julicee commited on
Commit
cd9c8e7
·
1 Parent(s): fe873d9

add tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<s>": 2671, "</s>": 2672}
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
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": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"a": 1, "d": 2, "e": 3, "g": 4, "i": 5, "l": 6, "o": 7, "p": 8, "q": 9, "、": 10, "。": 11, "《": 12, "》": 13, "「": 14, "」": 15, "ㄟ": 16, "一": 17, "丁": 18, "七": 19, "丈": 20, "三": 21, "上": 22, "下": 23, "不": 24, "且": 25, "世": 26, "丘": 27, "丙": 28, "丟": 29, "並": 30, "中": 31, "串": 32, "丶": 33, "丹": 34, "主": 35, "乃": 36, "久": 37, "之": 38, "乎": 39, "乏": 40, "乖": 41, "乘": 42, "乙": 43, "九": 44, "也": 45, "乳": 46, "乾": 47, "亂": 48, "了": 49, "予": 50, "事": 51, "二": 52, "互": 53, "五": 54, "井": 55, "些": 56, "亞": 57, "亡": 58, "交": 59, "亦": 60, "享": 61, "京": 62, "亭": 63, "亮": 64, "人": 65, "什": 66, "仁": 67, "仆": 68, "仇": 69, "今": 70, "介": 71, "仍": 72, "仔": 73, "他": 74, "付": 75, "仙": 76, "代": 77, "令": 78, "以": 79, "仰": 80, "仲": 81, "件": 82, "任": 83, "份": 84, "仿": 85, "企": 86, "伊": 87, "伏": 88, "伐": 89, "休": 90, "伯": 91, "估": 92, "伴": 93, "伸": 94, "伺": 95, "似": 96, "佃": 97, "但": 98, "佈": 99, "位": 100, "低": 101, "住": 102, "佑": 103, "佔": 104, "何": 105, "作": 106, "你": 107, "佳": 108, "併": 109, "使": 110, "來": 111, "侈": 112, "例": 113, "供": 114, "依": 115, "侮": 116, "侯": 117, "侵": 118, "侶": 119, "便": 120, "係": 121, "促": 122, "俄": 123, "俊": 124, "俗": 125, "保": 126, "信": 127, "修": 128, "俱": 129, "倉": 130, "個": 131, "倍": 132, "們": 133, "倒": 134, "候": 135, "倚": 136, "借": 137, "倡": 138, "値": 139, "倦": 140, "倫": 141, "值": 142, "假": 143, "偉": 144, "偏": 145, "做": 146, "停": 147, "健": 148, "側": 149, "偵": 150, "偶": 151, "偷": 152, "傅": 153, "傍": 154, "傑": 155, "傘": 156, "備": 157, "催": 158, "傲": 159, "傳": 160, "債": 161, "傷": 162, "傻": 163, "傾": 164, "僅": 165, "像": 166, "僚": 167, "僱": 168, "僵": 169, "價": 170, "儀": 171, "億": 172, "儘": 173, "償": 174, "優": 175, "儲": 176, "兀": 177, "允": 178, "元": 179, "兄": 180, "充": 181, "兇": 182, "先": 183, "光": 184, "克": 185, "免": 186, "兒": 187, "入": 188, "內": 189, "全": 190, "兩": 191, "八": 192, "公": 193, "六": 194, "兮": 195, "共": 196, "兵": 197, "其": 198, "具": 199, "典": 200, "兼": 201, "内": 202, "冊": 203, "再": 204, "冒": 205, "冗": 206, "冠": 207, "冤": 208, "冬": 209, "冰": 210, "冷": 211, "准": 212, "凋": 213, "凌": 214, "凍": 215, "凝": 216, "凡": 217, "凱": 218, "凹": 219, "出": 220, "函": 221, "刀": 222, "刁": 223, "分": 224, "切": 225, "刊": 226, "刑": 227, "划": 228, "列": 229, "初": 230, "判": 231, "別": 232, "利": 233, "刪": 234, "到": 235, "制": 236, "刷": 237, "券": 238, "刺": 239, "刻": 240, "則": 241, "前": 242, "剖": 243, "剛": 244, "剝": 245, "剩": 246, "剪": 247, "副": 248, "割": 249, "創": 250, "劃": 251, "劇": 252, "劈": 253, "劉": 254, "劍": 255, "劑": 256, "力": 257, "功": 258, "加": 259, "劣": 260, "助": 261, "努": 262, "勁": 263, "勇": 264, "勉": 265, "動": 266, "勘": 267, "務": 268, "勝": 269, "勞": 270, "募": 271, "勢": 272, "勤": 273, "勳": 274, "勵": 275, "勸": 276, "勾": 277, "勿": 278, "包": 279, "化": 280, "北": 281, "匙": 282, "匯": 283, "匱": 284, "區": 285, "十": 286, "千": 287, "升": 288, "午": 289, "半": 290, "卑": 291, "卓": 292, "協": 293, "南": 294, "博": 295, "占": 296, "卡": 297, "卦": 298, "印": 299, "危": 300, "即": 301, "卵": 302, "卷": 303, "卸": 304, "卻": 305, "厄": 306, "厚": 307, "原": 308, "厭": 309, "厲": 310, "去": 311, "參": 312, "又": 313, "叉": 314, "及": 315, "友": 316, "反": 317, "叔": 318, "取": 319, "受": 320, "叛": 321, "叢": 322, "口": 323, "古": 324, "句": 325, "另": 326, "叨": 327, "只": 328, "叫": 329, "召": 330, "叮": 331, "可": 332, "台": 333, "史": 334, "右": 