arp-trg / tokenizer.json
michelleyunun's picture
Upload tokenizer
93013b7
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 0,
"content": "<start>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 1,
"content": "<end>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 2,
"content": "<pad>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": null,
"pre_tokenizer": {
"type": "ByteLevel",
"add_prefix_space": false,
"trim_offsets": true,
"use_regex": true
},
"post_processor": {
"type": "ByteLevel",
"add_prefix_space": true,
"trim_offsets": false,
"use_regex": true
},
"decoder": {
"type": "ByteLevel",
"add_prefix_space": true,
"trim_offsets": true,
"use_regex": true
},
"model": {
"type": "BPE",
"dropout": null,
"unk_token": null,
"continuing_subword_prefix": null,
"end_of_word_suffix": null,
"fuse_unk": false,
"byte_fallback": false,
"vocab": {
"<start>": 0,
"<end>": 1,
"<pad>": 2,
"!": 3,
"\"": 4,
"'": 5,
"(": 6,
")": 7,
"+": 8,
",": 9,
"-": 10,
".": 11,
"0": 12,
"1": 13,
"2": 14,
"3": 15,
"4": 16,
"5": 17,
"6": 18,
"7": 19,
"8": 20,
"9": 21,
":": 22,
";": 23,
"<": 24,
">": 25,
"?": 26,
"A": 27,
"B": 28,
"C": 29,
"D": 30,
"E": 31,
"F": 32,
"G": 33,
"H": 34,
"I": 35,
"J": 36,
"K": 37,
"L": 38,
"M": 39,
"N": 40,
"O": 41,
"P": 42,
"Q": 43,
"R": 44,
"S": 45,
"T": 46,
"U": 47,
"V": 48,
"W": 49,
"X": 50,
"Y": 51,
"Z": 52,
"[": 53,
"]": 54,
"a": 55,
"b": 56,
"c": 57,
"d": 58,
"e": 59,
"f": 60,
"g": 61,
"h": 62,
"i": 63,
"j": 64,
"k": 65,
"l": 66,
"m": 67,
"n": 68,
"o": 69,
"p": 70,
"q": 71,
"r": 72,
"s": 73,
"t": 74,
"u": 75,
"v": 76,
"w": 77,
"x": 78,
"y": 79,
"z": 80,
"Ġ": 81,
"en": 82,
"ar": 83,
"st": 84,
"art": 85,
"end": 86,
"start": 87,
"Ġ<": 88,
"th": 89,
"Ġth": 90,
"er": 91,
"is": 92,
"at": 93,
"PL": 94,
"ST": 95,
"in": 96,
"an": 97,
"ĠI": 98,
"PA": 99,
"Ġthis": 100,
"PAST": 101,
"se": 102,
"ere": 103,
"on": 104,
"ER": 105,
"wh": 106,
"PER": 107,
"pa": 108,
"or": 109,
"it": 110,
"ow": 111,
"use": 112,
"PERF": 113,
"Ġthat": 114,
"pause": 115,
"to": 116,
"ĠIC": 117,
"Ġh": 118,
"ed": 119,
"and": 120,
"ll": 121,
"ay": 122,
"Ġb": 123,
"Ġs": 124,
"MPERF": 125,
"ĠPAST": 126,
"Ġwh": 127,
"ing": 128,
"ou": 129,
"le": 130,
"ti": 131,
"Ġand": 132,
"DU": 133,
"Ġo": 134,
"NA": 135,
"..": 136,
"for": 137,
"FU": 138,
"FUT": 139,
"li": 140,
"RE": 141,
"om": 142,
"DE": 143,
"ve": 144,
"DUP": 145,
"REDUP": 146,
"ut": 147,
"ch": 148,
"ke": 149,
"now": 150,
"IMPERF": 151,
"Ġa": 152,
"TA": 153,
",.": 154,
"ĠFUT": 155,
"CH": 156,
"DETA": 157,
"DETACH": 158,
"ea": 159,
"em": 160,
"Ġbut": 161,
"Ġhere": 162,
"Ġw": 163,
".-": 164,
"tion": 165,
"be": 166,
"Ġm": 167,
"ce": 168,
"ld": 169,
"AD": 170,
"ADV": 171,
"emen": 172,
"afor": 173,
"tioned": 174,
"ementioned": 175,
"aforementioned": 176,
"ri": 177,
"ers": 178,
"Ġ3": 179,
"RR": 180,
"RRPAST": 181,
"NARRPAST": 182,
"ĠNARRPAST": 183,
"Ġy": 184,
"re": 185,
"ver": 186,
"Ġli": 187,
"ell": 188,
"ĠIMPERF": 189,
"go": 190,
"lo": 191,
"ra": 192,
"there": 193,
"Ġ1": 194,
"EG": 195,
"NEG": 196,
"ther": 197,
"pers": 198,
"Ġlike": 199,
"ck": 200,
"id": 201,
"one": 202,
"ho": 203,
"here": 204,
"pe": 205,
"Ġthen": 206,
"Ġwhen": 207,
"ly": 208,
"know": 209,
"ge": 210,
"al": 211,
"gh": 212,
"kay": 213,
"me": 214,
"Ġokay": 215,
"OB": 216,
"op": 217,
"un": 218,
"12": 219,
"thing": 220,
"ĠIN": 221,
"IT": 222,
"all": 223,
"ome": 224,
"Ġt": 225,
"Ġwhat": 226,
"Ġf": 227,
"OBV": 228,
"Ġsin": 229,
"Ġd": 230,
