summaryrefslogtreecommitdiff
path: root/libtextcat/data/new_fingerprints/lm/malay.lm
diff options
context:
space:
mode:
Diffstat (limited to 'libtextcat/data/new_fingerprints/lm/malay.lm')
-rw-r--r--libtextcat/data/new_fingerprints/lm/malay.lm400
1 files changed, 400 insertions, 0 deletions
diff --git a/libtextcat/data/new_fingerprints/lm/malay.lm b/libtextcat/data/new_fingerprints/lm/malay.lm
new file mode 100644
index 000000000000..911d0cfef150
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/malay.lm
@@ -0,0 +1,400 @@
+_ 87128
+a 50232
+n 25424
+e 18746
+i 18605
+an 14419
+u 12470
+k 11955
+t 11875
+r 11007
+d 9856
+g 9545
+m 9390
+s 8926
+l 8631
+n_ 8004
+an_ 7095
+p 6890
+a_ 6739
+b 6645
+ng 6630
+h 5964
+da 5153
+_d 5107
+er 4625
+ka 4448
+la 4339
+y 4323
+i_ 4295
+en 4159
+ya 3800
+ang 3778
+_m 3750
+o 3593
+. 3539
+._ 3310
+at 3288
+ah 3216
+_b 3199
+_s 3177
+ta 3076
+ra 3036
+_k 2949
+g_ 2939
+ng_ 2933
+ar 2915
+_p 2906
+me 2884
+ga 2781
+di 2778
+ak 2727
+al 2705
+_me 2671
+ang_ 2524
+h_ 2509
+ba 2508
+pa 2454
+kan 2449
+in 2437
+tu 2411
+_t 2376
+sa 2338
+_da 2276
+j 2276
+pe 2225
+, 2150
+k_ 2147
+ma 2143
+se 2138
+am 2131
+kan_ 2117
+_di 2082
+,_ 2079
+ke 2048
+un 2004
+be 1947
+_a 1925
+na 1871
+ti 1868
+ri 1861
+u_ 1857
+as 1854
+ny 1827
+ha 1789
+te 1788
+_pe 1768
+em 1750
+it 1737
+_i 1732
+_ke 1711
+yan 1706
+ad 1698
+ia 1673
+yang 1673
+_y 1668
+_ya 1655
+yang_ 1653
+_se 1648
+ah_ 1646
+_yan 1639
+_yang 1639
+ala 1612
+nya 1587
+el 1576
+ik 1571
+t_ 1568
+ai 1549
+men 1531
+eng 1522
+_men 1464
+nga 1441
+dan 1366
+_be 1365
+si 1343
+uk 1328
+ada 1299
+nt 1291
+__ 1287
+ap 1276
+ua 1265
+___ 1238
+- 1213
+ja 1211
+ber 1204
+gan 1203
+_ba 1193
+____ 1189
+ni 1181
+_te 1169
+c 1143
+ran 1141
+_____ 1140
+m_ 1127
+ara 1118
+per 1099
+le 1084
+_dan 1083
+dan_ 1079
+ngan 1060
+_dan_ 1050
+ya_ 1046
+at_ 1044
+da_ 1021
+li 1016
+aka 1013
+A 999
+r_ 999
+w 997
+eb 995
+lah 980
+ata 980
+ak_ 978
+nd 974
+_ber 955
+gi 936
+is 933
+il 931
+tu_ 923
+s_ 920
+gan_ 915
+mb 913
+wa 904
+ag 903
+ngan_ 898
+ter 887
+nya_ 877
+S 873
+ek 853
+ru 852
+_l 838
+ela 828
+itu 824
+ol 822
+aha 822
+ada_ 820
+pu 812
+di_ 807
+bu 807
+am_ 804
+ur 801
+tan 790
+mp 790
+_per 786
+_sa 784
+M 782
+ut 781
+us 779
+era 779
+lam 778
+lah_ 775
+asa 767
+ki 761
+ir 759
+de 756
+enga 750
+su 748
+du 741
+id 739
+" 733
+akan 732
+apa 728
+_S 724
+ul 721
+lu 717
+ari 717
+dal 704
+et 698
+es 698
+pad 688
+_ma 688
+_M 685
+ana 684
+bi 679
+pada 673
+dala 673
+l_ 671
+ep 664
+f 662
+_di_ 658
+B 655
+ing 655
+_j 654
+ika 653
+ku 650
+_. 644
+akan_ 642
+ama 637
+pen 636
+alam 634
+eh 634
+pada_ 633
+ai_ 632
+_ter 632
+K 631
+mu 628
+ju 628
+P 626
+mem 625
+au 622
+_mem 614
+lan 612
+_._ 611
+ntu 608
+lam_ 605
+um 601
+on 600
+gk 597
+_in 597
+ngk 597
+a. 584
+meng 582
+_meng 578
+alam_ 577
+_A 576
+aa 575
+uk_ 572
+_pen 569
+ban 569
+or 569
+st 566
+ay 566
+dar 565
+_pa 564
+a._ 564
+_h 562
+bah 562
+_P 560
+D 559
+ri_ 558
+ini 552
+_de 551
+rt 550
+aan 545
+_it 542
+_itu 542
+nda 540
+eri 540
+dalam 537
+_B 533
+_dal 532
+ip 532
+_dala 532
+ta_ 528
+_u 527
+ung 525
+ih 524
+aw 520
+_n 519
+atu 517
+ila 513
+mi 513
+leh 513
+ian 512
+tuk 509
+awa 508
+gu 506
+ert 506
+engan 505
+ole 504
+_K 501
+seb 497
+ca 496
+gg 493
+_ta 489
+ra_ 488
+ngg 488
+itu_ 487
+emb 482
+ni_ 482
+ida 482
+nj 482
+_ti 479
+man 478
+den 477
+_D 474
+_ka 473
+aj 470
+oleh 468
+n. 468
+n._ 464
+ngka 464
+gka 464
+dak 464
+anga 461
+ena 459
+san 458
+pat 458
+rk 458
+( 455
+ent 454
+agi 453
+) 451
+ia_ 450
+ge 450
+ab 449
+im 447
+_ini 446
+ntuk 445
+I 445
+ar_ 440
+N 439
+aan_ 436
+_la 433
+pi 432
+baha 431
+deng 430
+han 430
+bag 429
+eh_ 429
+hu 429
+denga 428
+_o 427
+na_ 427
+T 425
+leh_ 422
+_den 422
+ka_ 419
+any 415
+ud 415
+rang 414
+anya 413
+gi_ 412
+angan 412
+a, 411
+_deng 410
+ita 409
+kat 408
+re 408
+_( 406
+tuk_ 403
+aga 401
+ne 400
+and 399
+aya 398
+_dar 397
+a,_ 396
+ro 396
+ntuk_ 393
+eba 392
+aran 390
+_" 387
+ed 385
+end 384
+ko 383
+sa_ 381
+p_ 381
+ara_ 380
+_seb 379
+alah 379
+oleh_ 379
+an. 378
+dak_ 378
+eg 378
+hi 376
+dari 375
+an._ 375
+au_ 373
+bo 373
+ti_ 371
+ula 371