GleamEyeBeast commited on
Commit
00122e7
1 Parent(s): 0ee9e71

add tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +1 -0
  2. tokenizer_config.json +1 -0
  3. vocab.json +1 -0
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "replace_word_delimiter_char": " ", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"'": 1, "-": 2, "9": 3, "A": 4, "B": 5, "C": 6, "D": 7, "E": 8, "F": 9, "G": 10, "H": 11, "I": 12, "J": 13, "K": 14, "L": 15, "M": 16, "N": 17, "O": 18, "P": 19, "Q": 20, "R": 21, "S": 22, "T": 23, "U": 24, "V": 25, "W": 26, "X": 27, "Y": 28, "Z": 29, "a": 30, "b": 31, "c": 32, "d": 33, "e": 34, "f": 35, "g": 36, "h": 37, "i": 38, "j": 39, "k": 40, "l": 41, "m": 42, "n": 43, "o": 44, "p": 45, "q": 46, "r": 47, "s": 48, "t": 49, "u": 50, "v": 51, "w": 52, "x": 53, "y": 54, "z": 55, "一": 56, "丁": 57, "七": 58, "万": 59, "三": 60, "上": 61, "下": 62, "不": 63, "与": 64, "丑": 65, "专": 66, "且": 67, "世": 68, "业": 69, "东": 70, "丢": 71, "两": 72, "严": 73, "丧": 74, "个": 75, "中": 76, "丰": 77, "串": 78, "临": 79, "丹": 80, "为": 81, "主": 82, "丽": 83, "举": 84, "久": 85, "么": 86, "义": 87, "之": 88, "乌": 89, "乎": 90, "乏": 91, "乐": 92, "乒": 93, "乓": 94, "九": 95, "也": 96, "习": 97, "乡": 98, "书": 99, "买": 100, "乱": 101, "了": 102, "予": 103, "争": 104, "事": 105, "二": 106, "于": 107, "亏": 108, "云": 109, "互": 110, "五": 111, "亚": 112, "些": 113, "亡": 114, "交": 115, "产": 116, "享": 117, "京": 118, "亮": 119, "亲": 120, "人": 121, "亿": 122, "什": 123, "仅": 124, "今": 125, "介": 126, "仍": 127, "从": 128, "仔": 129, "他": 130, "付": 131, "仙": 132, "代": 133, "令": 134, "以": 135, "们": 136, "仰": 137, "件": 138, "价": 139, "任": 140, "份": 141, "仿": 142, "企": 143, "伊": 144, "伍": 145, "休": 146, "众": 147, "优": 148, "伙": 149, "会": 150, "伞": 151, "传": 152, "伤": 153, "伯": 154, "估": 155, "伴": 156, "似": 157, "伽": 158, "但": 159, "位": 160, "低": 161, "住": 162, "体": 163, "何": 164, "余": 165, "佛": 166, "作": 167, "你": 168, "佣": 169, "佬": 170, "佳": 171, "使": 172, "侈": 173, "例": 174, "供": 175, "依": 176, "侠": 177, "侧": 178, "侯": 179, "侵": 180, "便": 181, "促": 182, "俊": 183, "俗": 184, "保": 185, "信": 186, "修": 187, "俱": 188, "倍": 189, "倒": 190, "候": 191, "值": 192, "倾": 193, "假": 194, "偏": 195, "做": 196, "停": 197, "健": 198, "偶": 199, "偷": 200, "储": 201, "催": 202, "傲": 203, "像": 204, "儿": 205, "允": 206, "元": 207, "兄": 208, "充": 209, "先": 210, "光": 211, "克": 212, "免": 213, "兔": 214, "入": 215, "全": 216, "八": 217, "公": 218, "六": 219, "兰": 220, "共": 221, "关": 222, "兴": 223, "兵": 