{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 0, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 1, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 2, "content": "", "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": { "": 0, "": 1, "": 2, "'": 3, "(": 4, ")": 5, "-": 6, ".": 7, "1": 8, "2": 9, "3": 10, "4": 11, "<": 12, ">": 13, "?": 14, "A": 15, "B": 16, "C": 17, "D": 18, "E": 19, "F": 20, "G": 21, "H": 22, "I": 23, "J": 24, "K": 25, "L": 26, "M": 27, "N": 28, "O": 29, "P": 30, "Q": 31, "R": 32, "S": 33, "T": 34, "U": 35, "V": 36, "W": 37, "Z": 38, "[": 39, "]": 40, "a": 41, "b": 42, "c": 43, "d": 44, "e": 45, "f": 46, "g": 47, "h": 48, "i": 49, "j": 50, "k": 51, "l": 52, "m": 53, "n": 54, "o": 55, "p": 56, "q": 57, "r": 58, "s": 59, "t": 60, "u": 61, "v": 62, "w": 63, "x": 64, "y": 65, "z": 66, "~": 67, "¢": 68, "©": 69, "Ã": 70, "Ġ": 71, "nd": 72, "ar": 73, "st": 74, "end": 75, "art": 76, "Ġ<": 77, "start": 78, "II": 79, "CV": 80, "CVB": 81, "FV": 82, "PFV": 83, "DE": 84, "SS": 85, "BL": 86, "ĠII": 87, "ER": 88, "ĠDE": 89, "ĠDEM": 90, "Ġb": 91, "me": 92, "ST": 93, "OBL": 94, "er": 95, "SG": 96, "AT": 97, "PST": 98, "ESS": 99, "OP": 100, "TOP": 101, "PL": 102, "Ġs": 103, "PR": 104, "th": 105, "LAT": 106, "ĠI": 107, "ĠIII": 108, "ou": 109, "Ġbe": 110, "ERG": 111, "EN": 112, "GEN": 113, "in": 114, "NT": 115, "Ġh": 116, "ĠIV": 117, "Ġw": 118, "ome": 119, "ay": 120, "UN": 121, "IN": 122, "on": 123, "UNW": 124, "an": 125, "come": 126, "PRT": 127, "Ġy": 128, "re": 129, "Ġg": 130, "le": 131, "PO": 132, "Ġyou": 133, "QU": 134, "ther": 135, "Ġme": 136, "SU": 137, "ISG": 138, "OT": 139, "QUOT": 140, "POSS": 141, "Ġd": 142, "at": 143, "Ġf": 144, "ll": 145, "Ġt": 146, "IISG": 147, "PER": 148, "SUPER": 149, "ve": 150, "ow": 151, "and": 152, "Ġa": 153, "Ġm": 154, "PRS": 155, "DEF": 156, "AD": 157, "or": 158, "ing": 159, "Ġsay": 160, "Ġth": 161, "Ġp": 162, "one": 163, "ABL": 164, "CO": 165, "ANT": 166, "EG": 167, "NEG": 168, "be": 169, "id": 170, "CONT": 171, "se": 172, "Ġc": 173, "ke": 174, "do": 175, "ge": 176, "IM": 177, "oo": 178, "IPFV": 179, "ch": 180, "Ġone": 181, "ide": 182, "ad": 183, "ake": 184, "EM": 185, "PH": 186, "EMPH": 187, "Ġe": 188, "Ġgi": 189, "other": 190, "NPRS": 191, "ter": 192, "INF": 193, "Ġr": 194, "Ġwh": 195, "Ġk": 196, "gh": 197, "Ġgo": 198, "IPL": 199, "IT": 200, "WIT": 201, "become": 202, "Ġbo": 203, "ck": 204, "ill": 205, "han": 206, "go": 207, "en": 208, "it": 209, "take": 210, "VER": 211, "VERS": 212, "ES": 213, "RES": 214, "TR": 215, "ATTR": 216, "ce": 217, "CNT": 218, "CNTR": 219, "Ġn": 220, "Ġkhan": 221, "ld": 222, "CN": 223, "Ġin": 224, "al": 225, "FU": 226, "FUT": 227, "Ġboy": 228, "MS": 229, "MSD": 230, "Ġcome": 231, "PU": 232, "ut": 233, "side": 234, "APU": 235, "APUD": 236, "aw": 237, "if": 238, "un": 239, "pp": 240, "there": 