michelleyunun commited on
Commit
28bf6c0
·
1 Parent(s): 5a01870

Upload tokenizer

Browse files
Files changed (1) hide show
  1. tokenizer.json +1106 -2
tokenizer.json CHANGED
@@ -610,7 +610,559 @@
610
  "Ġfr": 548,
611
  "Ġfin": 549,
612
  "acar": 550,
613
- "ablar": 551
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
614
  },
615
  "merges": [
616
  "a r",
@@ -1089,7 +1641,559 @@
1089
  "Ġf r",
1090
  "Ġf in",
1091
  "ac ar",
1092
- "ab lar"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1093
  ]
1094
  }
1095
  }
 
610
  "Ġfr": 548,
611
  "Ġfin": 549,
612
  "acar": 550,
613
+ "ablar": 551,
614
+ "ropa": 552,
615
+ "che": 553,
616
+ "Ġpalabra": 554,
617
+ "vez": 555,
618
+ "Ġpe": 556,
619
+ "imero": 557,
620
+ "char": 558,
621
+ "fer": 559,
622
+ "Ġpu": 560,
623
+ "Ġfinado": 561,
624
+ "ara": 562,
625
+ "Ġcer": 563,
626
+ "pasar": 564,
627
+ "per": 565,
628
+ "est": 566,
629
+ "morir": 567,
630
+ "minar": 568,
631
+ "Ġprimero": 569,
632
+ "Ġma": 570,
633
+ "Ġaño": 571,
634
+ "agarrar": 572,
635
+ "si": 573,
636
+ "Ġre": 574,
637
+ "¡": 575,
638
+ "sacar": 576,
639
+ "Ġva": 577,
640
+ "nosotros": 578,
641
+ "Ġmal": 579,
642
+ "Ġba": 580,
643
+ "esposa": 581,
644
+ "Ġnoche": 582,
645
+ "Ġiglesia": 583,
646
+ "ué": 584,
647
+ "Ġdespué": 585,
648
+ "ecesidad": 586,
649
+ "Ġdespués": 587,
650
+ "Ġcier": 588,
651
+ "Ġmucho": 589,
652
+ "Ġlej": 590,
653
+ "Ġlejos": 591,
654
+ "Ġrecibir": 592,
655
+ "Ġcuán": 593,
656
+ "Ġcuándo": 594,
657
+ "AGT": 595,
658
+ "LAS": 596,
659
+ "ce": 597,
660
+ "una": 598,
661
+ "gual": 599,
662
+ "hay": 600,
663
+ "Ġhora": 601,
664
+ "Ġpapá": 602,
665
+ "za": 603,
666
+ "Ġca": 604,
667
+ "mar": 605,
668
+ "señar": 606,
669
+ "traer": 607,
670
+ "ga": 608,
671
+ "Ġmis": 609,
672
+ "ita": 610,
673
+ "mano": 611,
674
+ "ĠCLAS": 612,
675
+ "zar": 613,
676
+ "Ġcar": 614,
677
+ "lan": 615,
678
+ "ana": 616,
679
+ "Ġcierto": 617,
680
+ "Ġdar": 618,
681
+ "echar": 619,
682
+ "gente": 620,
683
+ "quier": 621,
684
+ "Ġcam": 622,
685
+ "ru": 623,
686
+ "enseñar": 624,
687
+ "Ġcomer": 625,
688
+ "ejo": 626,
689
+ "rir": 627,
690
+ "Ġ¡": 628,
691
+ "terminar": 629,
692
+ "Ġcerro": 630,
693
+ "Ġnecesidad": 631,
694
+ "uera": 632,
695
+ "Ġpadre": 633,
696
+ "abuelo": 634,
697
+ "Ġigual": 635,
698
+ "hablar": 636,
699
+ "Ġdi": 637,
700
+ "PREP": 638,
701
+ "ensar": 639,
702
+ "da": 640,
703
+ "ien": 641,
704
+ "Ġll": 642,
705
+ "ija": 643,
706
+ "comprar": 644,
707
+ "estar": 645,
708
+ "Ġpuro": 646,
709
+ "pañ": 647,
710
+ "én": 648,
711
+ "emp": 649,
712
+ "Ġfuerte": 650,
713
+ "Ġsegu": 651,
714
+ "Ġesta": 652,
715
+ "bra": 653,
716
+ "sent": 654,
717
+ "Ġtambi": 655,
718