224, "其": 225, "具": 226, "典": 227, "养": 228, "兼": 229, "兽": 230, "内": 231, "再": 232, "冒": 233, "写": 234, "军": 235, "农": 236, "冠": 237, "冰": 238, "冲": 239, "决": 240, "况": 241, "冷": 242, "准": 243, "凌": 244, "减": 245, "几": 246, "凡": 247, "凸": 248, "出": 249, "击": 250, "刀": 251, "刃": 252, "分": 253, "切": 254, "划": 255, "刘": 256, "则": 257, "刚": 258, "创": 259, "初": 260, "删": 261, "判": 262, "利": 263, "别": 264, "刮": 265, "到": 266, "制": 267, "刷": 268, "刺": 269, "刻": 270, "剂": 271, "削": 272, "前": 273, "剑": 274, "剧": 275, "剩": 276, "副": 277, "力": 278, "办": 279, "功": 280, "加": 281, "务": 282, "劣": 283, "动": 284, "助": 285, "努": 286, "励": 287, "劳": 288, "势": 289, "勇": 290, "勒": 291, "勾": 292, "包": 293, "化": 294, "北": 295, "匹": 296, "区": 297, "十": 298, "千": 299, "升": 300, "午": 301, "半": 302, "华": 303, "协": 304, "卓": 305, "单": 306, "卖": 307, "南": 308, "博": 309, "占": 310, "卡": 311, "卢": 312, "卧": 313, "卫": 314, "印": 315, "危": 316, "即": 317, "却": 318, "卷": 319, "厂": 320, "厅": 321, "历": 322, "厉": 323, "压": 324, "厌": 325, "厕": 326, "原": 327, "去": 328, "参": 329, "又": 330, "叉": 331, "及": 332, "友": 333, "双": 334, "反": 335, "发": 336, "取": 337, "受": 338, "变": 339, "叛": 340, "口": 341, "古": 342, "句": 343, "另": 344, "只": 345, "叫": 346, "叭": 347, "可": 348, "台": 349, "史": 350, "右": 351, "叶": 352, "号": 353, "司": 354, "吃": 355, "各": 356, "合": 357, "同": 358, "名": 359, "后": 360, "吐": 361, "向": 362, "吓": 363, "吗": 364, "否": 365, "吧": 366, "听": 367, "启": 368, "吵": 369, "吸": 370, "吹": 371, "吼": 372, "呀": 373, "呃": 374, "呆": 375, "告": 376, "呐": 377, "呗": 378, "员": 379, "呛": 380, "呢": 381, "呦": 382, "周": 383, "味": 384, "呵": 385, "呼": 386, "命": 387, "和": 388, "咎": 389, "咖": 390, "咨": 391, "咯": 392, "咱": 393, "咸": 394, "品": 395, "哆": 396, "哇": 397, "哈": 398, "响": 399, "哎": 400, "哥": 401, "哦": 402, "哪": 403, "哭": 404, "哲": 405, "哼": 406, "唉": 407, "唐": 408, "唔": 409, "唤": 410, "售": 411, "唯": 412, "唱": 413, "商": 414, "啊": 415, "啡": 416, "啥": 417, "啦": 418, "啧": 419, "啪": 420, "喂": 421, "善": 422, "喇": 423, "喊": 424, "喜": 425, "喝": 426, "喻": 427, "嗯": 428, "嘛": 429, "嘞": 430, "嘴": 431, "嘿": 432, "噢": 433, "器": 434, "噪": 435, "噱": 436, "嚯": 437, "四": 438, "回": 439, "因": 440, "团": 441, "园": 442, "困": 443, "围": 444, "固": 445, "国": 446, "图": 447, "圈": 448, "土": 449, "在": 450, "地": 451, "圳": 452, "场": 453, "圾": 454, "均": 455, "坏": 456, "坐": 457, "坑": 458, "块": 459, "坚": 460, "坡": 461, "垃": 462, "型": 463, "垫": 464, "埋": 465, "城": 466, "域": 467, "培": 468, "基": 