241, "ind": 242, "Ġwe": 243, "DI": 244, "DIST": 245, "ree": 246, "ss": 247, "away": 248, "ood": 249, "Ġthere": 250, "ur": 251, "CND": 252, "Ġbr": 253, "Ġhe": 254, "Ġman": 255, "out": 256, "ver": 257, "Ġas": 258, "ell": 259, "om": 260, "Ġle": 261, "Ġgive": 262, "au": 263, "ain": 264, "augh": 265, "Ġbecome": 266, "Ġl": 267, "aughter": 268, "Ġsh": 269, "ere": 270, "ard": 271, "Ġask": 272, "SIM": 273, ").": 274, "ie": 275, "rl": 276, "Ġst": 277, "ather": 278, "Ġhome": 279, "Ġbrother": 280, "Ġre": 281, "ag": 282, "ove": 283, "Ġgirl": 284, "il": 285, "Ġson": 286, "sh": 287, "age": 288, "row": 289, "Ġdaughter": 290, "app": 291, "nt": 292, "ep": 293, "et": 294, "ring": 295, "ear": 296, "ir": 297, "Ġday": 298, "ri": 299, "Ġtell": 300, "ng": 301, "urn": 302, "up": 303, "ave": 304, "IMPR": 305, "ven": 306, "Ġso": 307, "ack": 308, "uch": 309, "ry": 310, "orse": 311, "Ġwhat": 312, "ore": 313, "ist": 314, "old": 315, "Ġinside": 316, "Ġhorse": 317, "Ġthing": 318, "ife": 319, "get": 320, "Ġv": 321, "bring": 322, "op": 323, "ant": 324, "Ġmother": 325, "eat": 326, "Ġfather": 327, "bove": 328, "even": 329, "Ġto": 330, "Ġput": 331, "ater": 332, "Ġwater": 333, "Ġdr": 334, "SUB": 335, "Ġwife": 336, "Ġthree": 337, "la": 338, "Ġfi": 339, "CS": 340, "CSL": 341, "turn": 342, "Ġthrow": 343, "am": 344, "us": 345, "ward": 346, "Ġne": 347, "happ": 348, "Ġyoung": 349, "ne": 350, "Ġfr": 351, "Ġleave": 352, "Ġnow": 353, "igh": 354, "Ġabove": 355, "Ġtw": 356, "Ġout": 357, "Ġoutside": 358, "AU": 359, "CAU": 360, "CAUS": 361, "own": 362, "much": 363, "lo": 364, "Ġhere": 365, "ig": 366, "Ġvill": 367, "Ġvillage": 368, "all": 369, "arry": 370, "fter": 371, "Ġafter": 372, "ick": 373, "Ġback": 374, "DISTR": 375, "Ġdown": 376, "ouse": 377, "happen": 378, "ion": 379, "Ġ-": 380, "Ġtwo": 381, "Ġan": 382, "see": 383, "Ġfrom": 384, "main": 385, "ime": 386, "hind": 387, "now": 388, "lace": 389, "Ġdo": 390, "kill": 391, "ju": 392, "Ġget": 393, "let": 394, "ul": 395, "fill": 396, "the": 397, "want": 398, "Ġold": 399, "ue": 400, "Ġhow": 401, "AL": 402, "ALL": 403, "Ġhouse": 404, "ed": 405, "IIPL": 406, "INT": 407, "ook": 408, "Ġshe": 409, "ull": 410, "IMM": 411, "Ġpe": 412, "Ġhun": 413, "Ġmou": 414, "ap": 415, "gether": 416, "Ġtogether": 417, "ight": 418, "send": 419, "Ġremain": 420, "Ġway": 421, "Ġall": 422, "ople": 423, "find": 424, "ink": 425, "Ġrun": 426, "Ġsp": 427, "Ġgold": 428, "Ġsist": 429, "Ġhand": 430, "Ġsister": 431, "ail": 432, "Ġpo": 433, "LCV": 434, "ness": 435, "Ġheart": 436, "thing": 437, "man": 438, "li": 439, "Ġri": 440, "Ġwor": 441, "ame": 442, "good": 443, "is": 444, "as": 445, "agon": 446, "Ġdragon": 447, "Ġpeople": 448, "Ġbehind": 449, "to": 450, "ĠA": 451, "band": 452, "Ġhus": 453, "Ġhusband": 454, "Ġwhy": 455, "Ġfo": 456, "CNC": 457, "oman": 458, "Ġag": 459, "Ġtime": 460, "Ġfor": 461, "know": 462, "Ġsle": 463, "Ġex": 