+ "INS": 656,
719
+ "tirar": 657,
720
+ "ierba": 658,
721
+ "ambiar": 659,
722
+ "bien": 660,
723
+ "ación": 661,
724
+ "Ġcuev": 662,
725
+ "llevar": 663,
726
+ "Ġcueva": 664,
727
+ "edio": 665,
728
+ "ena": 666,
729
+ "ños": 667,
730
+ "nos": 668,
731
+ "Ġmil": 669,
732
+ "mu": 670,
733
+ "Ġcuanto": 671,
734
+ "gunos": 672,
735
+ "Ġalgunos": 673,
736
+ "pañero": 674,
737
+ "tes": 675,
738
+ "ĠS": 676,
739
+ "Ġtambién": 677,
740
+ "ĠM": 678,
741
+ "ble": 679,
742
+ "blo": 680,
743
+ "Ġmilpa": 681,
744
+ "Ġropa": 682,
745
+ "abuela": 683,
746
+ "Ġcor": 684,
747
+ "ivo": 685,
748
+ "Ġaños": 686,
749
+ "Ġcost": 687,
750
+ "Ġgal": 688,
751
+ "crecer": 689,
752
+ "uel": 690,
753
+ "ijol": 691,
754
+ "cam": 692,
755
+ "Ġsaber": 693,
756
+ "ongo": 694,
757
+ "Ġhongo": 695,
758
+ "it": 696,
759
+ "Ġdinero": 697,
760
+ "Ġla": 698,
761
+ "Ġven": 699,
762
+ "idar": 700,
763
+ "compadre": 701,
764
+ "óma": 702,
765
+ "ómago": 703,
766
+ "iar": 704,
767
+ "embra": 705,
768
+ "sa": 706,
769
+ "Ġdios": 707,
770
+ "Ġsalir": 708,
771
+ "ible": 709,
772
+ "eso": 710,
773
+ "conocer": 711,
774
+ "ri": 712,
775
+ "entro": 713,
776
+ "br": 714,
777
+ "Ġad": 715,
778
+ "orar": 716,
779
+ "año": 717,
780
+ "Ġcorrer": 718,
781
+ "enzar": 719,
782
+ "ender": 720,
783
+ "Ġder": 721,
784
+ "Ġcule": 722,
785
+ "Ġculebra": 723,
786
+ "Ġar": 724,
787
+ "EXS": 725,
788
+ "av": 726,
789
+ "Ġqu": 727,
790
+ "asar": 728,
791
+ "Ġmalo": 729,
792
+ "mon": 730,
793
+ "of": 731,
794
+ "ile": 732,
795
+ "Ġllegar": 733,
796
+ "Ġentrar": 734,
797
+ "Ġjugar": 735,
798
+ "orm": 736,
799
+ "je": 737,
800
+ "Ġay": 738,
801
+ "sentir": 739,
802
+ "fr": 740,
803
+ "dinero": 741,
804
+ "icio": 742,
805
+ "Ġfrijol": 743,
806
+ "pue": 744,
807
+ "Ġpos": 745,
808
+ "Ġquedar": 746,
809
+ "guantar": 747,
810
+ "Ġfav": 748,
811
+ "Ġfavor": 749,
812
+ "Ġvivo": 750,
813
+ "Ġalgo": 751,
814
+ "acias": 752,
815
+ "Ġpuer": 753,
816
+ "Ġdaño": 754,
817
+ "cocer": 755,
818
+ "Ġseñorita": 756,
819
+ "isteza": 757,
820
+ "cab": 758,
821
+ "tal": 759,
822
+ "Ġpalo": 760,
823
+ "Ġmisa": 761,
824
+ "ni": 762,
825
+ "Ġpuerta": 763,
826
+ "di": 764,
827
+ "Ġtal": 765,
828
+ "Ġnuera": 766,
829
+ "ina": 767,
830
+ "Ġsiembra": 768,
831
+ "ĠSan": 769,
832
+ "ace": 770,
833
+ "entar": 771,
834
+ "tro": 772,
835
+ "ici": 773,
836
+ "cabeza": 774,
837
+ "reg": 775,
838
+ "oso": 776,
839
+ "Ġcamino": 777,
840
+ "Ġderrepente": 778,
841
+ "Ġpara": 779,
842
+ "Ġmamá": 780,
843
+ "Ġcompañero": 781,
844
+ "Ġcostal": 782,
845
+ "cambiar": 783,
846
+ "her": 784,
847
+ "Ġbien": 785,
848
+ "inco": 786,
849
+ "el": 787,
850
+ "Ġgalán": 788,
851
+ "ura": 789,
852
+ "segu": 790,
853
+ "acate": 791,
