 +o 1406 +h 1369 +s 1249 +l 929 +n_ 890 +_t 862 +_a 843 +d 818 +e_ 798 +th 704 +w 661 +he 625 +an 612 +t_ 606 +u 592 +_th 575 +c 508 +s_ 471 +the 470 +, 469 +- 458 +in 455 +m 445 +,_ 440 +b 434 +g 429 +er 409 +ee 408 +_the 407 +k 402 +an_ 402 +f 385 +_w 378 +he_ 376 +the_ 364 +_an 362 +_o 360 +y 358 +_the_ 354 +_s 353 +_an_ 342 +a_ 335 +r_ 327 +_b 316 +d_ 303 +i_ 278 +en 277 +p 270 +ei 245 +A 236 +wa 232 +_A 231 +re 229 +in_ 229 +ui 218 +oo 217 +le 217 +ai 216 +et 212 +ti 209 +it 209 +_f 206 +te 204 +_a_ 203 +_m 202 +ha 200 +as 193 +on 188 +at 184 +_i 183 +_wa 183 +_c 182 +o_ 180 +or 178 +_h 176 +_g 169 +ch 165 +A_ 159 +_l 158 +_A_ 157 +st 156 +_d 155 +_ti 148 +. 148 +._ 146 +ke 144 +ti_ 143 +-- 143 +_o_ 142 +ow 142 +--- 140 +ed 138 +---- 138 +_r 137 +as_ 137 +y_ 136 +er_ 136 +----- 136 +ir 135 +aa 135 +la 131 +een 130 +ae 129 +_ti_ 128 +ra 126 +es 125 +nd 124 +de 120 +h_ 120 +ie 120 +ar 119 +ll 119 +nt 118 +ot 118 +en_ 115 +ma 115 +eet 113 +her 112 +el 112 +is 112 +' 112 +at_ 111 +ic 109 +se 108 +or_ 106 +wu 104 +me 104 +ne 103 +fo 102 +on_ 101 +was 99 +_was 98 +et_ 98 +ri 98 +_e 97 +_ma 97 +v 97 +_n 97 +! 97 +li 97 +ht 93 +hi 92 +_wu 92 +ng 91 +ro 91 +it_ 90 +ck 90 +_fo 90 +tha 90 +k_ 89 +il 89 +cht 86 +eet_ 86 +_p 86 +we 86 +_was_ 85 +was_ 85 +rt 84 +ed_ 83 +ter 83 +id 83 +ga 82 +; 82 +;_ 81 +ther 79 +tt 76 +air 76 +e, 75 +un 75 +ho 75 +for 74 +ge 74 +_st 73 +_y 72 +_he 72 +wh 71 +_on 71 +sh 70 +z 70 +e,_ 69 +bi 68 +_tha 68 +wui 67 +!_ 67 +ad 67 +een_ 66 +l_ 66 +ts 66 +_for 66 +n, 66 +_wh 65 +re_ 65 +be 65 +eh 64 +hat 64 +ns 64 +br 64 +g_ 64 +ui_ 64 +rr 64 +wui_ 63 +ni 63 +_wui 62 +ay 62 +s, 62 +pe 61 +n,_ 61 +bo 61 +al 61 +ye 61 +_bi 60 +oot 60 +na 60 +ang 60 +s,_ 59 +es_ 59 +ill 58 +that 58 +_wui_ 58 +nn 58 +eh_ 58 +oa 57 +han 57 +_that 56 +_br 56 +ca 56 +_ga 56 +ng_ 56 +um 55 +hat_ 55 +oon 55 +od 55 +for_ 55 +no 55 +ree 55 +_for_ 54 +_le 54 +ht_ 54 +ot_ 54 +_k 53 +rd 53 +ki 53 +aw 53 +nd_ 53 +_on_ 53 +_it 53 +ik 53 +t, 53 +_be 52 +that_ 52 +ve 52 +rn 52 +'s 51 +au 51 +co 51 +ich 51 +to 51 +lo 51 +t,_ 51 +ea 51 +tee 51 +lan 50 +fi 50 +_at 50 +am 50 +_in 50 +ere 50 +ur 50 +le_ 50 +nt_ 49 +'s_ 49 +hin 49 +yi 49 +hr 49 +ts_ 49 +_ca 48 +" 48 +ta 48 +cht_ 48 +-_ 48 +_as 47 +T 47 +ang_ 47 +lei 46 +_ma_ 46 +tr 46 +_ro 46 +fe 46 +ma_ 46 +icht 46 +_as_ 46 +der 46 +cl 46 +e- 45 +n- 45 +thr 45 +ba 45 +m_ 45 +st_ 45 +rt_ 45 +_u 45 +do 45 +_T 45 +im 44 +_se 44 +sk 44 +_la 44 +eik 44 +bit 43 +ike 43 +B 43 +kee 43 +tte 43 +di 43 +eed 43 +_B 42 +_aa 42 +her_ 42 +da 42 +ff 42 +tu 42 +ie_ 42 +_cl 42 +_ba 42 +oot_ 42 +bu 41 +eike 41 +oc 41 +hu 41 +_thr 41 +ther_ 41 +_co 41 +aa_ 41 +so 41 +_me 41 +H 41 +_H 40 +ke_ 40 +ert 40 +lu 40 +ist 40 +si 40 +iz 40 +ar_ 39 +uc 39 +thi 39 +ad_ 39 +ru 39 +owe 39 +gi 38 +_bit 38 +_do 38 +int 38 +bl 38 +ld 38 +_at_ 38 +lt 38 +ac 38 +_ha 38 +ae_ 38 +rs 37 +here 37 +ei_ 37 +han_ 37 +p_ 37 +is_ 37 +eth 37 +fa 37 +_sk 37 +ll_ 37 +ss 36 +bra 36 +wha 36 +gl 36 +ck_ 36 +pl 36 +lin 36 +ir_ 36 +ab 36 +_ther 36 +_da 35 +ce 35 +rin 35 +_oo 35 +rl 35 +wee 35 +and 35 +sa 35 +_yi 35 +_bra 35 +'d 35 +ds 35 +_bo 35 |