335, "司": 336, "吃": 337, "各": 338, "合": 339, "吉": 340, "吊": 341, "同": 342, "名": 343, "吐": 344, "向": 345, "君": 346, "否": 347, "吧": 348, "含": 349, "吭": 350, "吸": 351, "吹": 352, "吻": 353, "吼": 354, "呀": 355, "呂": 356, "呆": 357, "呈": 358, "告": 359, "呢": 360, "周": 361, "呱": 362, "味": 363, "呵": 364, "呼": 365, "命": 366, "咆": 367, "和": 368, "咕": 369, "咖": 370, "咬": 371, "咳": 372, "哀": 373, "品": 374, "哄": 375, "哇": 376, "哈": 377, "哉": 378, "哎": 379, "員": 380, "哥": 381, "哦": 382, "哩": 383, "哪": 384, "哭": 385, "哲": 386, "哺": 387, "哼": 388, "唆": 389, "唐": 390, "唬": 391, "售": 392, "唯": 393, "唱": 394, "唷": 395, "唸": 396, "商": 397, "啊": 398, "問": 399, "啖": 400, "啟": 401, "啡": 402, "啤": 403, "啥": 404, "啦": 405, "啼": 406, "善": 407, "喉": 408, "喊": 409, "喔": 410, "喘": 411, "喜": 412, "喝": 413, "喧": 414, "喪": 415, "喬": 416, "單": 417, "喵": 418, "喻": 419, "嗆": 420, "嗎": 421, "嗚": 422, "嗜": 423, "嗨": 424, "嗯": 425, "嗽": 426, "嘆": 427, "嘉": 428, "嘍": 429, "嘗": 430, "嘛": 431, "嘯": 432, "嘰": 433, "嘲": 434, "嘴": 435, "嘻": 436, "噌": 437, "噓": 438, "噗": 439, "器": 440, "噴": 441, "噶": 442, "噸": 443, "噹": 444, "嚀": 445, "嚇": 446, "嚕": 447, "嚨": 448, "嚴": 449, "嚼": 450, "囉": 451, "四": 452, "回": 453, "因": 454, "困": 455, "固": 456, "圈": 457, "國": 458, "圍": 459, "園": 460, "圓": 461, "圖": 462, "團": 463, "土": 464, "在": 465, "地": 466, "圾": 467, "址": 468, "均": 469, "坊": 470, "坐": 471, "坑": 472, "坡": 473, "坦": 474, "坪": 475, "垂": 476, "垃": 477, "型": 478, "埋": 479, "城": 480, "域": 481, "執": 482, "培": 483, "基": 484, "堂": 485, "堅": 486, "堆": 487, "堡": 488, "堪": 489, "報": 490, "場": 491, "堵": 492, "塊": 493, "塑": 494, "塔": 495, "塗": 496, "塞": 497, "填": 498, "塭": 499, "境": 500, "墓": 501, "增": 502, "墨": 503, "墮": 504, "墾": 505, "壁": 506, "壇": 507, "壓": 508, "壘": 509, "壞": 510, "壟": 511, "士": 512, "壯": 513, "壺": 514, "壽": 515, "夏": 516, "夕": 517, "外": 518, "多": 519, "夜": 520, "夠": 521, "夢": 522, "夥": 523, "大": 524, "天": 525, "太": 526, "夫": 527, "央": 528, "失": 529, "夷": 530, "夾": 531, "奇": 532, "奈": 533, "奉": 534, "奏": 535, "契": 536, "奔": 537, "套": 538, "奢": 539, "奧": 540, "奪": 541, "奮": 542, "女": 543, "奶": 544, "奸": 545, "她": 546, "好": 547, "如": 548, "妃": 549, "妄": 550, "妖": 551, "妙": 552, "妥": 553, "妨": 554, "妳": 555, "妹": 556, "妻": 557, "妾": 558, "姆": 559, "姊": 560, "始": 561, "姍": 562, "姐": 563, "姑": 564, "姓": 565, "委": 566, "姚": 567, "姨": 568, "姬": 569, "姻": 570, "威": 571, "娑": 572, "娘": 573, "娛": 574, "娶": 575, "娼": 576, "婆": 577, "婊": 578, "婚": 579, "婦": 580, "婪": 581, "媒": 582, "媳": 583, "媽": 584, "嫁": 585, "嫖": 586, "嫩": 587, "嬤": 588, "嬰": 589, "嬸": 590, "子": 591, "孕": 592, "字": 593, "存": 594, "孝": 595, "季": 596, "孤": 597, "孩": 598, "孫": 599, "孵": 600, "學": 601, "它": 602, "宅": 603, "守": 604, "安": 605, "完": 606, "宗": 607, "官": 608, "定": 609, "宜": 610, "客": 611, "宣": 612, "室": 613, "宮": 614, "宰": 615, "害": 616, "宴": 617, "宵": 618, "家": 619, "容": 620, "宿": 621, "寂": 622, "寄": 623, "密": 624, "富": 625, "寒": 626, "寓": 627, "寞": 628, "察": 629, "實": 630, "寧": 631, "審": 632, "寫": 633, "寬": 634, "寮": 635, "寵": 636, "寶": 637, "寸": 638, "寺": 639, "封": 640, "射": 641, "將": 642, "專": 643, "尊": 644, "尋": 645, "對": 646, "導": 647, "小": 648, "少": 649, "尖": 650, "尚": 651, "尤": 652, "尬": 653, "就": 654, "尷": 655, "尺": 656, "尼": 657, "尾": 658, "尿": 659, "局": 660, "屁": 661, "居": 662, "屆": 663, "屈": 664, "屋": 665, "屌": 666, "屎": 667, "屏": 668, "屑": 669, "展": 670, "屜": 671, "屠": 672, "層": 673, "履": 674, "屬": 675, "屯": 676, "山": 677, "岩": 678, "岸": 679, "峰": 680, "島": 681, "峻": 682, "峽": 683, "崛": 684, "崴": 685, "嶄": 686, "巔": 687, "川": 688, "州": 689, "巡": 