469, "堂": 470, "堆": 471, "堕": 472, "塔": 473, "塘": 474, "塞": 475, "填": 476, "境": 477, "墙": 478, "增": 479, "壁": 480, "士": 481, "壮": 482, "声": 483, "处": 484, "备": 485, "复": 486, "夏": 487, "外": 488, "多": 489, "夜": 490, "够": 491, "大": 492, "天": 493, "太": 494, "夫": 495, "央": 496, "失": 497, "头": 498, "夸": 499, "夺": 500, "奇": 501, "奋": 502, "奏": 503, "契": 504, "奖": 505, "套": 506, "奠": 507, "奢": 508, "奥": 509, "女": 510, "奶": 511, "她": 512, "好": 513, "如": 514, "妇": 515, "妈": 516, "妍": 517, "妙": 518, "妨": 519, "妹": 520, "姆": 521, "始": 522, "姐": 523, "委": 524, "姚": 525, "姿": 526, "威": 527, "娜": 528, "娱": 529, "媒": 530, "媲": 531, "嫌": 532, "子": 533, "字": 534, "存": 535, "季": 536, "孤": 537, "学": 538, "孩": 539, "宁": 540, "它": 541, "宅": 542, "宇": 543, "守": 544, "安": 545, "完": 546, "宏": 547, "宗": 548, "官": 549, "宙": 550, "定": 551, "宜": 552, "宝": 553, "实": 554, "宠": 555, "审": 556, "客": 557, "宣": 558, "室": 559, "害": 560, "家": 561, "容": 562, "宽": 563, "宿": 564, "寄": 565, "密": 566, "富": 567, "寝": 568, "察": 569, "寡": 570, "对": 571, "寻": 572, "导": 573, "寿": 574, "封": 575, "射": 576, "将": 577, "小": 578, "少": 579, "尔": 580, "尖": 581, "尝": 582, "尤": 583, "尬": 584, "就": 585, "尴": 586, "尼": 587, "尽": 588, "尾": 589, "局": 590, "屁": 591, "层": 592, "居": 593, "届": 594, "屏": 595, "展": 596, "属": 597, "山": 598, "岁": 599, "岗": 600, "岛": 601, "岩": 602, "岭": 603, "峰": 604, "崖": 605, "崩": 606, "巅": 607, "巍": 608, "川": 609, "州": 610, "巢": 611, "工": 612, "左": 613, "巧": 614, "巨": 615, "巩": 616, "差": 617, "己": 618, "已": 619, "巴": 620, "币": 621, "市": 622, "布": 623, "帅": 624, "师": 625, "希": 626, "帐": 627, "帖": 628, "帝": 629, "带": 630, "席": 631, "帮": 632, "常": 633, "幅": 634, "幕": 635, "干": 636, "平": 637, "年": 638, "并": 639, "幸": 640, "幻": 641, "幼": 642, "广": 643, "庆": 644, "床": 645, "序": 646, "库": 647, "应": 648, "底": 649, "府": 650, "废": 651, "度": 652, "座": 653, "庭": 654, "康": 655, "庸": 656, "延": 657, "建": 658, "开": 659, "异": 660, "弃": 661, "弄": 662, "弊": 663, "式": 664, "引": 665, "弟": 666, "张": 667, "弥": 668, "弯": 669, "弱": 670, "弹": 671, "强": 672, "归": 673, "当": 674, "录": 675, "形": 676, "彩": 677, "影": 678, "彼": 679, "往": 680, "征": 681, "径": 682, "待": 683, "很": 684, "律": 685, "徐": 686, "徒": 687, "得": 688, "循": 689, "微": 690, "德": 691, "徽": 692, "心": 693, "必": 694, "忆": 695, "忍": 696, "志": 697, "忘": 698, "忙": 699, "忠": 700, "快": 701, "念": 702, "忽": 703, "态": 704, "怎": 705, "怕": 706, "怜": 707, "思": 708, "怡": 709, "急": 710, "怦": 711, "性": 712, "怨": 713, "怪": 