464, "ble": 465, "tle": 466, "gin": 467, "ye": 468, "Ġeye": 469, "ine": 470, "wards": 471, "arri": 472, "arriage": 473, "ea": 474, "ory": 475, "Ġstory": 476, "lead": 477, "az": 478, "Ġch": 479, "carry": 480, "Ġco": 481, "Ġfox": 482, "ither": 483, "oney": 484, "Ġfore": 485, "Ġwoman": 486, "Ġfood": 487, "here": 488, "Ġany": 489, "Ġafterwards": 490, "Ġmeet": 491, "Ġfire": 492, "Ġtree": 493, "Ġhead": 494, "ex": 495, "Ġsheep": 496, "Ġsleep": 497, "very": 498, "alf": 499, "Ġthe": 500, "Ġriver": 501, "Ġother": 502, "Ġcat": 503, "im": 504, "Ġplace": 505, "ust": 506, "Ġat": 507, "Ġhen": 508, "appear": 509, "ntain": 510, "Ġgr": 511, "Ġhunter": 512, "ite": 513, "TER": 514, "TERM": 515, "ly": 516, "sc": 517, "day": 518, "Ġdrink": 519, "Ġar": 520, "mp": 521, "ning": 522, "ice": 523, "Ġmoney": 524, "Ġmarriage": 525, "Ġroo": 526, "jump": 527, "POST": 528, "Ġbig": 529, "ĠO": 530, "our": 531, "aut": 532, "Ġforest": 533, "ale": 534, "EQU": 535, "sm": 536, "ĠT": 537, "Ġhear": 538, "Ġsad": 539, "Ġeag": 540, "Ġeagle": 541, "Ġbeaut": 542, "ead": 543, "Ġmountain": 544, "fore": 545, "Ġbefore": 546, "Ġbear": 547, "ild": 548, "Ġwho": 549, "die": 550, "ĠR": 551, "Ġstick": 552, "uest": 553, "cut": 554, "Ġfort": 555, "Ġapp": 556, "ate": 557, "ct": 558, "HI": 559, "OHI": 560, "PROHI": 561, "PROHIB": 562, "ound": 563, "Ġbegin": 564, "Ġside": 565, "ird": 566, "erd": 567, "ation": 568, "Ġmeat": 569, "mor": 570, "ith": 571, "morning": 572, "ure": 573, "look": 574, "Ġlet": 575, "ol": 576, "ity": 577, "und": 578, "iful": 579, "Ġbeautiful": 580, "Ġclo": 581, "alth": 582, "Ġsend": 583, "Ġagree": 584, "ich": 585, "Ġsadness": 586, "Ġjump": 587, "beat": 588, "Ġclothing": 589, "ra": 590, "Ġo": 591, "wood": 592, "Ġchild": 593, "Ġbird": 594, "Ġbre": 595, "show": 596, "exist": 597, "Ġfirewood": 598, "ape": 599, "ire": 600, "Ġon": 601, "Ġtake": 602, "Ġhit": 603, "place": 604, "dle": 605, "bad": 606, "hbad": 607, "azhbad": 608, "ĠRazhbad": 609, "ĠRazhbadin": 610, "Ġsun": 611, "Ġspring": 612, "must": 613, "iddle": 614, "av": 615, "big": 616, "ic": 617, "tie": 618, "bu": 619, "ĠM": 620, "Ġtoday": 621, "Ġdoor": 622, "Ġbl": 623, "more": 624, "Ġru": 625, "Ġmer": 626, "chman": 627, "ait": 628, "Ġhenchman": 629, "ger": 630, "mo": 631, "ase": 632, "Ġdad": 633, "ting": 634, "Ġbull": 635, "Ġq": 636, "ress": 637, "chant": 638, "Ġmerchant": 639, "Ġwol": 640, "Ġwolf": 641, "RD": 642, "Ġsc": 643, "less": 644, "irst": 645, "middle": 646, "Ġend": 647, "ish": 648, "imal": 649, "animal": 650, "jug": 651, "Ġtale": 652, "Ġride": 653, "Ġwid": 654, "oot": 655, "Ġwidow": 656, "air": 657, "Ġshout": 658, "alk": 659, "Ġhide": 660, "Ġwealth": 661, "Ġthither": 662, "Ġcattle": 663, "ĠIsm": 664, "ĠIsmail": 665, "eal": 666, "scape": 667, "Ġpre": 668, "Ġwhere": 669, "Ġnear": 670, "ast": 671, "where": 672, "you": 673, "sw": 674, "Ġlook": 675, "key": 676, "marry": 