854
+ "Ġpapa": 792,
855
+ "cal": 793,
856
+ "dea": 794,
857
+ "Ġlim": 795,
858
+ "cio": 796,
859
+ "estómago": 797,
860
+ "nar": 798,
861
+ "ON": 799,
862
+ "Ġhierba": 800,
863
+ "uv": 801,
864
+ "ven": 802,
865
+ "Ġpro": 803,
866
+ "ueg": 804,
867
+ "Ġsacate": 805,
868
+ "Ġpoder": 806,
869
+ "mujer": 807,
870
+ "Ġadentro": 808,
871
+ "Ġposible": 809,
872
+ "itación": 810,
873
+ "ndo": 811,
874
+ "Ġmedio": 812,
875
+ "pr": 813,
876
+ "señor": 814,
877
+ "carga": 815,
878
+ "yote": 816,
879
+ "Ġasi": 817,
880
+ "alar": 818,
881
+ "uerza": 819,
882
+ "ida": 820,
883
+ "Ġlad": 821,
884
+ "brero": 822,
885
+ "GN": 823,
886
+ "ĠGN": 824,
887
+ "ĠGNT": 825,
888
+ "pal": 826,
889
+ "saber": 827,
890
+ "Ġsembrar": 828,
891
+ "Ġhechar": 829,
892
+ "aguantar": 830,
893
+ "ñora": 831,
894
+ "Ġseñora": 832,
895
+ "Ġgu": 833,
896
+ "Ġmijo": 834,
897
+ "hija": 835,
898
+ "ubir": 836,
899
+ "incar": 837,
900
+ "Ġladino": 838,
901
+ "abrir": 839,
902
+ "Ġbuscar": 840,
903
+ "eja": 841,
904
+ "contar": 842,
905
+ "cordar": 843,
906
+ "oficio": 844,
907
+ "ormir": 845,
908
+ "Ġcan": 846,
909
+ "ante": 847,
910
+ "Ġseis": 848,
911
+ "lavar": 849,
912
+ "Ġvenado": 850,
913
+ "bar": 851,
914
+ "alquier": 852,
915
+ "Ġcualquier": 853,
916
+ "smo": 854,
917
+ "ve": 855,
918
+ "ombrero": 856,
919
+ "mismo": 857,
920
+ "ig": 858,
921
+ "Ġgr": 859,
922
+ "Ġcinco": 860,
923
+ "sta": 861,
924
+ "uego": 862,
925
+ "Ġdifer": 863,
926
+ "Ġlluv": 864,
927
+ "Ġlluvia": 865,
928
+ "AF": 866,
929
+ "eto": 867,
930
+ "sem": 868,
931
+ "Ġtor": 869,
932
+ "Ġbar": 870,
933
+ "Ġcoyote": 871,
934
+ "pita": 872,
935
+ "Ġleña": 873,
936
+ "cado": 874,
937
+ "lpa": 875,
938
+ "Ġantes": 876,
939
+ "imba": 877,
940
+ "stru": 878,
941
+ "Ġsa": 879,
942
+ "Ġtra": 880,
943
+ "poco": 881,
944
+ "Ġenfr": 882,
945
+ "Ġenfrente": 883,
946
+ "joven": 884,
947
+ "Ġolla": 885,
948
+ "las": 886,
949
+ "Ġotros": 887,
950
+ "illa": 888,
951
+ "tate": 889,
952
+ "Ġju": 890,
953
+ "pueblo": 891,
954
+ "hechar": 892,
955
+ "sombrero": 893,
956
+ "enar": 894,
957
+ "anar": 895,
958
+ "Ġenfer": 896,
959
+ "Ġbo": 897,
960
+ "Ġlos": 898,
961
+ "Ġcuenta": 899,
962
+ "cara": 900,
963
+ "Ġjoven": 901,
964
+ "ire": 902,
965
+ "ayu": 903,
966
+ "sear": 904,
967
+ "ear": 905,
968
+ "hu": 906,
969
+ "uela": 907,
970
+ "Ġmar": 908,
971
+ "correr": 909,
972
+ "Ġbaile": 910,
973
+ "Ġlimitación": 911,
974
+ "Ġdiferente": 912,
975
+ "AU": 913,
976
+ "CAU": 914,
977
+ "dormir": 915,
978
+ "nacer": 916,
979
+ "tam": 917,
980
+ "queño": 918,
981
+ "ÃŃr": 919,
982
+ "comenzar": 920,
983
+ "sea": 921,
984
+ "pensar": 922,
985
+ "recordar": 923,
986
+ "amon": 924,
987