714, "总": 715, "恋": 716, "恐": 717, "恩": 718, "息": 719, "恶": 720, "悉": 721, "您": 722, "悬": 723, "悲": 724, "情": 725, "惊": 726, "惑": 727, "惜": 728, "惧": 729, "惨": 730, "惩": 731, "惫": 732, "惬": 733, "惯": 734, "想": 735, "意": 736, "感": 737, "愿": 738, "慈": 739, "慌": 740, "慎": 741, "慕": 742, "慢": 743, "慧": 744, "慰": 745, "憾": 746, "懂": 747, "懒": 748, "懵": 749, "戏": 750, "成": 751, "我": 752, "或": 753, "战": 754, "戚": 755, "截": 756, "戴": 757, "户": 758, "房": 759, "所": 760, "扁": 761, "手": 762, "才": 763, "扎": 764, "扑": 765, "扒": 766, "打": 767, "扔": 768, "托": 769, "执": 770, "扩": 771, "扫": 772, "扬": 773, "扯": 774, "扰": 775, "扶": 776, "批": 777, "扼": 778, "找": 779, "承": 780, "技": 781, "抉": 782, "把": 783, "抓": 784, "投": 785, "抗": 786, "折": 787, "抛": 788, "抢": 789, "护": 790, "报": 791, "抱": 792, "押": 793, "抽": 794, "担": 795, "拉": 796, "拍": 797, "拐": 798, "拒": 799, "拓": 800, "拔": 801, "拖": 802, "招": 803, "拟": 804, "拣": 805, "拥": 806, "择": 807, "括": 808, "拭": 809, "拯": 810, "拱": 811, "拼": 812, "拿": 813, "持": 814, "挂": 815, "指": 816, "按": 817, "挑": 818, "挞": 819, "挡": 820, "挣": 821, "挤": 822, "挥": 823, "挨": 824, "挪": 825, "挺": 826, "捅": 827, "损": 828, "换": 829, "据": 830, "捷": 831, "授": 832, "掉": 833, "掌": 834, "排": 835, "探": 836, "接": 837, "控": 838, "推": 839, "措": 840, "提": 841, "插": 842, "握": 843, "搏": 844, "搓": 845, "搜": 846, "搞": 847, "搬": 848, "搭": 849, "携": 850, "摁": 851, "摄": 852, "摆": 853, "摇": 854, "摊": 855, "摔": 856, "撇": 857, "撑": 858, "撕": 859, "撞": 860, "播": 861, "撸": 862, "撼": 863, "擅": 864, "操": 865, "攒": 866, "支": 867, "收": 868, "改": 869, "攻": 870, "���": 871, "政": 872, "故": 873, "效": 874, "敌": 875, "敏": 876, "救": 877, "教": 878, "敢": 879, "散": 880, "数": 881, "整": 882, "文": 883, "料": 884, "断": 885, "斯": 886, "新": 887, "方": 888, "施": 889, "旁": 890, "旅": 891, "族": 892, "无": 893, "既": 894, "日": 895, "旦": 896, "早": 897, "时": 898, "昂": 899, "明": 900, "易": 901, "星": 902, "映": 903, "春": 904, "昧": 905, "昨": 906, "是": 907, "显": 908, "晃": 909, "晋": 910, "晕": 911, "晚": 912, "晨": 913, "普": 914, "景": 915, "智": 916, "暑": 917, "暖": 918, "暗": 919, "暴": 920, "曝": 921, "更": 922, "曾": 923, "替": 924, "最": 925, "月": 926, "有": 927, "朋": 928, "服": 929, "望": 930, "期": 931, "未": 932, "末": 933, "本": 934, "术": 935, "机": 936, "杀": 937, "杂": 938, "权": 939, "杆": 940, "李": 941, "材": 942, "村": 943, "束": 944, "条": 945, "来": 946, "杨": 947, "杯": 948, "杰": 949, "松": 950, "板": 951, "极": 952, "构": 953, "析": 954, "林": 955, "果": 956, "枝": 957, "枪": 958, "架": 