690, "巢": 691, "工": 692, "左": 693, "巧": 694, "巨": 695, "差": 696, "己": 697, "已": 698, "巴": 699, "巷": 700, "巾": 701, "市": 702, "布": 703, "帆": 704, "希": 705, "帖": 706, "帝": 707, "帥": 708, "師": 709, "席": 710, "帳": 711, "帶": 712, "常": 713, "帽": 714, "幅": 715, "幌": 716, "幕": 717, "幣": 718, "幫": 719, "干": 720, "平": 721, "年": 722, "幸": 723, "幹": 724, "幻": 725, "幼": 726, "幾": 727, "庄": 728, "床": 729, "序": 730, "底": 731, "店": 732, "府": 733, "度": 734, "座": 735, "庫": 736, "庭": 737, "康": 738, "庸": 739, "廁": 740, "廂": 741, "廊": 742, "廖": 743, "廚": 744, "廟": 745, "廠": 746, "廢": 747, "廣": 748, "廬": 749, "廳": 750, "延": 751, "廷": 752, "建": 753, "弄": 754, "弊": 755, "式": 756, "弔": 757, "引": 758, "弘": 759, "弟": 760, "弱": 761, "張": 762, "強": 763, "彈": 764, "彌": 765, "彎": 766, "彙": 767, "形": 768, "彩": 769, "影": 770, "役": 771, "彼": 772, "往": 773, "待": 774, "很": 775, "徊": 776, "律": 777, "後": 778, "徑": 779, "徒": 780, "得": 781, "徘": 782, "徙": 783, "從": 784, "復": 785, "循": 786, "徬": 787, "微": 788, "徵": 789, "德": 790, "徹": 791, "心": 792, "必": 793, "忍": 794, "志": 795, "忘": 796, "忙": 797, "快": 798, "念": 799, "忽": 800, "怎": 801, "怒": 802, "怕": 803, "怖": 804, "思": 805, "怠": 806, "急": 807, "怦": 808, "性": 809, "怨": 810, "怪": 811, "怵": 812, "恃": 813, "恆": 814, "恍": 815, "恐": 816, "恕": 817, "恢": 818, "恤": 819, "恩": 820, "恭": 821, "息": 822, "恰": 823, "悄": 824, "悅": 825, "悉": 826, "悔": 827, "悟": 828, "悠": 829, "患": 830, "您": 831, "悲": 832, "情": 833, "惇": 834, "惋": 835, "惑": 836, "惕": 837, "惘": 838, "惜": 839, "惠": 840, "惡": 841, "惰": 842, "惱": 843, "想": 844, "惶": 845, "惹": 846, "愁": 847, "愈": 848, "愉": 849, "意": 850, "愕": 851, "愚": 852, "愛": 853, "愜": 854, "感": 855, "愣": 856, "愧": 857, "慈": 858, "態": 859, "慌": 860, "慎": 861, "慕": 862, "慘": 863, "慚": 864, "慢": 865, "慣": 866, "慧": 867, "慮": 868, "慰": 869, "慶": 870, "慾": 871, "憂": 872, "憊": 873, "憑": 874, "憩": 875, "憲": 876, "憶": 877, "憾": 878, "懂": 879, "懇": 880, "應": 881, "懲": 882, "懶": 883, "懷": 884, "懼": 885, "戀": 886, "成": 887, "我": 888, "戒": 889, "或": 890, "戚": 891, "截": 892, "戰": 893, "戲": 894, "戴": 895, "戶": 896, "房": 897, "所": 898, "扇": 899, "扉": 900, "手": 901, "才": 902, "扎": 903, "打": 904, "托": 905, "扛": 906, "扣": 907, "扭": 908, "扮": 909, "扯": 910, "扶": 911, "批": 912, "扼": 913, "找": 914, "承": 915, "技": 916, "抄": 917, "把": 918, "抒": 919, "抓": 920, "投": 921, "抖": 922, "抗": 923, "折": 924, "披": 925, "抬": 926, "抱": 927, "抵": 928, "抹": 929, "抽": 930, "拆": 931, "拉": 932, "拋": 933, "拍": 934, "拒": 935, "拓": 936, "拔": 937, "拖": 938, "拘": 939, "拚": 940, "招": 941, "拜": 942, "括": 943, "拯": 944, "拱": 945, "拳": 946, "拼": 947, "拾": 948, "拿": 949, "持": 950, "指": 951, "按": 952, "挑": 953, "挖": 954, "挫": 955, "振": 956, "捍": 957, "捐": 958, "捕": 959, "捨": 960, "捲": 961, "捷": 962, "掃": 963, "授": 964, "掉": 965, "掌": 966, "掏": 967, "排": 968, "掘": 969, "掙": 970, "掛": 971, "掠": 972, "採": 973, "探": 974, "接": 975, "控": 976, "推": 977, "掩": 978, "措": 979, "掰": 980, "揉": 981, "描": 982, "提": 983, "插": 984, "揚": 985, "換": 986, "握": 987, "揣": 988, "揭": 989, "揮": 990, "援": 991, "揹": 992, "損": 993, "搏": 994, "搖": 995, "搗": 996, "搜": 997, "搞": 998, "搬": 999, "搭": 1000, "搶": 1001, "摔": 1002, "摘": 1003, "摟": 1004, "摧": 1005, "摩": 1006, "摯": 1007, "摸": 1008, "撇": 1009, "撒": 1010, "撞": 1011, "撤": 1012, "撥": 1013, "撫": 1014, "播": 1015, "撲": 1016, "撿": 1017, "擁": 1018, "擅": 1019, "擇": 1020, "擊": 1021, "擋": 1022, "操": 1023, "擎": 1024, "擔": 1025, "據": 1026, "擠": 1027, "擦": 1028, "擬": 1029, "擱": 1030, "擲": 1031, "擴": 1032, "擺": 1033, "擾": 1034, "攜": 1035, "攝": 1036, "攤": 1037, "支": 1038, "收": 1039, "攸": 1040, "改": 