"ju": 231,
".(": 232,
"Ġc": 233,
"Ġto": 234,
"Ġsince": 235,
"Ġnow": 236,
"oun": 237,
"ong": 238,
"ĠREDUP": 239,
"us": 240,
"just": 241,
"ĠA": 242,
"of": 243,
"what": 244,
"es": 245,
"Ġu": 246,
"ople": 247,
"people": 248,
"say": 249,
"no": 250,
"Ġ2": 251,
"ght": 252,
"Ġor": 253,
"Ġwhere": 254,
"od": 255,
"Ġthe": 256,
"as": 257,
"Ġuh": 258,
"paho": 259,
"chi": 260,
"rapaho": 261,
"ake": 262,
"fa": 263,
"ent": 264,
"Ġjust": 265,
"...": 266,
"that": 267,
"ill": 268,
"are": 269,
"Ġyou": 270,
"where": 271,
"way": 272,
"gr": 273,
"Ġthere": 274,
")-": 275,
"any": 276,
"ite": 277,
"Ġhe": 278,
"ain": 279,
"ir": 280,
"out": 281,
"ĠArapaho": 282,
"la": 283,
").": 284,
"so": 285,
"ha": 286,
"time": 287,
"do": 288,
"things": 289,
"Ġp": 290,
"BIT": 291,
"how": 292,
"'s": 293,
"rom": 294,
"MPER": 295,
"ab": 296,
"Ġwell": 297,
"NI": 298,
"cat": 299,
"Ġbe": 300,
"own": 301,
"di": 302,
"child": 303,
"Ġuhh": 304,
"Ġal": 305,
"STR": 306,
"Ġl": 307,
"other": 308,
"ound": 309,
"see": 310,
"he": 311,
"aid": 312,
"Ġold": 313,
"up": 314,
"IMPER": 315,
"Ġso": 316,
"tell": 317,
"Ġin": 318,
"locat": 319,
"when": 320,
"ide": 321,
"rive": 322,
"bo": 323,
"located": 324,
"eah": 325,
"ag": 326,
"ss": 327,
"Ġno": 328,
"na": 329,
"person": 330,
"ry": 331,
"fe": 332,
"eak": 333,
"Ġhow": 334,
"ack": 335,
"ro": 336,
"PO": 337,
"sp": 338,
"aybe": 339,
"Ġyeah": 340,
"Ġalso": 341,
"the": 342,
"Ġall": 343,
"good": 344,
"ant": 345,
"thus": 346,
"Ġmaybe": 347,
"from": 348,
"ith": 349,
"ne": 350,
"ive": 351,
"oman": 352,
"ITER": 353,
"Ġe": 354,
"Ġone": 355,
"father": 356,
"Ġst": 357,
"grand": 358,
"itt": 359,
"Ġover": 360,
"side": 361,
"get": 362,
"DUBIT": 363,
"around": 364,
"arrive": 365,
"ad": 366,
"Ġsome": 367,
"ĠINT": 368,
"Ġknow": 369,
"ter": 370,
"ĠDUBIT": 371,
"Ġit": 372,
"very": 373,
"AT": 374,
"im": 375,
"EN": 376,
"SS": 377,
"age": 378,
"DEF": 379,
"oo": 380,
"each": 381,
"ca": 382,
"ĠINDEF": 383,
"gu": 384,
"Ġtoo": 385,
"speak": 386,
"Ġthey": 387,
"back": 388,
"ittle": 389,
"ct": 390,
"AL": 391,
"POSS": 392,
"ĠINSTR": 393,
"ĠS": 394,
"alk": 395,
"ways": 396,
"LAT": 397,
"have": 398,
"live": 399,
"ul": 400,
"Ġsaid": 401,
"Ġman": 402,
"Ġabo": 403,
"Ġabove": 404,
"Ġsay": 405,
"eat": 406,
"again": 407,
"med": 408,
"able": 409,
"et": 410,
"ur": 411,
"IN": 412,
"orse": 413,
"br": 414,
"po": 415,
"many": 416,
"down": 417,
"with": 418,
"ru": 419,
"ren": 420,
"SU": 421,
"ater": 422,
"ead": 423,
"Ġon": 424,
"Ġri": 425,
"ster": 426,
"Ġwoman": 427,
"sh": 428,
"lan": 429,
"pla": 430,
"mp": 431,
"by": 432,
"ink": 433,
"ory": 434,
"ff": 435,
"children": 436,
"Ġwhite": 437,
"ard": 438,
"BJ": 439,
"ALLAT": 440,
"SUBJ": 441,
"ĠW": 442,
"ion": 443,
"want": 444,
"make": 445,
"ance": 446,
"Ġg": 447,
"ERR": 448,
"ind": 449,
"ĠB": 450,
"oy": 451,
"off": 452,
"mo": 453,
"mother": 454,
"Ġlong": 455,
"res": 456,
"ick": 457,
"ĠC": 458,
"de": 459,
"ight": 460,
"place": 461,
"ĠINTERR": 462,
"old": 463,
"run": 464,
"lf": 465,
"long": 466,
"men": 467,
"ate": 468,
"ig": 469,
"guage": 470,
"ree": 471,
"qu": 472,
"ool": 473,
"little": 474,
"take": 475,
"name": 476,
"away": 477,
"com": 478,
"call": 479,
"INSTR": 480,
"ish": 481,
"LO": 482,
"LOC": 483,
"Ġyes": 484,
"ave": 485,
"'t": 486,
"ABIT": 487,
"HABIT": 488,
"ful": 489,
"Ġthing": 490,
"sse": 491,
"about": 492,
"ago": 493,
"over": 494,
"self": 495,
"Ġaround": 496,
"pr": 497,
"oung": 498,
"come": 499,
"put": 500,
"ep": 501,