959, "枷": 960, "某": 961, "染": 962, "柔": 963, "查": 964, "柿": 965, "标": 966, "栏": 967, "树": 968, "校": 969, "样": 970, "核": 971, "根": 972, "格": 973, "框": 974, "案": 975, "桌": 976, "梗": 977, "梦": 978, "梭": 979, "梯": 980, "械": 981, "梵": 982, "检": 983, "棋": 984, "棒": 985, "椅": 986, "楚": 987, "楼": 988, "概": 989, "榨": 990, "槛": 991, "槟": 992, "槽": 993, "模": 994, "樱": 995, "橡": 996, "欠": 997, "次": 998, "欢": 999, "欣": 1000, "欧": 1001, "欲": 1002, "款": 1003, "歌": 1004, "止": 1005, "正": 1006, "此": 1007, "步": 1008, "武": 1009, "歧": 1010, "歪": 1011, "歹": 1012, "死": 1013, "殊": 1014, "残": 1015, "殖": 1016, "段": 1017, "毁": 1018, "母": 1019, "每": 1020, "比": 1021, "毕": 1022, "毛": 1023, "民": 1024, "气": 1025, "氛": 1026, "氢": 1027, "氧": 1028, "水": 1029, "永": 1030, "求": 1031, "汉": 1032, "汕": 1033, "汗": 1034, "江": 1035, "池": 1036, "污": 1037, "汰": 1038, "汽": 1039, "沃": 1040, "沈": 1041, "沉": 1042, "沙": 1043, "沛": 1044, "沟": 1045, "没": 1046, "河": 1047, "油": 1048, "治": 1049, "沼": 1050, "沿": 1051, "泄": 1052, "泌": 1053, "法": 1054, "泛": 1055, "波": 1056, "泣": 1057, "注": 1058, "泰": 1059, "泳": 1060, "泽": 1061, "洁": 1062, "洋": 1063, "洗": 1064, "洞": 1065, "津": 1066, "洲": 1067, "活": 1068, "派": 1069, "流": 1070, "浅": 1071, "测": 1072, "济": 1073, "浓": 1074, "浙": 1075, "浣": 1076, "浩": 1077, "浪": 1078, "浮": 1079, "海": 1080, "浸": 1081, "消": 1082, "涉": 1083, "涌": 1084, "液": 1085, "涵": 1086, "淀": 1087, "淘": 1088, "深": 1089, "混": 1090, "清": 1091, "渊": 1092, "渐": 1093, "渠": 1094, "温": 1095, "港": 1096, "渲": 1097, "渴": 1098, "游": 1099, "湖": 1100, "湾": 1101, "湿": 1102, "溃": 1103, "溅": 1104, "源": 1105, "溢": 1106, "溺": 1107, "滑": 1108, "满": 1109, "滨": 1110, "滴": 1111, "漂": 1112, "漏": 1113, "演": 1114, "漫": 1115, "潜": 1116, "潭": 1117, "潮": 1118, "澳": 1119, "激": 1120, "灌": 1121, "火": 1122, "灭": 1123, "灯": 1124, "灰": 1125, "灵": 1126, "灿": 1127, "炒": 1128, "炸": 1129, "点": 1130, "炼": 1131, "烂": 1132, "烈": 1133, "烤": 1134, "烦": 1135, "烧": 1136, "热": 1137, "焦": 1138, "然": 1139, "煌": 1140, "照": 1141, "煽": 1142, "熊": 1143, "熏": 1144, "熟": 1145, "熬": 1146, "燃": 1147, "爆": 1148, "爬": 1149, "爱": 1150, "父": 1151, "爸": 1152, "爽": 1153, "片": 1154, "版": 1155, "牌": 1156, "牙": 1157, "牛": 1158, "物": 1159, "牲": 1160, "特": 1161, "牺": 1162, "犀": 1163, "犯": 1164, "状": 1165, "狂": 1166, "狗": 1167, "独": 1168, "狼": 1169, "猎": 1170, "猜": 1171, "猝": 1172, "猫": 1173, "献": 1174, "猴": 1175, "玄": 1176, "率": 1177, "王": 1178, "玛": 1179, "玩": 1180, "环": 1181, "现": 1182, "玻": 1183, "珍": 1184, "珠": 1185, "班": 