677, "ĠORD": 678, "gather": 679, "verthe": 680, "Ġneverthe": 681, "Ġnevertheless": 682, "ers": 683, "Ġfri": 684, "Ġevery": 685, "Ġansw": 686, "Ġanswer": 687, "Ġde": 688, "Ġfriend": 689, "ittle": 690, "young": 691, "Ġseven": 692, "ren": 693, "Ġchildren": 694, "head": 695, "Ġcame": 696, "Ġcamel": 697, "Ġeven": 698, "Ġund": 699, "Ġunder": 700, "ĠU": 701, "Ġruble": 702, "Ġsea": 703, "Ġturn": 704, "most": 705, "Ġwind": 706, "rice": 707, "Ġfe": 708, "quest": 709, "Ġrequest": 710, "ip": 711, "for": 712, "my": 713, "ĠB": 714, "ĠK": 715, "Ġdie": 716, "pt": 717, "cept": 718, "lif": 719, "Ġsuch": 720, "herd": 721, "Ġshep": 722, "Ġshepherd": 723, "Ġahead": 724, "Ġring": 725, "Ġsell": 726, "Ġfive": 727, "back": 728, "fall": 729, "Ġbur": 730, "little": 731, "Ġrif": 732, "Ġrifle": 733, "ĠAli": 734, "Ġfind": 735, "Ġtr": 736, "pper": 737, "Ġcopper": 738, "Ġwealthy": 739, "Ġfin": 740, "steal": 741, "Ġent": 742, "Ġentire": 743, "tt": 744, "Ġyear": 745, "dd": 746, "ho": 747, "kh": 748, "behind": 749, "ough": 750, "Ġbel": 751, "ock": 752, "Ġal": 753, "Ġevening": 754, "nake": 755, "OPT": 756, "iz": 757, "Ġcap": 758, "ule": 759, "adi": 760, "time": 761, "Ġhair": 762, "Ġwhich": 763, "are": 764, "Ġear": 765, "Ġsnake": 766, "stand": 767, "Ġwork": 768, "first": 769, "Ġstep": 770, "Ġmat": 771, "live": 772, "arth": 773, "Ġearth": 774, "Ġunderstand": 775, "ĠH": 776, "with": 777, "goat": 778, "ance": 779, "ĠTav": 780, "ĠTavadi": 781, "pers": 782, "Ġup": 783, "Ġdownward": 784, "person": 785, "ĠG": 786, "orrow": 787, "Ġbow": 788, "ong": 789, "usa": 790, "lp": 791, "Ġhelp": 792, "Ġword": 793, "Ġdag": 794, "Ġdagger": 795, "di": 796, "Ġwindow": 797, "calf": 798, "laughter": 799, "slaughter": 800, "Ġappear": 801, "Ġpr": 802, "Ġbread": 803, "Ġsome": 804, "onkey": 805, "Ġdonkey": 806, "Ġagain": 807, "ee": 808, "Ġexcept": 809, "Ġthen": 810, "pl": 811, "Ġanymore": 812, "Ġfar": 813, "Ġcow": 814, "ah": 815, "ZA": 816, "Ġaround": 817, "ute": 818, "run": 819, "ment": 820, "dv": 821, "Ġadv": 822, "ool": 823, "Ġadvice": 824, "une": 825, "ade": 826, "sit": 827, "Ġtow": 828, "ards": 829, "Ġtowards": 830, "return": 831, "of": 832, "ous": 833, "ac": 834, "Ġbag": 835, "Ġgla": 836, "Ġglass": 837, "ass": 838, "Ġmuch": 839, "uick": 840, "vite": 841, "Ġinvite": 842, "Ġsomething": 843, "Ġsu": 844, "sent": 845, "ive": 846, "HUN": 847, "LHUN": 848, "Ġtalent": 849, "Ġsit": 850, "Ġmouth": 851, "Ġshoot": 852, "sp": 853, "Ġbell": 854, "Ġbelly": 855, "above": 856, "Ġkill": 857, "ster": 858, "hit": 859, "Ġhunting": 860, "Ġlight": 861, "shed": 862, "Ġcall": 863, "lift": 864, "each": 865, "od": 866, "Ġcom": 867, "che": 868, "Ġtom": 869, "Ġblood": 870, "Ġor": 871, "Ġfortune": 872, "ream": 873, "ief": 874, "happy": 875, "Ġquick": 876, "begin": 877, "Ġvery": 878, "Ġthrice": 879, "Ġname": 880, "xt": 881, "STR": 882, "INSTR": 883, "ever": 884, "pull": 