+ "Ġcomprar": 925,
988
+ "Ġman": 926,
989
+ "Ġmes": 927,
990
+ "entos": 928,
991
+ "oma": 929,
992
+ "lanco": 930,
993
+ "usar": 931,
994
+ "mana": 932,
995
+ "hermana": 933,
996
+ "Ġaun": 934,
997
+ "oler": 935,
998
+ "Ġseguro": 936,
999
+ "Ġaunque": 937,
1000
+ "ton": 938,
1001
+ "ñana": 939,
1002
+ "Ġlom": 940,
1003
+ "Ġmañana": 941,
1004
+ "Ġmano": 942,
1005
+ "lanici": 943,
1006
+ "uegro": 944,
1007
+ "tz": 945,
1008
+ "Ġmismo": 946,
1009
+ "tzal": 947,
1010
+ "Ġzo": 948,
1011
+ "Ġsara": 949,
1012
+ "guate": 950,
1013
+ "pepita": 951,
1014
+ "perder": 952,
1015
+ "Ġsaraguate": 953,
1016
+ "venta": 954,
1017
+ "Ġqui": 955,
1018
+ "Ġmi": 956,
1019
+ "Ġmeter": 957,
1020
+ "Ġdu": 958,
1021
+ "Ġve": 959,
1022
+ "untar": 960,
1023
+ "ismo": 961,
1024
+ "Ġpensar": 962,
1025
+ "Ġapar": 963,
1026
+ "Ġhaber": 964,
1027
+ "Ġtodos": 965,
1028
+ "atro": 966,
1029
+ "oÃŃr": 967,
1030
+ "Ġap": 968,
1031
+ "ueño": 969,
1032
+ "Ġestar": 970,
1033
+ "Ġlevantar": 971,
1034
+ "Ġverde": 972,
1035
+ "Ġcarn": 973,
1036
+ "Ġrande": 974,
1037
+ "Ġaire": 975,
1038
+ "resar": 976,
1039
+ "Ġcuatro": 977,
1040
+ "bajo": 978,
1041
+ "Ġmonte": 979,
1042
+ "uelta": 980,
1043
+ "veja": 981,
1044
+ "Ġblanco": 982,
1045
+ "Ġvi": 983,
1046
+ "Ġquin": 984,
1047
+ "grar": 985,
1048
+ "subir": 986,
1049
+ "des": 987,
1050
+ "Ġbr": 988,
1051
+ "Ġquetzal": 989,
1052
+ "Ġale": 990,
1053
+ "Ġher": 991,
1054
+ "regresar": 992,
1055
+ "mentos": 993,
1056
+ "Ġtan": 994,
1057
+ "ÃŃo": 995,
1058
+ "instru": 996,
1059
+ "Ġfuego": 997,
1060
+ "cutar": 998,
1061
+ "Ġdiez": 999,
1062
+ "seguir": 1000,
1063
+ "Ġsapo": 1001,
1064
+ "instrumentos": 1002,
1065
+ "can": 1003,
1066
+ "gado": 1004,
1067
+ "ojo": 1005,
1068
+ "Ġab": 1006,
1069
+ "Ġagarrar": 1007,
1070
+ "Ġcuar": 1008,
1071
+ "oria": 1009,
1072
+ "dela": 1010,
1073
+ "alta": 1011,
1074
+ "ascal": 1012,
1075
+ "emascal": 1013,
1076
+ "Ġtortilla": 1014,
1077
+ "Ġlomismo": 1015,
1078
+ "ED": 1016,
1079
+ "MED": 1017,
1080
+ "vir": 1018,
1081
+ "ste": 1019,
1082
+ "Ġsu": 1020,
1083
+ "edad": 1021,
1084
+ "Ġbajar": 1022,
1085
+ "Ġgracias": 1023,
1086
+ "fes": 1024,
1087
+ "desp": 1025,
1088
+ "Ġsem": 1026,
1089
+ "cortar": 1027,
1090
+ "Ġprofes": 1028,
1091
+ "palabra": 1029,
1092
+ "Ġprofesor": 1030,
1093
+ "reta": 1031,
1094
+ "Ġ???-???": 1032,
1095
+ "solo": 1033,
1096
+ "bolla": 1034,
1097
+ "ĠPP": 1035,
1098
+ "istoria": 1036,
1099
+ "ayudar": 1037,
1100
+ "--": 1038,
1101
+ "agua": 1039,
1102
+ "xtam": 1040,
1103
+ "pagar": 1041,
1104
+ "Ġpueblo": 1042,
1105
+ "uerzo": 1043,
1106
+ "Ġcabeza": 1044,
1107
+ "Ġviejo": 1045,
1108
+ "mirar": 1046,
1109
+ "sal": 1047,
1110
+ "sid": 1048,
1111