"man": 502,
"thers": 503,
"then": 504,
"hite": 505,
"language": 506,
"ble": 507,
"chool": 508,
"Ġ0": 509,
"ĠJ": 510,
"rec": 511,
"el": 512,
"give": 513,
"tain": 514,
"still": 515,
"wo": 516,
"bli": 517,
"said": 518,
"Ġchildren": 519,
"ĠNEG": 520,
"pl": 521,
"Ġdo": 522,
"ĠE": 523,
"walk": 524,
"fter": 525,
"ear": 526,
"row": 527,
"always": 528,
"blig": 529,
"ef": 530,
"day": 531,
"ffer": 532,
"story": 533,
"ning": 534,
"along": 535,
"il": 536,
"fferent": 537,
"Ġright": 538,
"ĠWhite": 539,
"Ġoblig": 540,
"pp": 541,
"dian": 542,
"son": 543,
"Ġr": 544,
"lp": 545,
"ever": 546,
"Ġhorse": 547,
"atch": 548,
"Ġuhm": 549,
"ic": 550,
"our": 551,
"Ġtri": 552,
"Ġgo": 553,
"lat": 554,
"Ġun": 555,
"some": 556,
"car": 557,
"con": 558,
"Ġfrom": 559,
"iz": 560,
"ok": 561,
"ENS": 562,
"Ġboy": 563,
"home": 564,
"te": 565,
"ĠM": 566,
"ENSE": 567,
"Ġother": 568,
"try": 569,
"chief": 570,
"Ġhis": 571,
"ĠP": 572,
"think": 573,
"gin": 574,
"well": 575,
"stand": 576,
"sit": 577,
"ower": 578,
"camp": 579,
"wor": 580,
"Ġne": 581,
"ine": 582,
"low": 583,
"resent": 584,
"kill": 585,
"not": 586,
"Ġnot": 587,
"ven": 588,
"help": 589,
"ta": 590,
"Ġtrick": 591,
"ask": 592,
"lot": 593,
"int": 594,
"WY": 595,
"look": 596,
"Ġtrickster": 597,
"different": 598,
"Ġperson": 599,
"til": 600,
"ugh": 601,
"present": 602,
"mon": 603,
"OBL": 604,
"ud": 605,
"Ġbu": 606,
"named": 607,
"ac": 608,
"Ġindian": 609,
"Ġuntil": 610,
"ber": 611,
"if": 612,
"used": 613,
"Ġle": 614,
"Ġro": 615,
"school": 616,
"into": 617,
"power": 618,
"set": 619,
"inside": 620,
"hun": 621,
"young": 622,
"uch": 623,
"MP": 624,
"MPH": 625,
"grandfather": 626,
"fo": 627,
"Ġpeople": 628,
"ately": 629,
"Ġothers": 630,
"eremon": 631,
"Ġwas": 632,
"ap": 633,
"Ġof": 634,
"ĠINTENSE": 635,
"iately": 636,
"immed": 637,
"immediately": 638,
"water": 639,
"cause": 640,
"Ġmor": 641,
"ous": 642,
"posse": 643,
"ould": 644,
"riend": 645,
"bu": 646,
"Ġ4": 647,
"hear": 648,
"ffa": 649,
"ffalo": 650,
"Ġafter": 651,
"relat": 652,
"Ġhave": 653,
"ie": 654,
"ough": 655,
"cle": 656,
"Ġwith": 657,
"irst": 658,
"ose": 659,
"ĠEMPH": 660,
"arch": 661,
"Ġthus": 662,
"ex": 663,
"times": 664,
"red": 665,
"gle": 666,
"horse": 667,
"Ġat": 668,
"um": 669,
"much": 670,
"forth": 671,
"powerful": 672,
"woman": 673,
"ards": 674,
"called": 675,
"ise": 676,
"str": 677,
"tru": 678,
"begin": 679,
"Ġfar": 680,
"Ġah": 681,
"TEN": 682,
"POTEN": 683,
"POTENT": 684,
"ountain": 685,
"grandmother": 686,
"inish": 687,
"ather": 688,
"Ġchief": 689,
"watch": 690,
"relative": 691,
"am": 692,
"ure": 693,
"work": 694,
"clo": 695,
"Ġtell": 696,
"Ġwater": 697,
"rection": 698,
"Ġbuffalo": 699,
"ird": 700,
"Ġlife": 701,
"Ġcall": 702,
"teach": 703,
"ation": 704,
"comit": 705,
"Arapaho": 706,
"dance": 707,
"Ġimmediately": 708,
"Ġho": 709,
"ĠN": 710,
"bring": 711,
"far": 712,
"sing": 713,
"ĠArapahos": 714,
"Ġti": 715,
"arth": 716,
"Ġwhatever": 717,
"Ġ(": 718,
"lie": 719,
"search": 720,
"gether": 721,
"igh": 722,
"ceremon": 723,
"Ġsee": 724,
"wom": 725,
"happ": 726,
"bit": 727,
"Ġpr": 728,
"eagle": 729,
"Ġahh": 730,
"boy": 731,
"anim": 732,
"Ġlittle": 733,
"head": 734,
"Ġday": 735,
"Ġevery": 736,
"together": 737,
"rab": 738,
"ush": 739,
"Ġfor": 740,
"Ġget": 741,
"finish": 742,
"women": 743,
"quick": 744,
"find": 745,
"tough": 746,
"ĠIMPER": 747,
"ĠG": 748,
"Ġwe": 749,
"Ġmy": 750,
"oper": 751,
"possess": 752,
"quickly": 753,
"ark": 754,
"Ġmountain": 755,