885, "Ġair": 886, "Ġbring": 887, "ngth": 888, "Ġtomorrow": 889, "Ġteach": 890, "Ġten": 891, "Ġwell": 892, "Ġhowever": 893, "Ġrooster": 894, "qis": 895, "POT": 896, "Ġbox": 897, "ilqis": 898, "Ġfish": 899, "ĠBilqis": 900, "ĠBilqisdi": 901, "hide": 902, "ney": 903, "ND": 904, "COND": 905, "Ġfortress": 906, "ien": 907, "Ġboat": 908, "night": 909, "ug": 910, "ĠAra": 911, "ience": 912, "wait": 913, "Ġupward": 914, "Ġcattleshed": 915, "ige": 916, "Ġdream": 917, "Ġgrave": 918, "ak": 919, "Ġover": 920, "Ġspan": 921, "bil": 922, "Ġarmy": 923, "Ġthink": 924, "Ġthinking": 925, "Ġdog": 926, "ier": 927, "buy": 928, "ect": 929, "Ġleg": 930, "Ġneither": 931, "open": 932, "dy": 933, "dge": 934, "omed": 935, "agomed": 936, "Ġworld": 937, "Ġgran": 938, "ab": 939, "Ġviz": 940, "Ġvizier": 941, "IR": 942, "IRR": 943, "zan": 944, "Ġdis": 945, "buzan": 946, "ĠArabuzan": 947, "sein": 948, "ussein": 949, "ĠHussein": 950, "Ġwhite": 951, "est": 952, "Ġhalf": 953, "Ġide": 954, "tty": 955, "Ġidea": 956, "Ġbut": 957, "IMP": 958, "Ġbaz": 959, "Ġbazar": 960, "atch": 961, "Ġtie": 962, "Ġapple": 963, "gry": 964, "Ġbury": 965, "ket": 966, "pre": 967, "Ġinto": 968, "pretty": 969, "Ġreturn": 970, "eed": 971, "Ġwait": 972, "indeed": 973, "Ġsee": 974, "ank": 975, "wool": 976, "fight": 977, "Ġescape": 978, "plain": 979, "stead": 980, "Ġexam": 981, "loor": 982, "Ġneigh": 983, "lock": 984, "Ġneighb": 985, "Ġper": 986, "pute": 987, "Ġdispute": 988, "Ġroom": 989, "DU": 990, "DUB": 991, "Ġneck": 992, "Ġcure": 993, "Ġpour": 994, "LZ": 995, "MLZ": 996, "NMLZ": 997, "love": 998, "ĠUm": 999, "Ġmill": 1000, "cket": 1001, "Ġpocket": 1002, "remain": 1003, "Ġquickness": 1004, "ĠKusa": 1005, "rest": 1006, "ose": 1007, "Ġart": 1008, "Ġwood": 1009, "icle": 1010, "Ġarticle": 1011, "fr": 1012, "Ġcry": 1013, "Ġpole": 1014, "Ġland": 1015, "Ġagreement": 1016, "small": 1017, "escape": 1018, "yard": 1019, "ouch": 1020, "Ġherd": 1021, "Ġif": 1022, "reak": 1023, "Ġcon": 1024, "Ġram": 1025, "Ġknow": 1026, "ang": 1027, "Ġgraveyard": 1028, "Ġeat": 1029, "rength": 1030, "Ġstrength": 1031, "ally": 1032, "Ġsear": 1033, "ali": 1034, "Ġsearch": 1035, "qil": 1036, "sme": 1037, "qilich": 1038, "smear": 1039, "ro": 1040, "Ġdoct": 1041, "Ġdoctor": 1042, "Ġgard": 1043, "Ġgarden": 1044, "Ġfinally": 1045, "um": 1046, "Ġful": 1047, "Ġfulfill": 1048, "hood": 1049, "iss": 1050, "ĠQ": 1051, "cÃ": 1052, "ancÃ": 1053, "ĠfiancÃ": 1054, "Ġfiancé": 1055 }, "merges": [ "n d", "a r", "s t", "e nd", "ar t", "Ġ <", "st art", "I I", "C V", "CV B", "F V", "P FV", "D E", "S S", "B L", "Ġ II", "E R", "Ġ DE", "ĠDE M", "Ġ b", "m e", "S T", "O BL", "e r", "S G", "A T", "P ST", "E SS", "O P", "T OP", "P L", "Ġ s", "P R", "t h", "L AT", "Ġ I", "ĠII I", "o u", "Ġb e", "ER G", "E N", "G EN", "i n", "N T", "Ġ h", "ĠI V", "Ġ w", "o me", "a y", "U N", "I N", "o n", "UN W", "a n", "c