1041, "攻": 1042, "放": 1043, "政": 1044, "故": 1045, "效": 1046, "敏": 1047, "救": 1048, "敗": 1049, "敘": 1050, "教": 1051, "敝": 1052, "敢": 1053, "散": 1054, "敦": 1055, "敬": 1056, "敲": 1057, "整": 1058, "敵": 1059, "數": 1060, "斂": 1061, "文": 1062, "斌": 1063, "料": 1064, "斜": 1065, "斤": 1066, "斥": 1067, "斧": 1068, "斯": 1069, "新": 1070, "斷": 1071, "方": 1072, "於": 1073, "施": 1074, "旁": 1075, "旅": 1076, "旋": 1077, "族": 1078, "旗": 1079, "既": 1080, "日": 1081, "旦": 1082, "旨": 1083, "早": 1084, "旬": 1085, "旭": 1086, "旺": 1087, "昂": 1088, "昇": 1089, "昌": 1090, "明": 1091, "昏": 1092, "易": 1093, "昔": 1094, "星": 1095, "映": 1096, "春": 1097, "昧": 1098, "昨": 1099, "是": 1100, "昴": 1101, "時": 1102, "晃": 1103, "晚": 1104, "晨": 1105, "普": 1106, "景": 1107, "晰": 1108, "晴": 1109, "晶": 1110, "智": 1111, "晾": 1112, "暄": 1113, "暈": 1114, "暑": 1115, "暖": 1116, "暗": 1117, "暫": 1118, "暱": 1119, "暴": 1120, "曆": 1121, "曉": 1122, "曙": 1123, "曝": 1124, "曬": 1125, "曲": 1126, "更": 1127, "書": 1128, "曹": 1129, "曾": 1130, "替": 1131, "最": 1132, "會": 1133, "月": 1134, "有": 1135, "朋": 1136, "服": 1137, "朕": 1138, "朗": 1139, "望": 1140, "朝": 1141, "期": 1142, "木": 1143, "未": 1144, "末": 1145, "本": 1146, "札": 1147, "朱": 1148, "朵": 1149, "朽": 1150, "杉": 1151, "李": 1152, "材": 1153, "村": 1154, "杖": 1155, "杜": 1156, "束": 1157, "杭": 1158, "杯": 1159, "東": 1160, "松": 1161, "板": 1162, "枉": 1163, "析": 1164, "林": 1165, "枚": 1166, "果": 1167, "枝": 1168, "枯": 1169, "架": 1170, "柏": 1171, "某": 1172, "染": 1173, "柔": 1174, "柚": 1175, "查": 1176, "柯": 1177, "柳": 1178, "柴": 1179, "柵": 1180, "柺": 1181, "柿": 1182, "栗": 1183, "校": 1184, "株": 1185, "核": 1186, "根": 1187, "格": 1188, "栽": 1189, "桃": 1190, "框": 1191, "案": 1192, "桌": 1193, "桶": 1194, "桿": 1195, "梅": 1196, "梗": 1197, "條": 1198, "梨": 1199, "梯": 1200, "梳": 1201, "棄": 1202, "棉": 1203, "棋": 1204, "棒": 1205, "棚": 1206, "棟": 1207, "森": 1208, "棲": 1209, "棵": 1210, "椅": 1211, "植": 1212, "椒": 1213, "椰": 1214, "楊": 1215, "楚": 1216, "業": 1217, "極": 1218, "概": 1219, "榕": 1220, "榜": 1221, "榮": 1222, "構": 1223, "槍": 1224, "樁": 1225, "樂": 1226, "樑": 1227, "樓": 1228, "標": 1229, "樞": 1230, "模": 1231, "樣": 1232, "樵": 1233, "樸": 1234, "樹": 1235, "樽": 1236, "橋": 1237, "橘": 1238, "橙": 1239, "機": 1240, "橡": 1241, "檔": 1242, "檢": 1243, "檬": 1244, "檯": 1245, "檸": 1246, "檻": 1247, "櫃": 1248, "欄": 1249, "欉": 1250, "權": 1251, "欠": 1252, "次": 1253, "欣": 1254, "欲": 1255, "欸": 1256, "欽": 1257, "款": 1258, "歉": 1259, "歌": 1260, "歐": 1261, "歡": 1262, "止": 1263, "正": 1264, "此": 1265, "步": 1266, "武": 1267, "歧": 1268, "歲": 1269, "歷": 1270, "歸": 1271, "死": 1272, "殊": 1273, "殘": 1274, "段": 1275, "殷": 1276, "殺": 1277, "殼": 1278, "殿": 1279, "毀": 1280, "毋": 1281, "母": 1282, "每": 1283, "毒": 1284, "比": 1285, "毛": 1286, "毫": 1287, "氏": 1288, "民": 1289, "氛": 1290, "氣": 1291, "氧": 1292, "氫": 1293, "氰": 1294, "水": 1295, "永": 1296, "氾": 1297, "汁": 1298, "求": 1299, "汐": 1300, "汗": 1301, "汙": 1302, "汛": 1303, "汝": 1304, "江": 1305, "池": 1306, "污": 1307, "汰": 1308, "決": 1309, "汽": 1310, "汾": 1311, "沈": 1312, "沉": 1313, "沐": 1314, "沒": 1315, "沖": 1316, "沙": 1317, "沛": 1318, "没": 1319, "沮": 1320, "沱": 1321, "河": 1322, "油": 1323, "治": 1324, "況": 1325, "泉": 1326, "法": 1327, "泛": 1328, "泡": 1329, "波": 1330, "泣": 1331, "泥": 1332, "注": 1333, "泰": 1334, "泳": 1335, "洋": 1336, "洗": 1337, "洛": 1338, "洞": 1339, "津": 1340, "洱": 1341, "洲": 1342, "活": 1343, "洽": 1344, "派": 1345, "流": 1346, "浪": 1347, "浮": 1348, "浴": 1349, "海": 1350, "消": 1351, "涉": 1352, "涯": 1353, "液": 1354, "涵": 1355, "涸": 1356, "涼": 1357, "淇": 1358, "淋": 1359, "淑": 1360, "淒": 1361, "淘": 1362, "淚": 