"IC": 756,
"you": 757,
"Ġland": 758,
"Ġfo": 759,
"longer": 760,
"Ġsomething": 761,
"most": 762,
"enter": 763,
"big": 764,
"pear": 765,
"pi": 766,
"Ġeagle": 767,
"?)": 768,
"outh": 769,
"ess": 770,
"Ġag": 771,
"Ġmo": 772,
"Ġfirst": 773,
"animal": 774,
"sten": 775,
"Ġdown": 776,
"Ġcow": 777,
"ught": 778,
"ob": 779,
"Ġagain": 780,
"ook": 781,
"ought": 782,
"ĠR": 783,
"ret": 784,
"hand": 785,
"Ġtry": 786,
"urn": 787,
"??": 788,
"Ġhorses": 789,
"Ġwor": 790,
"?-": 791,
"ody": 792,
"llow": 793,
"Ġme": 794,
"lack": 795,
"per": 796,
"Ġsp": 797,
"dge": 798,
"hold": 799,
"der": 800,
"ank": 801,
"Ġee": 802,
"wi": 803,
"wr": 804,
"Ġtwo": 805,
"friend": 806,
"si": 807,
"body": 808,
"two": 809,
"mor": 810,
"ally": 811,
"eam": 812,
"Ġbig": 813,
"reat": 814,
"ĠH": 815,
"direction": 816,
"ldi": 817,
"Ġdi": 818,
"eal": 819,
"UM": 820,
"ener": 821,
"dr": 822,
"ts": 823,
"ember": 824,
"older": 825,
"ldier": 826,
"Ġsoon": 827,
"ies": 828,
"truly": 829,
"Ġup": 830,
"ĠNUM": 831,
"ire": 832,
"Ġstory": 833,
"cha": 834,
"appear": 835,
"'re": 836,
"ssed": 837,
"ĠD": 838,
"king": 839,
"lu": 840,
"night": 841,
"read": 842,
"TAT": 843,
"holy": 844,
"ENTAT": 845,
"ander": 846,
"ving": 847,
"tra": 848,
"wards": 849,
"Ġoh": 850,
"VENTAT": 851,
"gl": 852,
"oney": 853,
"fore": 854,
"pect": 855,
"Ġback": 856,
"ary": 857,
"dle": 858,
"show": 859,
"vis": 860,
"Ġfood": 861,
"Ġspeak": 862,
"ize": 863,
"fly": 864,
"mer": 865,
"den": 866,
"Ġsong": 867,
"Ġse": 868,
"ity": 869,
"operly": 870,
"Ġis": 871,
"irl": 872,
"hill": 873,
"hosh": 874,
"follow": 875,
"leep": 876,
"Ġpa": 877,
"HI": 878,
"OHI": 879,
"ROHI": 880,
"ROHIB": 881,
"Ġschool": 882,
"Ġsh": 883,
"drive": 884,
"ĠShosh": 885,
"uck": 886,
"Ġdon": 887,
"Ġinside": 888,
"right": 889,
"ot": 890,
"arn": 891,
"Ġbear": 892,
"Ġlet": 893,
"Ġsoldier": 894,
"grandchild": 895,
"Ġvery": 896,
"white": 897,
"whiz": 898,
"play": 899,
"don": 900,
"ile": 901,
"listen": 902,
"ced": 903,
"rabbit": 904,
"after": 905,
"Ġyoung": 906,
"this": 907,
"gs": 908,
"emember": 909,
"hunt": 910,
"pray": 911,
"ort": 912,
"cook": 913,
"ĠPROHIB": 914,
"meet": 915,
"ol": 916,
"fle": 917,
"band": 918,
"Ġwho": 919,
"Ġmore": 920,
"Ġcome": 921,
"Ġby": 922,
"ty": 923,
"ious": 924,
"cut": 925,
"gener": 926,
"ĠJo": 927,
"generation": 928,
"ade": 929,
"move": 930,
"Ġbecause": 931,
"earth": 932,
"yet": 933,
"ote": 934,
"sho": 935,
"att": 936,
"Ġboys": 937,
"Ġrock": 938,
"life": 939,
"outside": 940,
"was": 941,
"does": 942,
"ull": 943,
"ĠShoshone": 944,
"Ġteach": 945,
"hair": 946,
"house": 947,
"IG": 948,
"OBLIG": 949,
"ĠSt": 950,
"est": 951,
"never": 952,
"jump": 953,
"Ġk": 954,
"Ġgood": 955,
"love": 956,
"Ġtru": 957,
"ken": 958,
"ĠSun": 959,
"Ġmorning": 960,
"Ġbefore": 961,
"ip": 962,
"Ġalways": 963,
"Ġrabbit": 964,
"ĠL": 965,
"fast": 966,
"hit": 967,
"raz": 968,
"hard": 969,
"Ġyear": 970,
"running": 971,
"Ġmeat": 972,
"Ġthank": 973,
"Ġmoney": 974,
"usband": 975,
"wife": 976,
"ĠT": 977,
"going": 978,
"part": 979,
"Ġshe": 980,
"ey": 981,
"sk": 982,
"ange": 983,
"like": 984,
"Ġtake": 985,
"Dance": 986,
"Ġsouth": 987,
"US": 988,
"respect": 989,
"gather": 990,
"reek": 991,
"ich": 992,
"unable": 993,
"par": 994,
"Ġmake": 995,
"ist": 996,
"Ġab": 997,
"fall": 998,
"Ġfour": 999,
"Ġpo": 1000,
"Ġcar": 1001,
"ĠOBLIG": 1002,
"top": 1003,
"Ġabout": 1004,
"treat": 1005,
"Ġv": 1006,
"Ġsomeone": 1007,
"ĠIR": 1008,
"Ġhouse": 1009,
"ĠF": 1010,
"Ġla": 1011,
"AUS": 1012,