ome", "PR T", "Ġ y", "r e", "Ġ g", "l e", "P O", "Ġy ou", "Q U", "th er", "Ġ me", "S U", "I SG", "O T", "QU OT", "PO SS", "Ġ d", "a t", "Ġ f", "l l", "Ġ t", "II SG", "P ER", "SU PER", "v e", "o w", "a nd", "Ġ a", "Ġ m", "PR S", "DE F", "A D", "o r", "in g", "Ġs ay", "Ġ th", "Ġ p", "on e", "A BL", "C O", "A NT", "E G", "N EG", "b e", "i d", "CO NT", "s e", "Ġ c", "k e", "d o", "g e", "I M", "o o", "I PFV", "c h", "Ġ one", "id e", "a d", "a ke", "E M", "P H", "EM PH", "Ġ e", "Ġg i", "o ther", "N PRS", "t er", "IN F", "Ġ r", "Ġw h", "Ġ k", "g h", "Ġg o", "I PL", "I T", "W IT", "be come", "Ġb o", "c k", "i ll", "h an", "g o", "e n", "i t", "t ake", "V ER", "VER S", "E S", "R ES", "T R", "AT TR", "c e", "C NT", "CNT R", "Ġ n", "Ġk han", "l d", "C N", "Ġ in", "a l", "F U", "FU T", "Ġbo y", "M S", "MS D", "Ġ come", "P U", "u t", "s ide", "A PU", "APU D", "a w", "i f", "u n", "p p", "ther e", "i nd", "Ġw e", "D I", "DI ST", "re e", "s s", "aw ay", "oo d", "Ġ there", "u r", "CN D", "Ġb r", "Ġh e", "Ġm an", "ou t", "v er", "Ġa s", "e ll", "o m", "Ġ le", "Ġgi ve", "a u", "a in", "au gh", "Ġbe come", "Ġ l", "augh ter", "Ġs h", "er e", "ar d", "Ġas k", "S IM", ") .", "i e", "r l", "Ġ st", "a ther", "Ġh ome", "Ġbr other", "Ġ re", "a g", "o ve", "Ġgi rl", "i l", "Ġs on", "s h", "a ge", "r ow", "Ġd aughter", "a pp", "n t", "e p", "e t", "r ing", "e ar", "i r", "Ġd ay", "r i", "Ġt ell", "n g", "ur n", "u p", "a ve", "IM PR", "ve n", "Ġs o", "a ck", "u ch", "r y", "or se", "Ġwh at", "o re", "i st", "o ld", "Ġin side", "Ġh orse", "Ġth ing", "if e", "ge t", "Ġ v", "b ring", "o p", "an t", "Ġm other", "e at", "Ġf ather", "b ove", "e ven", "Ġt o", "Ġp ut", "at er", "Ġw ater", "Ġd r", "SU B", "Ġw ife", "Ġth ree", "l a", "Ġf i", "C S", "CS L", "t urn", "Ġth row", "a m", "u s", "w ard", "Ġn e", "h app", "Ġyou ng", "n e", "Ġf r", "Ġle ave", "Ġn ow", "i gh", "Ġa bove", "Ġt w", "Ġ out", "Ġout side", "A U", "C AU", "CAU S", "ow n", "m uch", "l o", "Ġh ere", "i g", "Ġv ill", "Ġvill age", "a ll", "ar ry", "f ter", "Ġa fter", "i ck", "Ġb ack", "DIST R", "Ġd own", "ou se", "happ en", "i on", "Ġ -", "Ġtw o", "Ġ an", "se e", "Ġfr om", "m ain", "i me", "h ind", "n ow", "la ce", "Ġd o", "k ill", "j u", "Ġg et", "le t", "u l", "f ill", "th e", "w ant", "Ġ old", "u e", "Ġh ow", "A L", "AL L", "Ġh ouse", "e d", "II PL", "I NT", "oo k", "Ġsh e", "u ll", "IM M", "Ġp e", "Ġh un", "Ġm ou", "a p", "ge ther", "Ġto gether", "igh t", "s end", "Ġre main", "Ġw ay", "Ġa ll", "op le", "f ind", "in k", "Ġr un", "Ġs p", "Ġgo ld", "Ġs ist", "Ġh and", "Ġsist er", "a il", "Ġp o", "L CV", "ne ss", "Ġhe art", "th ing", "m an", "l i", "Ġr i", "Ġw or", "a me", "g ood", "i s", "a s", "ag on", "Ġdr agon", "Ġpe ople", "Ġbe hind", "t o", "Ġ A", "b and", "Ġh us", "Ġhus band", "Ġwh y", "Ġf o", "CN C", "om an", "Ġa g", "Ġt ime", "Ġf or", "k now", "Ġs