1363, "淡": 1364, "淨": 1365, "淪": 1366, "深": 1367, "混": 1368, "淺": 1369, "添": 1370, "清": 1371, "減": 1372, "渡": 1373, "渥": 1374, "測": 1375, "港": 1376, "渲": 1377, "渴": 1378, "游": 1379, "渾": 1380, "湊": 1381, "湍": 1382, "湖": 1383, "湧": 1384, "湯": 1385, "源": 1386, "準": 1387, "溝": 1388, "溪": 1389, "溫": 1390, "溺": 1391, "滂": 1392, "滅": 1393, "滋": 1394, "滌": 1395, "滑": 1396, "滯": 1397, "滴": 1398, "滾": 1399, "滿": 1400, "漁": 1401, "漂": 1402, "漆": 1403, "漏": 1404, "演": 1405, "漠": 1406, "漢": 1407, "漫": 1408, "漲": 1409, "漸": 1410, "潑": 1411, "潔": 1412, "潛": 1413, "潤": 1414, "潮": 1415, "澄": 1416, "澎": 1417, "澤": 1418, "澳": 1419, "激": 1420, "濃": 1421, "濕": 1422, "濟": 1423, "濫": 1424, "濱": 1425, "濾": 1426, "瀑": 1427, "瀕": 1428, "灌": 1429, "灑": 1430, "灘": 1431, "灣": 1432, "火": 1433, "灰": 1434, "災": 1435, "炎": 1436, "炒": 1437, "炫": 1438, "炸": 1439, "為": 1440, "烈": 1441, "烊": 1442, "烏": 1443, "烤": 1444, "烹": 1445, "無": 1446, "焦": 1447, "焰": 1448, "然": 1449, "煎": 1450, "煙": 1451, "照": 1452, "煩": 1453, "煮": 1454, "熊": 1455, "熟": 1456, "熬": 1457, "熱": 1458, "燃": 1459, "燈": 1460, "燒": 1461, "燙": 1462, "營": 1463, "燥": 1464, "燦": 1465, "爆": 1466, "爍": 1467, "爐": 1468, "爛": 1469, "爪": 1470, "爬": 1471, "爭": 1472, "爲": 1473, "父": 1474, "爸": 1475, "爹": 1476, "爺": 1477, "爽": 1478, "爾": 1479, "牆": 1480, "片": 1481, "版": 1482, "牌": 1483, "牙": 1484, "牛": 1485, "牠": 1486, "牡": 1487, "物": 1488, "牴": 1489, "特": 1490, "牽": 1491, "犬": 1492, "犯": 1493, "狀": 1494, "狗": 1495, "狠": 1496, "狼": 1497, "猛": 1498, "猜": 1499, "猩": 1500, "猴": 1501, "猶": 1502, "猿": 1503, "獄": 1504, "獅": 1505, "獎": 1506, "獨": 1507, "獲": 1508, "獵": 1509, "獸": 1510, "獻": 1511, "率": 1512, "玉": 1513, "王": 1514, "玩": 1515, "玻": 1516, "珍": 1517, "珠": 1518, "班": 1519, "現": 1520, "球": 1521, "理": 1522, "琪": 1523, "琴": 1524, "瑋": 1525, "瑜": 1526, "瑟": 1527, "瑩": 1528, "瑪": 1529, "瑰": 1530, "璃": 1531, "環": 1532, "瓜": 1533, "瓦": 1534, "瓶": 1535, "甄": 1536, "甘": 1537, "甚": 1538, "甜": 1539, "生": 1540, "產": 1541, "用": 1542, "甩": 1543, "甫": 1544, "田": 1545, "由": 1546, "甲": 1547, "申": 1548, "男": 1549, "町": 1550, "界": 1551, "畔": 1552, "留": 1553, "畢": 1554, "略": 1555, "番": 1556, "畫": 1557, "異": 1558, "當": 1559, "疊": 1560, "疏": 1561, "疑": 1562, "疙": 1563, "疫": 1564, "疲": 1565, "疼": 1566, "疾": 1567, "病": 1568, "症": 1569, "痕": 1570, "痛": 1571, "痰": 1572, "痴": 1573, "瘋": 1574, "瘟": 1575, "瘦": 1576, "瘩": 1577, "療": 1578, "癌": 1579, "癡": 1580, "癮": 1581, "癱": 1582, "登": 1583, "發": 1584, "白": 1585, "百": 1586, "的": 1587, "皆": 1588, "皇": 1589, "皮": 1590, "皺": 1591, "益": 1592, "盎": 1593, "盒": 1594, "盔": 1595, "盛": 1596, "盜": 1597, "盞": 1598, "盟": 1599, "盡": 1600, "監": 1601, "盤": 1602, "盪": 1603, "目": 1604, "盲": 1605, "直": 1606, "相": 1607, "盼": 1608, "盾": 1609, "省": 1610, "眉": 1611, "看": 1612, "真": 1613, "眠": 1614, "眷": 1615, "眼": 1616, "眾": 1617, "睛": 1618, "睡": 1619, "督": 1620, "睦": 1621, "瞧": 1622, "瞪": 1623, "瞬": 1624, "瞭": 1625, "瞻": 1626, "矛": 1627, "知": 1628, "矩": 1629, "短": 1630, "矮": 1631, "矲": 1632, "石": 1633, "砂": 1634, "研": 1635, "砲": 1636, "破": 1637, "硃": 1638, "硬": 1639, "碌": 1640, "碎": 1641, "碑": 1642, "碗": 1643, "碟": 1644, "碧": 1645, "碩": 1646, "碰": 1647, "碳": 1648, "確": 1649, "碼": 1650, "碾": 1651, "磁": 1652, "磐": 1653, "磚": 1654, "磨": 1655, "礎": 1656, "礙": 1657, "示": 1658, "社": 1659, "祈": 1660, "祉": 1661, "祕": 1662, "祖": 1663, "祝": 1664, "神": 1665, "祟": 1666, "祥": 1667, "票": 1668, "祭": 1669, "祿": 1670, "禁": 1671, "禍": 1672, "福": 1673, "禦": 1674, "禧": 1675, "禮": 1676, "禱": 1677, "禿": 1678, "秀": 1679, "私": 1680, "秉": 1681, "秋": 1682, "科": 1683, "秒": 1684, "秘": 