"CAUS": 1013,
"ring": 1014,
"ride": 1015,
"Ġsun": 1016,
"feel": 1017,
"happy": 1018,
"leave": 1019,
"thr": 1020,
"brush": 1021,
"four": 1022,
"Ġwhy": 1023,
"rible": 1024,
"grow": 1025,
"co": 1026,
"REAL": 1027,
"Ġstill": 1028,
"Ġtree": 1029,
"under": 1030,
"oneself": 1031,
"Ġde": 1032,
"?)-": 1033,
"ughter": 1034,
"ĠIRREAL": 1035,
"ories": 1036,
"pro": 1037,
"agon": 1038,
"razy": 1039,
"orn": 1040,
"ground": 1041,
"xt": 1042,
"known": 1043,
"less": 1044,
"lose": 1045,
"bless": 1046,
"Ġeven": 1047,
"gi": 1048,
"Ġname": 1049,
"care": 1050,
"new": 1051,
"Ġonly": 1052,
"husband": 1053,
"INT": 1054,
"strong": 1055,
"Ġtrue": 1056,
"Ġthree": 1057,
"terrible": 1058,
"Ġsw": 1059,
"ngl": 1060,
"comp": 1061,
"nglish": 1062,
"ame": 1063,
"Ġj": 1064,
"LLAT": 1065,
"ĠALLAT": 1066,
"lay": 1067,
"Ġch": 1068,
"bad": 1069,
"illage": 1070,
"Ġge": 1071,
"Ġthem": 1072,
"mar": 1073,
"point": 1074,
"ctor": 1075,
"Ġremember": 1076,
"meat": 1077,
"sw": 1078,
"ribe": 1079,
"ste": 1080,
"cond": 1081,
"eel": 1082,
"whatever": 1083,
"Ġsit": 1084,
"Ġsomewhere": 1085,
"udden": 1086,
"ceremoni": 1087,
"ft": 1088,
"stone": 1089,
"gry": 1090,
"another": 1091,
"Ġgot": 1092,
"Ġmost": 1093,
"owl": 1094,
"light": 1095,
"brother": 1096,
"Ġdance": 1097,
"slow": 1098,
"tch": 1099,
"fetch": 1100,
"Ġmoreover": 1101,
"anc": 1102,
"ule": 1103,
"buy": 1104,
"relatives": 1105,
"Ġtalk": 1106,
"Ġher": 1107,
"stream": 1108,
"drink": 1109,
"Ġthose": 1110,
"sleep": 1111,
"Ġtipi": 1112,
"song": 1113,
"Ġbird": 1114,
"deer": 1115,
"Ġwant": 1116,
"Ġdid": 1117,
"land": 1118,
"dark": 1119,
"Ġn": 1120,
"those": 1121,
"they": 1122,
"talk": 1123,
"turn": 1124,
"uddenly": 1125,
"ved": 1126,
"Ġused": 1127,
"Ġmule": 1128,
"fire": 1129,
"river": 1130,
"ait": 1131,
"properly": 1132,
"...-": 1133,
"Ġlive": 1134,
"reach": 1135,
"lieve": 1136,
"ach": 1137,
"catch": 1138,
"chase": 1139,
"high": 1140,
".'": 1141,
"rass": 1142,
"Ġword": 1143,
"ang": 1144,
"lanke": 1145,
"though": 1146,
"almost": 1147,
"arrow": 1148,
"because": 1149,
"raise": 1150,
"Ġspr": 1151,
"made": 1152,
"PPA": 1153,
"RT": 1154,
"iver": 1155,
"DEPPA": 1156,
"visit": 1157,
"DEPPART": 1158,
"esus": 1159,
"ĠJesus": 1160,
"wear": 1161,
"Ġgee": 1162,
"mb": 1163,
"Ġyour": 1164,
"lodge": 1165,
"ceremony": 1166,
"given": 1167,
"black": 1168,
"seize": 1169,
"sister": 1170,
"ried": 1171,
"les": 1172,
"Ġwatch": 1173,
"Ġgirl": 1174,
"Ġindians": 1175,
"face": 1176,
"taken": 1177,
"her": 1178,
"Ġgu": 1179,
"da": 1180,
"rem": 1181,
"sur": 1182,
"itten": 1183,
"Ġsometimes": 1184,
"IR": 1185,
"fight": 1186,
"),.": 1187,
"loc": 1188,
"recent": 1189,
"seen": 1190,
"Ġhigh": 1191,
"ift": 1192,
"og": 1193,
"happen": 1194,
"Ġwherever": 1195,
"Ġspring": 1196,
"ond": 1197,
"edic": 1198,
"oyote": 1199,
"Ġsc": 1200,
"enne": 1201,
"Ġteacher": 1202,
"uncle": 1203,
"Ġwould": 1204,
"ross": 1205,
"fr": 1206,
"Ġowl": 1207,
"told": 1208,
"Ġwhile": 1209,
"Ġfriend": 1210,
"quit": 1211,
"ting": 1212,
"Ġmedic": 1213,
"rist": 1214,
"Ġfather": 1215,
"ello": 1216,
"Ġchild": 1217,
"bull": 1218,
"Ġdifferent": 1219,
"udent": 1220,
"close": 1221,
"pass": 1222,
"taste": 1223,
"dis": 1224,
"(?)-": 1225,
"Ġstick": 1226,
"days": 1227,
"company": 1228,
"dy": 1229,
"vy": 1230,
"mall": 1231
},
"merges": [
"e n",
"a r",
"s t",
"ar t",
"en d",
"st art",
"Ġ <",
"t h",
"Ġ th",
"e r",
"i s",
"a t",
"P L",
"S T",
"i n",
"a n",
"Ġ I",
"P A",
"Ġth is",
"PA ST",
"s e",
"er e",