+ "ĠIsid": 1049,
1112
+ "Ġcal": 1050,
1113
+ "lote": 1051,
1114
+ "ĠIsidro": 1052,
1115
+ "iento": 1053,
1116
+ "Ġmo": 1054,
1117
+ "oni": 1055,
1118
+ "tristeza": 1056,
1119
+ "speto": 1057,
1120
+ "ioma": 1058,
1121
+ "ser": 1059,
1122
+ "tas": 1060,
1123
+ "Ġra": 1061,
1124
+ "Ġasta": 1062,
1125
+ "ach": 1063,
1126
+ "donar": 1064,
1127
+ "Ġhistoria": 1065,
1128
+ "asura": 1066,
1129
+ "idioma": 1067,
1130
+ "cuidar": 1068,
1131
+ "preci": 1069,
1132
+ "Ġunos": 1070,
1133
+ "Ġsentar": 1071,
1134
+ "abajar": 1072,
1135
+ "ranco": 1073,
1136
+ "Ġpequeño": 1074,
1137
+ "monio": 1075,
1138
+ "AFE": 1076,
1139
+ "xtamal": 1077,
1140
+ "precio": 1078,
1141
+ "jalar": 1079,
1142
+ "Ġplanici": 1080,
1143
+ "Ġ???-": 1081,
1144
+ "mandar": 1082,
1145
+ "creer": 1083,
1146
+ "Ġreg": 1084,
1147
+ "fuerza": 1085,
1148
+ "medad": 1086,
1149
+ "ped": 1087,
1150
+ "ral": 1088,
1151
+ "Ġpar": 1089,
1152
+ "llorar": 1090,
1153
+ "Ġzope": 1091,
1154
+ "brar": 1092,
1155
+ "bio": 1093,
1156
+ "cuela": 1094,
1157
+ "juntar": 1095,
1158
+ "suerte": 1096,
1159
+ "veces": 1097,
1160
+ "desear": 1098,
1161
+ "Ġsuegro": 1099,
1162
+ "gun": 1100,
1163
+ "Ġvuelta": 1101,
1164
+ "Ġdoce": 1102,
1165
+ "iviar": 1103
1166
  },
1167
  "merges": [
1168
  "a r",
 
1641
  "Ġf r",
1642
  "Ġf in",
1643
  "ac ar",
1644
+ "ab lar",
1645
+ "ro pa",
1646
+ "ch e",
1647
+ "Ġpal abra",
1648
+ "v ez",
1649
+ "Ġp e",
1650
+ "im ero",
1651
+ "ch ar",
1652
+ "f er",
1653
+ "Ġp u",
1654
+ "Ġfin ado",
1655
+ "ar a",
1656
+ "Ġc er",
1657
+ "pa sar",
1658
+ "p er",
1659
+ "e st",
1660
+ "m orir",
1661
+ "m inar",
1662
+ "Ġpr imero",
1663
+ "Ġm a",
1664
+ "Ġa ño",
1665
+ "a garrar",
1666
+ "s i",
1667
+ "Ġ re",
1668
+ "Â ¡",
1669
+ "s acar",
1670
+ "Ġv a",
1671
+ "no sotros",
1672
+ "Ġm al",
1673
+ "Ġb a",
1674
+ "espos a",
1675
+ "Ġno che",
1676
+ "Ġi glesia",
1677
+ "u é",
1678
+ "Ġdesp ué",
1679
+ "eces idad",
1680
+ "Ġdespué s",
1681
+ "Ġc ier",
1682
+ "Ġmu cho",
1683
+ "Ġl ej",
1684
+ "Ġlej os",
1685
+ "Ġ recibir",
1686
+ "Ġcu án",
1687
+ "Ġcuán do",
1688
+ "A GT",
1689
+ "L AS",
1690
+ "c e",
1691
+ "un a",
1692
+ "gu al",
1693
+ "h ay",
1694
+ "Ġh ora",
1695
+ "Ġpa pá",
1696
+ "z a",
1697
+ "Ġc a",
1698
+ "m ar",
1699
+ "se ñar",
1700
+ "tra er",
1701
+ "g a",
1702
+ "Ġm is",
1703
+ "i ta",
1704
+ "ma no",
1705
+ "ĠC LAS",
1706
+ "z ar",
1707
+ "Ġc ar",
1708
+ "l an",
1709
+ "an a",
1710
+ "Ġcier to",
1711
+ "Ġd ar",
1712
+ "e char",
1713
+ "g ente",
1714
+ "qu ier",
1715
+ "Ġc am",
1716
+ "r u",
1717
+ "en señar",
1718
+ "Ġcom er",
1719
+ "e jo",
1720
+ "r ir",
1721
+ "Ġ ¡",
1722
+ "ter minar",
1723
+ "Ġcer ro",
1724
+ "Ġn ecesidad",
1725
+ "uer a",