1685, "租": 1686, "秧": 1687, "秩": 1688, "移": 1689, "稅": 1690, "程": 1691, "稍": 1692, "稚": 1693, "種": 1694, "稱": 1695, "稻": 1696, "稿": 1697, "穀": 1698, "積": 1699, "穗": 1700, "穩": 1701, "穴": 1702, "究": 1703, "空": 1704, "穿": 1705, "突": 1706, "窗": 1707, "窮": 1708, "竅": 1709, "立": 1710, "站": 1711, "竟": 1712, "章": 1713, "童": 1714, "端": 1715, "競": 1716, "竹": 1717, "竿": 1718, "笑": 1719, "符": 1720, "第": 1721, "筆": 1722, "等": 1723, "筋": 1724, "筐": 1725, "筒": 1726, "答": 1727, "策": 1728, "箕": 1729, "算": 1730, "管": 1731, "箱": 1732, "節": 1733, "範": 1734, "篇": 1735, "築": 1736, "篩": 1737, "篷": 1738, "簡": 1739, "簷": 1740, "簽": 1741, "簿": 1742, "籃": 1743, "籌": 1744, "籍": 1745, "籠": 1746, "籤": 1747, "籮": 1748, "籲": 1749, "米": 1750, "籽": 1751, "粉": 1752, "粒": 1753, "粗": 1754, "粥": 1755, "粹": 1756, "精": 1757, "糊": 1758, "糕": 1759, "糖": 1760, "糞": 1761, "糟": 1762, "糧": 1763, "糬": 1764, "糰": 1765, "系": 1766, "糾": 1767, "紀": 1768, "約": 1769, "紅": 1770, "紋": 1771, "納": 1772, "紐": 1773, "紓": 1774, "純": 1775, "紙": 1776, "級": 1777, "紛": 1778, "素": 1779, "紡": 1780, "索": 1781, "紫": 1782, "累": 1783, "細": 1784, "紹": 1785, "終": 1786, "組": 1787, "絆": 1788, "結": 1789, "絕": 1790, "絡": 1791, "給": 1792, "絨": 1793, "統": 1794, "絲": 1795, "綁": 1796, "經": 1797, "綜": 1798, "綠": 1799, "維": 1800, "綱": 1801, "網": 1802, "綿": 1803, "緊": 1804, "緒": 1805, "線": 1806, "締": 1807, "緣": 1808, "編": 1809, "緩": 1810, "練": 1811, "緻": 1812, "縈": 1813, "縝": 1814, "縣": 1815, "縫": 1816, "縮": 1817, "縱": 1818, "總": 1819, "績": 1820, "繁": 1821, "織": 1822, "繞": 1823, "繩": 1824, "繪": 1825, "繫": 1826, "繳": 1827, "繹": 1828, "繼": 1829, "續": 1830, "纏": 1831, "纜": 1832, "缸": 1833, "缺": 1834, "罄": 1835, "罐": 1836, "罩": 1837, "罪": 1838, "置": 1839, "罰": 1840, "署": 1841, "罵": 1842, "罷": 1843, "罹": 1844, "羅": 1845, "羈": 1846, "羊": 1847, "美": 1848, "羞": 1849, "群": 1850, "羨": 1851, "義": 1852, "羽": 1853, "翁": 1854, "翅": 1855, "習": 1856, "翹": 1857, "翻": 1858, "翼": 1859, "耀": 1860, "老": 1861, "考": 1862, "者": 1863, "而": 1864, "耍": 1865, "耐": 1866, "耕": 1867, "耗": 1868, "耘": 1869, "耳": 1870, "耶": 1871, "耽": 1872, "聆": 1873, "聊": 1874, "聖": 1875, "聘": 1876, "聚": 1877, "聞": 1878, "聯": 1879, "聰": 1880, "聲": 1881, "聳": 1882, "職": 1883, "聽": 1884, "肅": 1885, "肉": 1886, "肋": 1887, "肘": 1888, "肚": 1889, "肝": 1890, "股": 1891, "肢": 1892, "肥": 1893, "肩": 1894, "肯": 1895, "育": 1896, "肺": 1897, "胃": 1898, "背": 1899, "胎": 1900, "胖": 1901, "胞": 1902, "胡": 1903, "胯": 1904, "胸": 1905, "能": 1906, "脆": 1907, "脈": 1908, "脖": 1909, "脫": 1910, "脹": 1911, "脾": 1912, "腐": 1913, "腔": 1914, "腦": 1915, "腫": 1916, "腮": 1917, "腰": 1918, "腳": 1919, "腸": 1920, "腹": 1921, "腿": 1922, "膀": 1923, "膏": 1924, "膠": 1925, "膨": 1926, "膩": 1927, "膽": 1928, "臂": 1929, "臃": 1930, "臉": 1931, "臟": 1932, "臣": 1933, "臨": 1934, "自": 1935, "臭": 1936, "至": 1937, "致": 1938, "臺": 1939, "舅": 1940, "與": 1941, "興": 1942, "舉": 1943, "舊": 1944, "舌": 1945, "舍": 1946, "舒": 1947, "舔": 1948, "舞": 1949, "舟": 1950, "航": 1951, "般": 1952, "船": 1953, "艦": 1954, "良": 1955, "艱": 1956, "色": 1957, "艷": 1958, "芋": 1959, "芒": 1960, "芙": 1961, "芬": 1962, "芭": 1963, "花": 1964, "芳": 1965, "芹": 1966, "芽": 1967, "苓": 1968, "苗": 1969, "苟": 1970, "若": 1971, "苦": 1972, "英": 1973, "茂": 1974, "范": 1975, "茄": 1976, "茫": 1977, "茱": 1978, "茲": 1979, "茶": 1980, "草": 1981, "荒": 1982, "荷": 1983, "莊": 1984, "莎": 1985, "莓": 1986, "莫": 1987, "菁": 1988, "菇": 1989, "菌": 1990, "菜": 1991, "華": 1992, "菲": 1993, "菸": 1994, "萄": 1995, "萊": 1996, "萬": 1997, "萱": 1998, "落": 1999, "葉": 2000, "著": 2001, "葛": 2002, "葡": 2003, "董": 2004, "葬": 2005, "蒂": 2006, "蒐": 2007, "蒙": 