"o n",
"E R",
"w h",
"P ER",
"p a",
"o r",
"i t",
"o w",
"u se",
"PER F",
"Ġth at",
"pa use",
"t o",
"ĠI C",
"Ġ h",
"e d",
"an d",
"l l",
"a y",
"Ġ b",
"Ġ s",
"M PERF",
"Ġ PAST",
"Ġ wh",
"in g",
"o u",
"l e",
"t i",
"Ġ and",
"D U",
"Ġ o",
"N A",
". .",
"f or",
"F U",
"FU T",
"l i",
"R E",
"o m",
"D E",
"v e",
"DU P",
"RE DUP",
"u t",
"c h",
"k e",
"n ow",
"I MPERF",
"Ġ a",
"T A",
", .",
"Ġ FUT",
"C H",
"DE TA",
"DETA CH",
"e a",
"e m",
"Ġb ut",
"Ġh ere",
"Ġ w",
". -",
"ti on",
"b e",
"Ġ m",
"c e",
"l d",
"A D",
"AD V",
"em en",
"a for",
"tion ed",
"emen tioned",
"afor ementioned",
"r i",
"er s",
"Ġ 3",
"R R",
"RR PAST",
"NA RRPAST",
"Ġ NARRPAST",
"Ġ y",
"r e",
"v er",
"Ġ li",
"e ll",
"ĠI MPERF",
"g o",
"l o",
"r a",
"th ere",
"Ġ 1",
"E G",
"N EG",
"th er",
"p ers",
"Ġli ke",
"c k",
"i d",
"on e",
"h o",
"h ere",
"p e",
"Ġth en",
"Ġwh en",
"l y",
"k now",
"g e",
"a l",
"g h",
"k ay",
"m e",
"Ġo kay",
"O B",
"o p",
"u n",
"1 2",
"th ing",
"ĠI N",
"I T",
"a ll",
"om e",
"Ġ t",
"Ġwh at",
"Ġ f",
"OB V",
"Ġs in",
"Ġ d",
"j u",
". (",
"Ġ c",
"Ġ to",
"Ġsin ce",
"Ġ now",
"ou n",
"on g",
"Ġ REDUP",
"u s",
"ju st",
"Ġ A",
"o f",
"wh at",
"e s",
"Ġ u",
"op le",
"pe ople",
"s ay",
"n o",
"Ġ 2",
"gh t",
"Ġ or",
"Ġwh ere",
"o d",
"Ġth e",
"a s",
"Ġu h",
"pa ho",
"ch i",
"ra paho",
"a ke",
"f a",
"en t",
"Ġ just",
".. .",
"th at",
"i ll",
"ar e",
"Ġy ou",
"wh ere",
"w ay",
"g r",
"Ġth ere",
") -",
"an y",
"it e",
"Ġh e",
"a in",
"i r",
"ou t",
"ĠA rapaho",
"l a",
") .",
"s o",
"h a",
"ti me",
"d o",
"thing s",
"Ġ p",
"B IT",
"h ow",
"' s",
"r om",
"M PER",
"a b",
"Ġw ell",
"N I",
"c at",
"Ġb e",
"ow n",
"d i",
"chi ld",
"Ġuh h",
"Ġa l",
"ST R",
"Ġ l",
"o ther",
"oun d",
"se e",
"h e",
"a id",
"Ġo ld",
"u p",
"I MPER",
"Ġs o",
"t ell",
"Ġ in",
"lo cat",
"wh en",
"id e",
"ri ve",
"b o",
"locat ed",
"ea h",
"a g",
"s s",
"Ġ no",
"n a",
"pers on",
"r y",
"f e",
"ea k",
"Ġh ow",
"a ck",
"r o",
"P O",
"s p",
"ay be",
"Ġy eah",
"Ġal so",
"th e",
"Ġa ll",
"go od",
"an t",
"th us",
"Ġm aybe",
"f rom",
"i th",
"n e",
"i ve",
"om an",
"IT ER",
"Ġ e",
"Ġ one",
"fa ther",
"Ġ st",
"gr and",
"it t",
"Ġo ver",
"s ide",
"ge t",
"DU BIT",
"ar ound",
"ar rive",
"a d",
"Ġs ome",
"ĠIN T",
"Ġ know",
"t er",
"Ġ DUBIT",
"Ġ it",
"ver y",
"A T",
"i m",
"E N",
"S S",
"a ge",
"DE F",
"o o",
"ea ch",
"c a",
"ĠIN DEF",
"g u",
"Ġto o",
"sp eak",
"Ġthe y",
"b ack",
"itt le",
"c t",
"A L",
"PO SS",
"ĠIN STR",
"Ġ S",
"al k",
"way s",
"L AT",
"ha ve",
"li ve",
"u l",
"Ġs aid",
"Ġm an",
"Ġa bo",
"Ġabo ve",
"Ġs ay",
"e at",
"ag ain",
"m ed",
"ab le",
"e t",
"u r",
"I N",
"or se",
"b r",
"p o",
"m any",
"d own",
"w ith",
"r u",
"r en",
"S U",
"at er",
"ea d",
"Ġ on",
"Ġ ri",
"st er",
"Ġw oman",
"s h",
"l an",
"p la",
"m p",
"b y",
"in k",
"or y",
"f f",
"child ren",
"Ġwh ite",
"ar d",
"B J",
"AL LAT",
"SU BJ",
"Ġ W",
"i on",
"w ant",
"m ake",
"an ce",
"Ġ g",
"ER R",
"in d",
"Ġ B",
"o y",
"of f",
"m o",
"m other",
"Ġl ong",
"re s",
"i ck",
"Ġ C",
"d e",
"i ght",
"pla ce",
"ĠINT ERR",
"o ld",
"r un",
"l f",
"l ong",
"m en",
"at e",
"i g",
"gu age",
"re e",
"q u",
"oo l",
"l ittle",
"t ake",
"na me",
"a way",
"c om",
"c all",
"IN STR",
"is h",
"L O",
"LO C",
"Ġy es",
"a ve",
"' t",
"A BIT",
"H ABIT",
"f ul",
"Ġth ing",
"s se",
"ab out",
"a go",
"o ver",
"se lf",
"Ġ around",
"p r",
"oun g",
"c ome",
"p ut",
"e p",
"m an",
"th ers",
"th en",
"h ite",
"lan guage",
"b le",