1726
+ "Ġp adre",
1727
+ "abue lo",
1728
+ "Ġi gual",
1729
+ "h ablar",
1730
+ "Ġd i",
1731
+ "P REP",
1732
+ "en sar",
1733
+ "d a",
1734
+ "i en",
1735
+ "Ġ ll",
1736
+ "i ja",
1737
+ "com prar",
1738
+ "e star",
1739
+ "Ġpu ro",
1740
+ "pa ñ",
1741
+ "é n",
1742
+ "em p",
1743
+ "Ġf uerte",
1744
+ "Ġse gu",
1745
+ "Ġest a",
1746
+ "b ra",
1747
+ "s ent",
1748
+ "Ġt ambi",
1749
+ "IN S",
1750
+ "t irar",
1751
+ "ier ba",
1752
+ "ambi ar",
1753
+ "bi en",
1754
+ "aci ón",
1755
+ "Ġc uev",
1756
+ "lle var",
1757
+ "Ġcuev a",
1758
+ "ed io",
1759
+ "en a",
1760
+ "ñ os",
1761
+ "no s",
1762
+ "Ġm il",
1763
+ "m u",
1764
+ "Ġcuan to",
1765
+ "gu nos",
1766
+ "Ġal gunos",
1767
+ "pañ ero",
1768
+ "t es",
1769
+ "Ġ S",
1770
+ "Ġtambi én",
1771
+ "Ġ M",
1772
+ "b le",
1773
+ "b lo",
1774
+ "Ġmil pa",
1775
+ "Ġ ropa",
1776
+ "abue la",
1777
+ "Ġc or",
1778
+ "iv o",
1779
+ "Ġa ños",
1780
+ "Ġco st",
1781
+ "Ġg al",
1782
+ "cre cer",
1783
+ "ue l",
1784
+ "ijo l",
1785
+ "c am",
1786
+ "Ġs aber",
1787
+ "on go",
1788
+ "Ġh ongo",
1789
+ "i t",
1790
+ "Ġd inero",
1791
+ "Ġl a",
1792
+ "Ġv en",
1793
+ "i dar",
1794
+ "com padre",
1795
+ "ó ma",
1796
+ "óma go",
1797
+ "i ar",
1798
+ "emb ra",
1799
+ "s a",
1800
+ "Ġd ios",
1801
+ "Ġs alir",
1802
+ "i ble",
1803
+ "es o",
1804
+ "cono cer",
1805
+ "r i",
1806
+ "ent ro",
1807
+ "b r",
1808
+ "Ġa d",
1809
+ "or ar",
1810
+ "a ño",
1811
+ "Ġcor rer",
1812
+ "en zar",
1813
+ "end er",
1814
+ "Ġd er",
1815
+ "Ġcu le",
1816
+ "Ġcule bra",
1817
+ "Ġ ar",
1818
+ "E XS",
1819
+ "a v",
1820
+ "Ġ qu",
1821
+ "as ar",
1822
+ "Ġmal o",
1823
+ "m on",
1824
+ "o f",
1825
+ "i le",
1826
+ "Ġ llegar",
1827
+ "Ġent rar",
1828
+ "Ġj ugar",
1829
+ "or m",
1830
+ "j e",
1831
+ "Ġa y",
1832
+ "sent ir",
1833
+ "f r",
1834
+ "d inero",
1835
+ "ic io",
1836
+ "Ġfr ijol",
1837
+ "p ue",
1838
+ "Ġp os",
1839
+ "Ġque dar",
1840
+ "gu antar",
1841
+ "Ġf av",
1842
+ "Ġfav or",
1843
+ "Ġv ivo",
1844
+ "Ġal go",
1845
+ "aci as",
1846
+ "Ġp uer",
1847
+ "Ġd año",
1848
+ "co cer",
1849
+ "Ġseñor ita",
1850
+ "ist eza",
1851
+ "c ab",
1852
+ "t al",
1853
+ "Ġpal o",
1854
+ "Ġmis a",
1855
+ "n i",
1856
+ "Ġpuer ta",
1857
+ "d i",
1858
+ "Ġt al",
1859
+ "Ġn uera",
1860
+ "in a",
1861
+ "Ġsi embra",
1862
+ "ĠS an",
1863
+ "ac e",
1864
+ "ent ar",
1865
+ "tr o",
1866
+ "ic i",
1867
+ "cab eza",
1868
+ "re g",
1869
+ "os o",
1870
+ "Ġcam ino",
1871
+ "Ġder repente",
1872
+ "Ġp ara",
1873
+ "Ġm amá",
1874
+ "Ġcom pañero",
1875
+ "Ġcost al",
1876
+ "c ambiar",
1877
+ "h er",
1878
+ "Ġb ien",
1879
+ "in co",
1880
+ "e l",
1881
+ "Ġgal án",
1882
+ "u ra",
1883
+ "se gu",
1884
+ "aca te",
1885
+ "Ġpa pa",