1186, "球": 1187, "理": 1188, "琐": 1189, "琢": 1190, "琪": 1191, "琴": 1192, "瑜": 1193, "璃": 1194, "璇": 1195, "瓜": 1196, "甄": 1197, "甚": 1198, "甜": 1199, "生": 1200, "甥": 1201, "用": 1202, "甩": 1203, "田": 1204, "由": 1205, "申": 1206, "电": 1207, "男": 1208, "画": 1209, "畅": 1210, "界": 1211, "留": 1212, "略": 1213, "畴": 1214, "疆": 1215, "疏": 1216, "疑": 1217, "疯": 1218, "疲": 1219, "疼": 1220, "疾": 1221, "病": 1222, "症": 1223, "痛": 1224, "痰": 1225, "瘦": 1226, "癌": 1227, "登": 1228, "白": 1229, "百": 1230, "的": 1231, "皮": 1232, "益": 1233, "监": 1234, "盒": 1235, "盖": 1236, "盘": 1237, "盛": 1238, "目": 1239, "盯": 1240, "直": 1241, "相": 1242, "盾": 1243, "省": 1244, "看": 1245, "真": 1246, "眼": 1247, "着": 1248, "睛": 1249, "睡": 1250, "督": 1251, "瞎": 1252, "瞪": 1253, "矛": 1254, "知": 1255, "矩": 1256, "短": 1257, "码": 1258, "研": 1259, "砰": 1260, "破": 1261, "砸": 1262, "础": 1263, "硕": 1264, "硬": 1265, "确": 1266, "碍": 1267, "碎": 1268, "碰": 1269, "碳": 1270, "磨": 1271, "示": 1272, "礼": 1273, "社": 1274, "祉": 1275, "祖": 1276, "祝": 1277, "神": 1278, "票": 1279, "祸": 1280, "禁": 1281, "福": 1282, "离": 1283, "秀": 1284, "私": 1285, "秋": 1286, "种": 1287, "科": 1288, "秒": 1289, "秘": 1290, "租": 1291, "秩": 1292, "积": 1293, "称": 1294, "移": 1295, "程": 1296, "稍": 1297, "稚": 1298, "稳": 1299, "究": 1300, "空": 1301, "穿": 1302, "突": 1303, "窄": 1304, "窝": 1305, "立": 1306, "竖": 1307, "站": 1308, "竞": 1309, "竟": 1310, "章": 1311, "童": 1312, "端": 1313, "竹": 1314, "笑": 1315, "笔": 1316, "符": 1317, "笨": 1318, "第": 1319, "等": 1320, "筐": 1321, "筑": 1322, "答": 1323, "策": 1324, "筛": 1325, "签": 1326, "简": 1327, "算": 1328, "管": 1329, "箭": 1330, "箱": 1331, "篇": 1332, "篑": 1333, "篮": 1334, "篷": 1335, "米": 1336, "类": 1337, "粉": 1338, "粒": 1339, "粘": 1340, "粤": 1341, "粮": 1342, "精": 1343, "糖": 1344, "糟": 1345, "系": 1346, "素": 1347, "索": 1348, "紧": 1349, "累": 1350, "繁": 1351, "纠": 1352, "红": 1353, "约": 1354, "级": 1355, "纪": 1356, "纯": 1357, "纳": 1358, "纸": 1359, "纹": 1360, "线": 1361, "练": 1362, "组": 1363, "细": 1364, "织": 1365, "终": 1366, "绍": 1367, "经": 1368, "结": 1369, "绕": 1370, "给": 1371, "络": 1372, "绝": 1373, "统": 1374, "继": 1375, "绩": 1376, "绪": 1377, "续": 1378, "绳": 1379, "维": 1380, "综": 1381, "绿": 1382, "缓": 1383, "编": 1384, "缘": 1385, "缚": 1386, "缩": 1387, "缺": 1388, "罐": 1389, "网": 1390, "罗": 1391, "罚": 1392, "罪": 1393, "置": 1394, "美": 1395, "羡": 1396, "群": 1397, "羽": 1398, "翔": 1399, "翘": 1400, "翻": 1401, "翼": 1402, "老": 1403, "考": 1404, "者": 1405, "而": 1406, "耍": 1407, "耐": 