"ch ool",
"Ġ 0",
"Ġ J",
"re c",
"e l",
"g ive",
"t ain",
"st ill",
"w o",
"b li",
"s aid",
"Ġ children",
"Ġ NEG",
"p l",
"Ġd o",
"Ġ E",
"w alk",
"f ter",
"e ar",
"r ow",
"al ways",
"bli g",
"e f",
"d ay",
"ff er",
"st ory",
"n ing",
"al ong",
"i l",
"ffer ent",
"Ġri ght",
"ĠW hite",
"Ġo blig",
"p p",
"di an",
"s on",
"Ġ r",
"l p",
"e ver",
"Ġh orse",
"at ch",
"Ġuh m",
"i c",
"ou r",
"Ġt ri",
"Ġ go",
"l at",
"Ġ un",
"s ome",
"c ar",
"c on",
"Ġf rom",
"i z",
"o k",
"EN S",
"Ġb oy",
"h ome",
"t e",
"Ġ M",
"ENS E",
"Ġo ther",
"t ry",
"chi ef",
"Ġh is",
"Ġ P",
"th ink",
"g in",
"w ell",
"st and",
"s it",
"ow er",
"ca mp",
"w or",
"Ġ ne",
"in e",
"l ow",
"res ent",
"k ill",
"no t",
"Ġno t",
"v en",
"he lp",
"t a",
"Ġtri ck",
"as k",
"lo t",
"in t",
"W Y",
"lo ok",
"Ġtrick ster",
"di fferent",
"Ġ person",
"ti l",
"u gh",
"p resent",
"m on",
"OB L",
"u d",
"Ġb u",
"na med",
"a c",
"Ġin dian",
"Ġun til",
"b er",
"i f",
"use d",
"Ġ le",
"Ġ ro",
"s chool",
"in to",
"p ower",
"se t",
"in side",
"h un",
"y oung",
"u ch",
"M P",
"MP H",
"grand father",
"f o",
"Ġ people",
"ate ly",
"Ġo thers",
"ere mon",
"Ġw as",
"a p",
"Ġo f",
"ĠINT ENSE",
"i ately",
"im med",
"immed iately",
"w ater",
"ca use",
"Ġm or",
"ou s",
"po sse",
"ou ld",
"ri end",
"b u",
"Ġ 4",
"he ar",
"f fa",
"ffa lo",
"Ġa fter",
"re lat",
"Ġh ave",
"i e",
"ou gh",
"c le",
"Ġw ith",
"ir st",
"o se",
"ĠE MPH",
"ar ch",
"Ġth us",
"e x",
"time s",
"r ed",
"g le",
"h orse",
"Ġ at",
"u m",
"m uch",
"for th",
"power ful",
"w oman",
"ard s",
"call ed",
"is e",
"st r",
"t ru",
"be gin",
"Ġf ar",
"Ġa h",
"T EN",
"PO TEN",
"POTEN T",
"oun tain",
"grand mother",
"in ish",
"a ther",
"Ġ chief",
"w atch",
"relat ive",
"a m",
"u re",
"wor k",
"c lo",
"Ġt ell",
"Ġw ater",
"rec tion",
"Ġbu ffalo",
"ir d",
"Ġli fe",
"Ġc all",
"t each",
"at ion",
"com it",
"A rapaho",
"d ance",
"Ġ immediately",
"Ġh o",
"Ġ N",
"br ing",
"f ar",
"s ing",
"ĠArapaho s",
"Ġ ti",
"art h",
"Ġwhat ever",
"Ġ (",
"li e",
"se arch",
"ge ther",
"i gh",
"c eremon",
"Ġ see",
"w om",
"ha pp",
"b it",
"Ġp r",
"ea gle",
"Ġah h",
"bo y",
"an im",
"Ġl ittle",
"h ead",
"Ġd ay",
"Ġe very",
"to gether",
"ra b",
"us h",
"Ġ for",
"Ġ get",
"f inish",
"wom en",
"qu ick",
"f ind",
"to ugh",
"ĠI MPER",
"Ġ G",
"Ġw e",
"Ġm y",
"op er",
"posse ss",
"quick ly",
"ar k",
"Ġm ountain",
"I C",
"y ou",
"Ġl and",
"Ġf o",
"long er",
"Ġsome thing",
"mo st",
"ent er",
"b ig",
"pe ar",
"p i",
"Ġ eagle",
"? )",
"ou th",
"es s",
"Ġa g",
"Ġm o",
"Ġf irst",
"anim al",
"st en",
"Ġd own",
"Ġc ow",
"u ght",
"o b",
"Ġag ain",
"oo k",
"ou ght",
"Ġ R",
"re t",
"h and",
"Ġt ry",
"ur n",
"? ?",
"Ġhorse s",
"Ġw or",
"? -",
"od y",
"ll ow",
"Ġm e",
"la ck",
"p er",
"Ġs p",
"d ge",
"ho ld",
"d er",
"an k",
"Ġe e",
"w i",
"w r",
"Ġt wo",
"f riend",
"s i",
"b ody",
"t wo",
"m or",
"all y",
"ea m",
"Ġb ig",
"re at",
"Ġ H",
"di rection",
"ld i",
"Ġd i",
"ea l",
"U M",
"en er",
"d r",
"t s",
"em ber",
"old er",
"ldi er",
"Ġso on",
"i es",
"tru ly",
"Ġu p",
"ĠN UM",
"i re",
"Ġst ory",
"ch a",
"ap pear",
"' re",
"sse d",
"Ġ D",
"k ing",
"l u",
"n ight",
"r ead",
"TA T",
"ho ly",
"EN TAT",
"and er",
"v ing",
"t ra",
"w ards",
"Ġo h",
"V ENTAT",
"g l",
"one y",
"for e",
"pe ct",
"Ġb ack",
"ar y",
"d le",
"s how",
"v is",
"Ġfo od",
"Ġsp eak",
"iz e",
"f ly",
"m er",
"d en",
"Ġs ong",
"Ġ se",
"it y",
"oper ly",
"Ġ is",
"ir l",
"h ill",
"ho sh",
"fo llow",
"le ep",
"Ġ pa",