2008, "蒸": 2009, "蒼": 2010, "蓋": 2011, "蓮": 2012, "蔔": 2013, "蔚": 2014, "蔡": 2015, "蔣": 2016, "蔥": 2017, "蔭": 2018, "蕾": 2019, "薄": 2020, "薏": 2021, "薑": 2022, "薦": 2023, "薩": 2024, "薪": 2025, "薯": 2026, "藉": 2027, "藍": 2028, "藏": 2029, "藝": 2030, "藤": 2031, "藥": 2032, "藩": 2033, "蘆": 2034, "蘊": 2035, "蘋": 2036, "蘑": 2037, "蘭": 2038, "蘿": 2039, "虎": 2040, "虐": 2041, "處": 2042, "虛": 2043, "虞": 2044, "號": 2045, "虧": 2046, "蚊": 2047, "蚤": 2048, "蛇": 2049, "蛋": 2050, "蛙": 2051, "蛛": 2052, "蛻": 2053, "蜂": 2054, "蜘": 2055, "蜜": 2056, "蝦": 2057, "螃": 2058, "融": 2059, "螞": 2060, "螢": 2061, "螺": 2062, "蟬": 2063, "蟲": 2064, "蟹": 2065, "蟻": 2066, "蠅": 2067, "蠢": 2068, "蠱": 2069, "蠻": 2070, "血": 2071, "行": 2072, "衍": 2073, "術": 2074, "街": 2075, "衛": 2076, "衝": 2077, "衡": 2078, "衣": 2079, "表": 2080, "衫": 2081, "衰": 2082, "袋": 2083, "袖": 2084, "被": 2085, "袱": 2086, "裁": 2087, "裂": 2088, "裙": 2089, "補": 2090, "裝": 2091, "裡": 2092, "裸": 2093, "製": 2094, "複": 2095, "褐": 2096, "褲": 2097, "襄": 2098, "襪": 2099, "襲": 2100, "西": 2101, "要": 2102, "覆": 2103, "見": 2104, "規": 2105, "覓": 2106, "視": 2107, "親": 2108, "覺": 2109, "覽": 2110, "觀": 2111, "角": 2112, "解": 2113, "觸": 2114, "言": 2115, "訂": 2116, "計": 2117, "訊": 2118, "討": 2119, "訐": 2120, "訓": 2121, "訕": 2122, "託": 2123, "記": 2124, "訝": 2125, "訟": 2126, "訣": 2127, "訪": 2128, "設": 2129, "許": 2130, "訴": 2131, "診": 2132, "註": 2133, "詐": 2134, "評": 2135, "詞": 2136, "詢": 2137, "試": 2138, "詩": 2139, "詬": 2140, "詭": 2141, "話": 2142, "該": 2143, "詳": 2144, "詹": 2145, "誇": 2146, "誌": 2147, "認": 2148, "誓": 2149, "誕": 2150, "誘": 2151, "語": 2152, "誠": 2153, "誡": 2154, "誣": 2155, "誤": 2156, "說": 2157, "誰": 2158, "課": 2159, "誼": 2160, "調": 2161, "談": 2162, "請": 2163, "諒": 2164, "論": 2165, "諮": 2166, "諸": 2167, "諾": 2168, "謀": 2169, "謂": 2170, "謄": 2171, "謊": 2172, "講": 2173, "謝": 2174, "謠": 2175, "謹": 2176, "證": 2177, "識": 2178, "譚": 2179, "譜": 2180, "警": 2181, "譯": 2182, "議": 2183, "護": 2184, "譽": 2185, "讀": 2186, "變": 2187, "讓": 2188, "讚": 2189, "谷": 2190, "豆": 2191, "豈": 2192, "豐": 2193, "豚": 2194, "象": 2195, "豪": 2196, "豫": 2197, "豬": 2198, "貌": 2199, "貓": 2200, "貝": 2201, "貞": 2202, "負": 2203, "財": 2204, "貢": 2205, "貧": 2206, "貨": 2207, "販": 2208, "貪": 2209, "貫": 2210, "責": 2211, "貲": 2212, "貴": 2213, "買": 2214, "貸": 2215, "費": 2216, "貼": 2217, "貿": 2218, "資": 2219, "賊": 2220, "賓": 2221, "賞": 2222, "賠": 2223, "賢": 2224, "賣": 2225, "賤": 2226, "賦": 2227, "質": 2228, "賭": 2229, "賴": 2230, "賺": 2231, "購": 2232, "賽": 2233, "贈": 2234, "贊": 2235, "贏": 2236, "赤": 2237, "赫": 2238, "走": 2239, "起": 2240, "趁": 2241, "超": 2242, "越": 2243, "趕": 2244, "趟": 2245, "趣": 2246, "趨": 2247, "足": 2248, "趴": 2249, "跆": 2250, "跋": 2251, "跌": 2252, "跑": 2253, "跚": 2254, "距": 2255, "跟": 2256, "跡": 2257, "跨": 2258, "路": 2259, "跳": 2260, "踉": 2261, "踏": 2262, "踐": 2263, "踩": 2264, "踴": 2265, "踹": 2266, "蹄": 2267, "蹌": 2268, "蹟": 2269, "蹣": 2270, "蹤": 2271, "蹦": 2272, "蹲": 2273, "躁": 2274, "躍": 2275, "身": 2276, "躲": 2277, "躺": 2278, "軀": 2279, "車": 2280, "軌": 2281, "軍": 2282, "軟": 2283, "較": 2284, "載": 2285, "輔": 2286, "輕": 2287, "輩": 2288, "輪": 2289, "輯": 2290, "輸": 2291, "輾": 2292, "輿": 2293, "轄": 2294, "轉": 2295, "轎": 2296, "辛": 2297, "辜": 2298, "辣": 2299, "辦": 2300, "辨": 2301, "辭": 2302, "辯": 2303, "辱": 2304, "農": 2305, "迅": 2306, "迎": 2307, "近": 2308, "返": 2309, "迪": 2310, "迫": 2311, "述": 2312, "迴": 2313, "迷": 2314, "追": 2315, "退": 2316, "送": 2317, "逃": 2318, "逆": 2319, "透": 2320, "逐": 2321, "途": 2322, "逕": 2323, "逗": 2324, "這": 2325, "通": 2326, "逛": 2327, "逝": 2328, "逞": 2329, "速": 