1408, "耗": 1409, "耳": 1410, "耽": 1411, "聊": 1412, "职": 1413, "联": 1414, "聘": 1415, "聚": 1416, "聪": 1417, "肃": 1418, "肉": 1419, "肌": 1420, "肚": 1421, "股": 1422, "肤": 1423, "肥": 1424, "肪": 1425, "肯": 1426, "育": 1427, "肺": 1428, "胁": 1429, "胃": 1430, "胆": 1431, "背": 1432, "胎": 1433, "胖": 1434, "胜": 1435, "胞": 1436, "胡": 1437, "胶": 1438, "胺": 1439, "能": 1440, "脂": 1441, "脆": 1442, "脉": 1443, "脏": 1444, "脑": 1445, "脚": 1446, "脱": 1447, "脸": 1448, "腾": 1449, "腿": 1450, "膝": 1451, "臂": 1452, "自": 1453, "至": 1454, "致": 1455, "舍": 1456, "舒": 1457, "舞": 1458, "航": 1459, "般": 1460, "良": 1461, "色": 1462, "艺": 1463, "艾": 1464, "节": 1465, "芒": 1466, "芜": 1467, "花": 1468, "芽": 1469, "苏": 1470, "苦": 1471, "英": 1472, "苹": 1473, "范": 1474, "茶": 1475, "草": 1476, "荐": 1477, "荒": 1478, "荧": 1479, "莓": 1480, "莠": 1481, "莫": 1482, "莱": 1483, "莲": 1484, "获": 1485, "菜": 1486, "萄": 1487, "萌": 1488, "营": 1489, "落": 1490, "著": 1491, "葡": 1492, "蓝": 1493, "蔬": 1494, "蔽": 1495, "薄": 1496, "薇": 1497, "薪": 1498, "藏": 1499, "虎": 1500, "虑": 1501, "虚": 1502, "虽": 1503, "虾": 1504, "蛇": 1505, "蛋": 1506, "蛙": 1507, "蛮": 1508, "螃": 1509, "融": 1510, "蟹": 1511, "血": 1512, "行": 1513, "衍": 1514, "街": 1515, "衡": 1516, "衣": 1517, "补": 1518, "表": 1519, "衷": 1520, "袋": 1521, "被": 1522, "裂": 1523, "装": 1524, "裕": 1525, "裸": 1526, "裹": 1527, "西": 1528, "要": 1529, "覆": 1530, "见": 1531, "观": 1532, "规": 1533, "视": 1534, "觉": 1535, "角": 1536, "解": 1537, "触": 1538, "言": 1539, "譬": 1540, "计": 1541, "订": 1542, "认": 1543, "讨": 1544, "让": 1545, "训": 1546, "议": 1547, "讯": 1548, "记": 1549, "讲": 1550, "许": 1551, "论": 1552, "设": 1553, "证": 1554, "评": 1555, "识": 1556, "诉": 1557, "词": 1558, "译": 1559, "试": 1560, "话": 1561, "询": 1562, "该": 1563, "详": 1564, "语": 1565, "误": 1566, "诱": 1567, "说": 1568, "诶": 1569, "请": 1570, "诸": 1571, "诺": 1572, "读": 1573, "课": 1574, "谁": 1575, "调": 1576, "谈": 1577, "谐": 1578, "谓": 1579, "谚": 1580, "谢": 1581, "谣": 1582, "谨": 1583, "谱": 1584, "谷": 1585, "豆": 1586, "象": 1587, "负": 1588, "贡": 1589, "财": 1590, "责": 1591, "败": 1592, "账": 1593, "货": 1594, "质": 1595, "贪": 1596, "贱": 1597, "贴": 1598, "贵": 1599, "贸": 1600, "费": 1601, "赃": 1602, "资": 1603, "赋": 1604, "赌": 1605, "赏": 1606, "赔": 1607, "赚": 1608, "赛": 1609, "赞": 1610, "赢": 1611, "走": 1612, "赵": 1613, "赶": 1614, "起": 1615, "超": 1616, "越": 1617, "趟": 1618, "趣": 1619, "足": 1620, "趴": 1621, "跃": 1622, "跑": 1623, "距": 1624, "跟": 1625, "跨": 1626, "路": 1627, "跳": 1628, "践": 1629, "踏": 1630, "踢": 