1886
+ "c al",
1887
+ "de a",
1888
+ "Ġl im",
1889
+ "ci o",
1890
+ "est ómago",
1891
+ "n ar",
1892
+ "O N",
1893
+ "Ġh ierba",
1894
+ "u v",
1895
+ "v en",
1896
+ "Ġp ro",
1897
+ "ue g",
1898
+ "Ġs acate",
1899
+ "Ġpo der",
1900
+ "mu jer",
1901
+ "Ġad entro",
1902
+ "Ġpos ible",
1903
+ "it ación",
1904
+ "n do",
1905
+ "Ġm edio",
1906
+ "p r",
1907
+ "se ñor",
1908
+ "car ga",
1909
+ "yo te",
1910
+ "Ġa si",
1911
+ "al ar",
1912
+ "uer za",
1913
+ "id a",
1914
+ "Ġl ad",
1915
+ "br ero",
1916
+ "G N",
1917
+ "Ġ GN",
1918
+ "ĠGN T",
1919
+ "p al",
1920
+ "s aber",
1921
+ "Ġs embrar",
1922
+ "Ġh echar",
1923
+ "a guantar",
1924
+ "ñ ora",
1925
+ "Ġse ñora",
1926
+ "Ġ gu",
1927
+ "Ġm ijo",
1928
+ "h ija",
1929
+ "u bir",
1930
+ "in car",
1931
+ "Ġlad ino",
1932
+ "ab rir",
1933
+ "Ġbu scar",
1934
+ "ej a",
1935
+ "con tar",
1936
+ "cor dar",
1937
+ "of icio",
1938
+ "orm ir",
1939
+ "Ġc an",
1940
+ "an te",
1941
+ "Ġse is",
1942
+ "la var",
1943
+ "Ġven ado",
1944
+ "b ar",
1945
+ "al quier",
1946
+ "Ġcu alquier",
1947
+ "s mo",
1948
+ "v e",
1949
+ "om brero",
1950
+ "mi smo",
1951
+ "i g",
1952
+ "Ġg r",
1953
+ "Ġc inco",
1954
+ "st a",
1955
+ "ue go",
1956
+ "Ġdi fer",
1957
+ "Ġll uv",
1958
+ "Ġlluv ia",
1959
+ "A F",
1960
+ "e to",
1961
+ "s em",
1962
+ "Ġt or",
1963
+ "Ġb ar",
1964
+ "Ġco yote",
1965
+ "pi ta",
1966
+ "Ġle ña",
1967
+ "c ado",
1968
+ "l pa",
1969
+ "Ġan tes",
1970
+ "im ba",
1971
+ "st ru",
1972
+ "Ġs a",
1973
+ "Ġt ra",
1974
+ "po co",
1975
+ "Ġen fr",
1976
+ "Ġenfr ente",
1977
+ "jo ven",
1978
+ "Ġo lla",
1979
+ "l as",
1980
+ "Ġo tros",
1981
+ "i lla",
1982
+ "ta te",
1983
+ "Ġj u",
1984
+ "pue blo",
1985
+ "h echar",
1986
+ "s ombrero",
1987
+ "en ar",
1988
+ "an ar",
1989
+ "Ġen fer",
1990
+ "Ġb o",
1991
+ "Ġl os",
1992
+ "Ġcu enta",
1993
+ "car a",
1994
+ "Ġ joven",
1995
+ "ir e",
1996
+ "ay u",
1997
+ "se ar",
1998
+ "e ar",
1999
+ "h u",
2000
+ "ue la",
2001
+ "Ġm ar",
2002
+ "cor rer",
2003
+ "Ġba ile",
2004
+ "Ġlim itación",
2005
+ "Ġdifer ente",
2006
+ "A U",
2007
+ "C AU",
2008
+ "d ormir",
2009
+ "n acer",
2010
+ "t am",
2011
+ "que ño",
2012
+ "ÃŃ r",
2013
+ "com enzar",
2014
+ "se a",
2015
+ "p ensar",
2016
+ "re cordar",
2017
+ "am on",
2018
+ "Ġcom prar",
2019
+ "Ġm an",
2020
+ "Ġm es",
2021
+ "ent os",
2022
+ "om a",
2023
+ "lan co",
2024
+ "u sar",
2025
+ "man a",
2026
+ "her mana",
2027
+ "Ġa un",
2028
+ "ol er",
2029
+ "Ġsegu ro",
2030
+ "Ġaun que",
2031
+ "t on",
2032
+ "ñ ana",
2033
+ "Ġl om",
2034
+ "Ġma ñana",
2035
+ "Ġma no",
2036
+ "lan ici",
2037
+ "ueg ro",
2038
+ "t z",
2039
+ "Ġmis mo",
2040
+ "tz al",
2041
+ "Ġ zo",
2042
+ "Ġs ara",
2043