le", "Ġe x", "b le", "t le", "g in", "y e", "Ġe ye", "in e", "ward s", "ar ri", "arri age", "e a", "or y", "Ġst ory", "le ad", "a z", "Ġc h", "c arry", "Ġc o", "Ġfo x", "i ther", "one y", "Ġf ore", "Ġw oman", "Ġf ood", "h ere", "Ġan y", "Ġafter wards", "Ġme et", "Ġfi re", "Ġt ree", "Ġhe ad", "e x", "Ġshe ep", "Ġsle ep", "ver y", "al f", "Ġth e", "Ġri ver", "Ġ other", "Ġc at", "i m", "Ġp lace", "u st", "Ġ at", "Ġh en", "app ear", "nt ain", "Ġg r", "Ġhun ter", "it e", "T ER", "TER M", "l y", "s c", "d ay", "Ġdr ink", "Ġ ar", "m p", "n ing", "i ce", "Ġm oney", "Ġm arriage", "Ġr oo", "ju mp", "PO ST", "Ġb ig", "Ġ O", "ou r", "a ut", "Ġfore st", "a le", "E QU", "s m", "Ġ T", "Ġhe ar", "Ġs ad", "Ġe ag", "Ġeag le", "Ġbe aut", "e ad", "Ġmou ntain", "f ore", "Ġbe fore", "Ġbe ar", "i ld", "Ġwh o", "d ie", "Ġ R", "Ġst ick", "ue st", "c ut", "Ġfor t", "Ġa pp", "at e", "c t", "H I", "O HI", "PR OHI", "PROHI B", "ou nd", "Ġbe gin", "Ġs ide", "ir d", "er d", "at ion", "Ġme at", "m or", "i th", "mor ning", "u re", "l ook", "Ġle t", "o l", "it y", "u nd", "if ul", "Ġbeaut iful", "Ġc lo", "al th", "Ġs end", "Ġag ree", "i ch", "Ġsad ness", "Ġ jump", "be at", "Ġclo thing", "r a", "Ġ o", "w ood", "Ġch ild", "Ġb ird", "Ġb re", "sh ow", "ex ist", "Ġfire wood", "ap e", "i re", "Ġ on", "Ġt ake", "Ġh it", "p lace", "d le", "b ad", "h bad", "az hbad", "ĠR azhbad", "ĠRazhbad in", "Ġs un", "Ġsp ring", "m ust", "id dle", "a v", "b ig", "i c", "t ie", "b u", "Ġ M", "Ġto day", "Ġdo or", "Ġb l", "m ore", "Ġr u", "Ġme r", "ch man", "a it", "Ġhen chman", "g er", "m o", "a se", "Ġd ad", "t ing", "Ġb ull", "Ġ q", "re ss", "ch ant", "Ġmer chant", "Ġw ol", "Ġwol f", "R D", "Ġs c", "le ss", "ir st", "m iddle", "Ġ end", "i sh", "im al", "an imal", "ju g", "Ġt ale", "Ġr ide", "Ġw id", "oo t", "Ġwid ow", "a ir", "Ġsh out", "al k", "Ġh ide", "Ġwe alth", "Ġth ither", "Ġcat tle", "ĠI sm", "ĠIsm ail", "e al", "sc ape", "Ġp re", "Ġwh ere", "Ġn ear", "a st", "w here", "y ou", "s w", "Ġl ook", "ke y", "m arry", "ĠO RD", "g ather", "ver the", "Ġne verthe", "Ġneverthe less", "er s", "Ġf ri", "Ġe very", "Ġan sw", "Ġansw er", "Ġd e", "Ġfri end", "it tle", "you ng", "Ġs even", "re n", "Ġchild ren", "h ead", "Ġc ame", "Ġcame l", "Ġe ven", "Ġ und", "Ġund er", "Ġ U", "Ġru ble", "Ġs ea", "Ġt urn", "mo st", "Ġw ind", "ri ce", "Ġf e", "q uest", "Ġre quest", "i p", "f or", "m y", "Ġ B", "Ġ K", "Ġd ie", "p t", "ce pt", "l if", "Ġs uch", "h erd", "Ġsh ep", "Ġshep herd", "Ġa head", "Ġr ing", "Ġs ell", "Ġfi ve", "b ack", "f all", "Ġb ur", "l ittle", "Ġr if", "Ġrif le", "ĠA li", "Ġf ind", "Ġt r", "pp er", "Ġco pper", "Ġwealth y", "Ġf in", "st eal", "Ġe nt", "Ġent ire", "t t", "Ġy ear", "d d", "h o", "k h", "be hind", "ou gh", "Ġbe l", "o ck", "Ġa l", "Ġeven ing", "n ake", "OP T", "i z", "Ġc ap", "u le", "ad i", "t ime", "Ġh air", "Ġwh ich", "ar e", "Ġe