1631, "踩": 1632, "踪": 1633, "蹈": 1634, "身": 1635, "躺": 1636, "车": 1637, "轨": 1638, "转": 1639, "轮": 1640, "软": 1641, "轻": 1642, "载": 1643, "较": 1644, "辅": 1645, "辆": 1646, "辈": 1647, "辉": 1648, "辑": 1649, "输": 1650, "辛": 1651, "辣": 1652, "辨": 1653, "辩": 1654, "辱": 1655, "边": 1656, "达": 1657, "过": 1658, "运": 1659, "近": 1660, "返": 1661, "还": 1662, "这": 1663, "进": 1664, "远": 1665, "违": 1666, "连": 1667, "迟": 1668, "迪": 1669, "迫": 1670, "迷": 1671, "追": 1672, "退": 1673, "送": 1674, "适": 1675, "逆": 1676, "选": 1677, "透": 1678, "逐": 1679, "递": 1680, "途": 1681, "通": 1682, "逛": 1683, "速": 1684, "造": 1685, "逼": 1686, "遇": 1687, "遍": 1688, "道": 1689, "遗": 1690, "遥": 1691, "遵": 1692, "避": 1693, "邀": 1694, "邓": 1695, "那": 1696, "邦": 1697, "部": 1698, "都": 1699, "配": 1700, "酒": 1701, "酷": 1702, "醒": 1703, "采": 1704, "释": 1705, "里": 1706, "重": 1707, "野": 1708, "量": 1709, "金": 1710, "针": 1711, "钟": 1712, "钢": 1713, "钮": 1714, "钱": 1715, "钻": 1716, "铁": 1717, "铜": 1718, "银": 1719, "铺": 1720, "链": 1721, "锁": 1722, "锅": 1723, "锋": 1724, "错": 1725, "锣": 1726, "键": 1727, "锻": 1728, "镇": 1729, "镜": 1730, "长": 1731, "门": 1732, "闪": 1733, "闭": 1734, "问": 1735, "闲": 1736, "间": 1737, "闹": 1738, "闻": 1739, "阅": 1740, "阔": 1741, "队": 1742, "防": 1743, "阳": 1744, "阴": 1745, "阵": 1746, "阶": 1747, "阻": 1748, "阿": 1749, "附": 1750, "际": 1751, "陆": 1752, "陌": 1753, "降": 1754, "限": 1755, "陕": 1756, "院": 1757, "除": 1758, "险": 1759, "陪": 1760, "陶": 1761, "陷": 1762, "随": 1763, "隐": 1764, "隔": 1765, "障": 1766, "难": 1767, "雄": 1768, "雅": 1769, "集": 1770, "雇": 1771, "雕": 1772, "雨": 1773, "雪": 1774, "零": 1775, "雾": 1776, "需": 1777, "震": 1778, "露": 1779, "青": 1780, "静": 1781, "非": 1782, "靠": 1783, "面": 1784, "革": 1785, "鞋": 1786, "韧": 1787, "韩": 1788, "音": 1789, "页": 1790, "顶": 1791, "项": 1792, "顺": 1793, "须": 1794, "顾": 1795, "顿": 1796, "预": 1797, "领": 1798, "频": 1799, "颓": 1800, "颖": 1801, "题": 1802, "额": 1803, "风": 1804, "飘": 1805, "飞": 1806, "食": 1807, "餐": 1808, "饥": 1809, "饭": 1810, "饮": 1811, "饱": 1812, "饿": 1813, "馆": 1814, "馈": 1815, "首": 1816, "香": 1817, "马": 1818, "驱": 1819, "驶": 1820, "驾": 1821, "骂": 1822, "验": 1823, "骑": 1824, "骨": 1825, "骰": 1826, "骼": 1827, "高": 1828, "魁": 1829, "魂": 1830, "魔": 1831, "鰂": 1832, "鱼": 1833, "鲜": 1834, "鸟": 1835, "鸡": 1836, "鸭": 1837, "鹅": 1838, "鹏": 1839, "鹤": 1840, "鹰": 1841, "麦": 1842, "麻": 1843, "黄": 1844, "黑": 1845, "默": 1846, "鼓": 1847, "齐": 1848, "龄": 1849, "龙": 1850, "|": 0, "[UNK]": 1851, "[PAD]": 1852}