+ "gua te",
2044
+ "pe pita",
2045
+ "per der",
2046
+ "Ġsara guate",
2047
+ "v enta",
2048
+ "Ġ qui",
2049
+ "Ġm i",
2050
+ "Ġm eter",
2051
+ "Ġd u",
2052
+ "Ġv e",
2053
+ "un tar",
2054
+ "is mo",
2055
+ "Ġp ensar",
2056
+ "Ġa par",
2057
+ "Ġh aber",
2058
+ "Ġtodo s",
2059
+ "a tro",
2060
+ "o ÃŃr",
2061
+ "Ġa p",
2062
+ "ue ño",
2063
+ "Ġe star",
2064
+ "Ġle vantar",
2065
+ "Ġver de",
2066
+ "Ġcar n",
2067
+ "Ġ rande",
2068
+ "Ġa ire",
2069
+ "re sar",
2070
+ "Ġcu atro",
2071
+ "ba jo",
2072
+ "Ġmon te",
2073
+ "uel ta",
2074
+ "v eja",
2075
+ "Ġb lanco",
2076
+ "Ġv i",
2077
+ "Ġqu in",
2078
+ "g rar",
2079
+ "s ubir",
2080
+ "de s",
2081
+ "Ġb r",
2082
+ "Ġque tzal",
2083
+ "Ġa le",
2084
+ "Ġh er",
2085
+ "reg resar",
2086
+ "m entos",
2087
+ "Ġt an",
2088
+ "ÃŃ o",
2089
+ "in stru",
2090
+ "Ġf uego",
2091
+ "cu tar",
2092
+ "Ġdi ez",
2093
+ "segu ir",
2094
+ "Ġsa po",
2095
+ "instru mentos",
2096
+ "c an",
2097
+ "g ado",
2098
+ "o jo",
2099
+ "Ġa b",
2100
+ "Ġa garrar",
2101
+ "Ġcu ar",
2102
+ "or ia",
2103
+ "de la",
2104
+ "al ta",
2105
+ "as cal",
2106
+ "em ascal",
2107
+ "Ġtor tilla",
2108
+ "Ġlom ismo",
2109
+ "E D",
2110
+ "M ED",
2111
+ "v ir",
2112
+ "st e",
2113
+ "Ġs u",
2114
+ "ed ad",
2115
+ "Ġba jar",
2116
+ "Ġgr acias",
2117
+ "f es",
2118
+ "de sp",
2119
+ "Ġs em",
2120
+ "cor tar",
2121
+ "Ġpro fes",
2122
+ "pal abra",
2123
+ "Ġprofes or",
2124
+ "re ta",
2125
+ "Ġ??? -???",
2126
+ "so lo",
2127
+ "bo lla",
2128
+ "ĠP P",
2129
+ "ist oria",
2130
+ "ayu dar",
2131
+ "- -",
2132
+ "a gua",
2133
+ "x tam",
2134
+ "pa gar",
2135
+ "Ġpue blo",
2136
+ "uer zo",
2137
+ "Ġcab eza",
2138
+ "Ġvi ejo",
2139
+ "m irar",
2140
+ "s al",
2141
+ "s id",
2142
+ "ĠI sid",
2143
+ "Ġc al",
2144
+ "lo te",
2145
+ "ĠIsid ro",
2146
+ "i ento",
2147
+ "Ġm o",
2148
+ "on i",
2149
+ "tr isteza",
2150
+ "sp eto",
2151
+ "i oma",
2152
+ "s er",
2153
+ "t as",
2154
+ "Ġ ra",
2155
+ "Ġa sta",
2156
+ "ac h",
2157
+ "do nar",
2158
+ "Ġh istoria",
2159
+ "as ura",
2160
+ "id ioma",
2161
+ "cu idar",
2162
+ "p reci",
2163
+ "Ġuno s",
2164
+ "Ġs entar",
2165
+ "aba jar",
2166
+ "ran co",
2167
+ "Ġpe queño",
2168
+ "mon io",
2169
+ "AF E",
2170
+ "xtam al",
2171
+ "preci o",
2172
+ "j alar",
2173
+ "Ġp lanici",
2174
+ "Ġ??? -",
2175
+ "man dar",
2176
+ "cre er",
2177
+ "Ġre g",
2178
+ "f uerza",
2179
+ "m edad",
2180
+ "p ed",
2181
+ "r al",
2182
+ "Ġp ar",
2183
+ "ll orar",
2184
+ "Ġzo pe",
2185
+ "b rar",
2186
+ "b io",
2187
+ "c uela",
2188
+ "j untar",
2189
+ "s uerte",
2190
+ "v eces",
2191
+ "de sear",
2192
+ "Ġs uegro",
2193
+ "gu n",
2194
+ "Ġv uelta",
2195
+ "Ġdo ce",
2196
+ "iv iar"
2197
  ]
2198
  }
2199
  }