ar", "Ġs nake", "st and", "Ġwor k", "f irst", "Ġst ep", "Ġm at", "li ve", "art h", "Ġe arth", "Ġunder stand", "Ġ H", "w ith", "go at", "an ce", "ĠT av", "ĠTav adi", "p ers", "Ġ up", "Ġdown ward", "pers on", "Ġ G", "or row", "Ġb ow", "on g", "us a", "l p", "Ġhe lp", "Ġwor d", "Ġd ag", "Ġdag ger", "d i", "Ġwind ow", "c alf", "l aughter", "s laughter", "Ġapp ear", "Ġp r", "Ġbre ad", "Ġs ome", "on key", "Ġd onkey", "Ġag ain", "e e", "Ġex cept", "Ġth en", "p l", "Ġany more", "Ġf ar", "Ġc ow", "a h", "Z A", "Ġar ound", "ut e", "r un", "me nt", "d v", "Ġa dv", "oo l", "Ġadv ice", "un e", "ad e", "s it", "Ġt ow", "ard s", "Ġtow ards", "re turn", "o f", "ou s", "a c", "Ġb ag", "Ġg la", "Ġgla ss", "a ss", "Ġm uch", "u ick", "v ite", "Ġin vite", "Ġsome thing", "Ġs u", "se nt", "i ve", "H UN", "L HUN", "Ġtale nt", "Ġs it", "Ġmou th", "Ġsh oot", "s p", "Ġbe ll", "Ġbell y", "a bove", "Ġk ill", "st er", "h it", "Ġhun ting", "Ġl ight", "sh ed", "Ġc all", "lif t", "ea ch", "o d", "Ġc om", "ch e", "Ġt om", "Ġbl ood", "Ġ or", "Ġfort une", "re am", "ie f", "happ y", "Ġq uick", "be gin", "Ġ very", "Ġth rice", "Ġn ame", "x t", "ST R", "IN STR", "e ver", "p ull", "Ġa ir", "Ġbr ing", "ng th", "Ġtom orrow", "Ġt each", "Ġt en", "Ġwe ll", "Ġhow ever", "Ġroo ster", "q is", "PO T", "Ġbo x", "il qis", "Ġfi sh", "ĠB ilqis", "ĠBilqis di", "h ide", "ne y", "N D", "CO ND", "Ġfort ress", "i en", "Ġbo at", "n ight", "u g", "ĠA ra", "ien ce", "w ait", "Ġup ward", "Ġcattle shed", "i ge", "Ġd ream", "Ġgr ave", "a k", "Ġo ver", "Ġsp an", "b il", "Ġar my", "Ġth ink", "Ġthink ing", "Ġdo g", "i er", "bu y", "e ct", "Ġle g", "Ġne ither", "op en", "d y", "d ge", "ome d", "ag omed", "Ġwor ld", "Ġgr an", "a b", "Ġv iz", "Ġviz ier", "I R", "IR R", "z an", "Ġd is", "bu zan", "ĠAra buzan", "se in", "us sein", "ĠH ussein", "Ġwh ite", "e st", "Ġh alf", "Ġ ide", "tt y", "Ġide a", "Ġb ut", "IM P", "Ġb az", "Ġbaz ar", "at ch", "Ġt ie", "Ġapp le", "g ry", "Ġbur y", "ke t", "p re", "Ġin to", "pre tty", "Ġre turn", "e ed", "Ġw ait", "ind eed", "Ġs ee", "an k", "w ool", "f ight", "Ġe scape", "pl ain", "st ead", "Ġex am", "lo or", "Ġne igh", "lo ck", "Ġneigh b", "Ġp er", "p ute", "Ġdis pute", "Ġroo m", "D U", "DU B", "Ġne ck", "Ġc ure", "Ġp our", "L Z", "M LZ", "N MLZ", "l ove", "ĠU m", "Ġm ill", "c ket", "Ġpo cket", "re main", "Ġquick ness", "ĠK usa", "re st", "o se", "Ġ art", "Ġw ood", "ic le", "Ġart icle", "f r", "Ġc ry", "Ġpo le", "Ġl and", "Ġagree ment", "sm all", "e scape", "y ard", "ou ch", "Ġh erd", "Ġ if", "re ak", "Ġc on", "Ġr am", "Ġk now", "an g", "Ġgrave yard", "Ġe at", "re ngth", "Ġst rength", "all y", "Ġs ear", "al i", "Ġsear ch", "q il", "s me", "qil ich", "sme ar", "r o", "Ġdo ct", "Ġdoct or", "Ġg ard", "Ġgard en", "Ġfin ally", "u m", "Ġf ul", "Ġful fill", "h ood", "i ss", "Ġ Q", "c Ã", "an cÃ", "Ġfi ancÃ", "Ġfiancà ©" ] } }