"H I",
"O HI",
"R OHI",
"ROHI B",
"Ġs chool",
"Ġs h",
"d rive",
"ĠS hosh",
"u ck",
"Ġd on",
"Ġin side",
"ri ght",
"o t",
"ar n",
"Ġbe ar",
"Ġle t",
"Ġso ldier",
"grand child",
"Ġ very",
"wh ite",
"wh iz",
"pl ay",
"d on",
"i le",
"li sten",
"c ed",
"rab bit",
"a fter",
"Ġy oung",
"th is",
"g s",
"em ember",
"hun t",
"pr ay",
"or t",
"c ook",
"ĠP ROHIB",
"me et",
"o l",
"f le",
"b and",
"Ġwh o",
"Ġmor e",
"Ġc ome",
"Ġb y",
"t y",
"i ous",
"c ut",
"g ener",
"ĠJ o",
"gener ation",
"ad e",
"mo ve",
"Ġbe cause",
"e arth",
"y et",
"o te",
"s ho",
"at t",
"Ġboy s",
"Ġro ck",
"li fe",
"out side",
"w as",
"do es",
"u ll",
"ĠShosh one",
"Ġt each",
"ha ir",
"ho use",
"I G",
"OBL IG",
"ĠS t",
"e st",
"ne ver",
"ju mp",
"Ġ k",
"Ġ good",
"lo ve",
"Ġt ru",
"k en",
"ĠS un",
"Ġmor ning",
"Ġbe fore",
"i p",
"Ġal ways",
"Ġ rabbit",
"Ġ L",
"fa st",
"h it",
"ra z",
"h ard",
"Ġy ear",
"run ning",
"Ġm eat",
"Ġth ank",
"Ġm oney",
"us band",
"wi fe",
"Ġ T",
"go ing",
"p art",
"Ġs he",
"e y",
"s k",
"an ge",
"li ke",
"Ġt ake",
"D ance",
"Ġs outh",
"U S",
"res pect",
"g ather",
"ree k",
"i ch",
"un able",
"p ar",
"Ġm ake",
"i st",
"Ġa b",
"f all",
"Ġf our",
"Ġp o",
"Ġc ar",
"Ġ OBLIG",
"to p",
"Ġab out",
"t reat",
"Ġ v",
"Ġsome one",
"ĠI R",
"Ġho use",
"Ġ F",
"Ġ la",
"A US",
"C AUS",
"r ing",
"ri de",
"Ġs un",
"fe el",
"happ y",
"le ave",
"th r",
"br ush",
"f our",
"Ġwh y",
"ri ble",
"gr ow",
"c o",
"RE AL",
"Ġst ill",
"Ġt ree",
"un der",
"one self",
"Ġd e",
"? )-",
"ught er",
"ĠIR REAL",
"or ies",
"p ro",
"ag on",
"raz y",
"or n",
"gr ound",
"x t",
"know n",
"le ss",
"lo se",
"ble ss",
"Ġe ven",
"g i",
"Ġ name",
"c are",
"ne w",
"Ġon ly",
"h usband",
"IN T",
"str ong",
"Ġtru e",
"Ġth ree",
"ter rible",
"Ġs w",
"n gl",
"com p",
"ngl ish",
"a me",
"Ġ j",
"L LAT",
"ĠA LLAT",
"l ay",
"Ġ ch",
"b ad",
"ill age",
"Ġ ge",
"Ġth em",
"m ar",
"po int",
"ct or",
"Ġr emember",
"me at",
"s w",
"ri be",
"st e",
"con d",
"e el",
"what ever",
"Ġs it",
"Ġsome where",
"ud den",
"ceremon i",
"f t",
"st one",
"gr y",
"an other",
"Ġgo t",
"Ġmo st",
"ow l",
"li ght",
"br other",
"Ġd ance",
"s low",
"t ch",
"fe tch",
"Ġmore over",
"an c",
"u le",
"bu y",
"relative s",
"Ġt alk",
"Ġh er",
"str eam",
"dr ink",
"Ġth ose",
"s leep",
"Ġti pi",
"s ong",
"Ġb ird",
"de er",
"Ġw ant",
"Ġd id",
"l and",
"d ark",
"Ġ n",
"th ose",
"the y",
"t alk",
"t urn",
"udden ly",
"v ed",
"Ġ used",
"Ġm ule",
"f ire",
"ri ver",
"a it",
"pr operly",
".. .-",
"Ġli ve",
"r each",
"lie ve",
"a ch",
"cat ch",
"cha se",
"h igh",
". '",
"ra ss",
"Ġwor d",
"an g",
"lan ke",
"th ough",
"al most",
"ar row",
"be cause",
"ra ise",
"Ġs pr",
"m ade",
"P PA",
"R T",
"i ver",
"DE PPA",
"vis it",
"DEPPA RT",
"es us",
"ĠJ esus",
"w ear",
"Ġge e",
"m b",
"Ġyou r",
"lo dge",
"ceremon y",
"gi ven",
"b lack",
"se ize",
"si ster",
"ri ed",
"le s",
"Ġw atch",
"Ġg irl",
"Ġindian s",
"fa ce",
"ta ken",
"h er",
"Ġ gu",
"d a",
"r em",
"s ur",
"itt en",
"Ġsome times",
"I R",
"f ight",
") ,.",
"lo c",
"rec ent",
"se en",
"Ġh igh",
"if t",
"o g",
"happ en",
"Ġwhere ver",
"Ġspr ing",
"on d",
"ed ic",
"oy ote",
"Ġs c",
"en ne",
"Ġteach er",
"un cle",
"Ġw ould",
"ro ss",
"f r",
"Ġ owl",
"to ld",
"Ġwh ile",
"Ġf riend",
"qu it",
"t ing",
"Ġm edic",
"ri st",
"Ġf ather",
"ell o",
"Ġ child",
"bu ll",
"Ġdi fferent",
"ud ent",
"clo se",
"pa ss",
"ta ste",
"d is",
"( ?)-",
"Ġst ick",
"day s",
"comp any",
"d y",
"v y",
"m all"
]
}
}