2330, "造": 2331, "逢": 2332, "連": 2333, "週": 2334, "進": 2335, "逼": 2336, "逾": 2337, "遁": 2338, "遇": 2339, "遊": 2340, "運": 2341, "遍": 2342, "過": 2343, "道": 2344, "達": 2345, "違": 2346, "遙": 2347, "遜": 2348, "遞": 2349, "遠": 2350, "適": 2351, "遭": 2352, "遲": 2353, "遴": 2354, "遵": 2355, "遷": 2356, "選": 2357, "遺": 2358, "遼": 2359, "遽": 2360, "避": 2361, "邀": 2362, "邁": 2363, "還": 2364, "邊": 2365, "邏": 2366, "那": 2367, "邦": 2368, "邪": 2369, "邵": 2370, "郁": 2371, "郊": 2372, "郎": 2373, "郝": 2374, "部": 2375, "郭": 2376, "都": 2377, "鄉": 2378, "鄧": 2379, "鄭": 2380, "鄰": 2381, "配": 2382, "酒": 2383, "酗": 2384, "酪": 2385, "酬": 2386, "酵": 2387, "酷": 2388, "酸": 2389, "醉": 2390, "醒": 2391, "醜": 2392, "醫": 2393, "醬": 2394, "采": 2395, "釋": 2396, "里": 2397, "重": 2398, "野": 2399, "量": 2400, "釐": 2401, "金": 2402, "針": 2403, "釣": 2404, "鈴": 2405, "鉅": 2406, "鉤": 2407, "銀": 2408, "銘": 2409, "銜": 2410, "銷": 2411, "鋒": 2412, "鋪": 2413, "鋸": 2414, "鋼": 2415, "錄": 2416, "錢": 2417, "錦": 2418, "錨": 2419, "錯": 2420, "錶": 2421, "鍊": 2422, "鍋": 2423, "鍛": 2424, "鍵": 2425, "鍾": 2426, "鎂": 2427, "鎖": 2428, "鎮": 2429, "鏈": 2430, "鏡": 2431, "鐘": 2432, "鐵": 2433, "鑑": 2434, "鑰": 2435, "鑼": 2436, "長": 2437, "門": 2438, "閃": 2439, "閉": 2440, "開": 2441, "閒": 2442, "間": 2443, "閱": 2444, "闆": 2445, "闊": 2446, "關": 2447, "闢": 2448, "阱": 2449, "防": 2450, "阻": 2451, "阿": 2452, "陀": 2453, "附": 2454, "陌": 2455, "降": 2456, "限": 2457, "院": 2458, "陣": 2459, "除": 2460, "陪": 2461, "陰": 2462, "陳": 2463, "陷": 2464, "陸": 2465, "陽": 2466, "隆": 2467, "隊": 2468, "階": 2469, "隔": 2470, "際": 2471, "障": 2472, "隧": 2473, "隨": 2474, "險": 2475, "隱": 2476, "隻": 2477, "雀": 2478, "雄": 2479, "雅": 2480, "集": 2481, "雇": 2482, "雌": 2483, "雕": 2484, "雖": 2485, "雙": 2486, "雛": 2487, "雜": 2488, "雞": 2489, "離": 2490, "難": 2491, "雨": 2492, "雪": 2493, "雲": 2494, "零": 2495, "雷": 2496, "電": 2497, "需": 2498, "霄": 2499, "震": 2500, "霉": 2501, "霍": 2502, "霧": 2503, "露": 2504, "霸": 2505, "霹": 2506, "靂": 2507, "靈": 2508, "青": 2509, "靜": 2510, "非": 2511, "靠": 2512, "靡": 2513, "面": 2514, "革": 2515, "靭": 2516, "鞋": 2517, "鞭": 2518, "韋": 2519, "韓": 2520, "音": 2521, "韻": 2522, "響": 2523, "頁": 2524, "頂": 2525, "頃": 2526, "項": 2527, "順": 2528, "須": 2529, "預": 2530, "頓": 2531, "頗": 2532, "領": 2533, "頭": 2534, "頰": 2535, "頸": 2536, "頻": 2537, "顆": 2538, "題": 2539, "額": 2540, "顏": 2541, "願": 2542, "類": 2543, "顧": 2544, "顯": 2545, "顰": 2546, "風": 2547, "颱": 2548, "飄": 2549, "飆": 2550, "飛": 2551, "食": 2552, "飩": 2553, "飪": 2554, "飯": 2555, "飲": 2556, "飽": 2557, "飾": 2558, "餃": 2559, "餅": 2560, "養": 2561, "餐": 2562, "餓": 2563, "餘": 2564, "餚": 2565, "餛": 2566, "餡": 2567, "館": 2568, "餵": 2569, "饋": 2570, "饒": 2571, "饗": 2572, "首": 2573, "香": 2574, "馥": 2575, "馨": 2576, "馬": 2577, "駁": 2578, "駐": 2579, "駕": 2580, "駛": 2581, "駭": 2582, "騎": 2583, "騙": 2584, "騰": 2585, "騷": 2586, "驅": 2587, "驕": 2588, "驗": 2589, "驚": 2590, "驟": 2591, "骨": 2592, "髒": 2593, "體": 2594, "高": 2595, "髮": 2596, "鬆": 2597, "鬍": 2598, "鬚": 2599, "鬥": 2600, "鬧": 2601, "鬼": 2602, "魂": 2603, "魄": 2604, "魔": 2605, "魚": 2606, "魯": 2607, "魷": 2608, "鮪": 2609, "鮭": 2610, "鮮": 2611, "鯊": 2612, "鯛": 2613, "鯨": 2614, "鰈": 2615, "鰜": 2616, "鰭": 2617, "鰻": 2618, "鳥": 2619, "鳩": 2620, "鳳": 2621, "鳴": 2622, "鴉": 2623, "鴨": 2624, "鴻": 2625, "鵝": 2626, "鵲": 2627, "鶯": 2628, "鶴": 2629, "鷹": 2630, "鹹": 2631, "鹽": 2632, "鹿": 2633, "麗": 2634, "麥": 2635, "麵": 2636, "麻": 2637, "麼": 2638, "麽": 2639, "黃": 2640, "黎": 2641, "黑": 2642, "默": 2643, "點": 2644, "黨": 2645, "鼎": 2646, "鼓": 2647, "鼻": 2648, "齁": 2649, "齊": 2650, "齡": 2651, "龍": 2652, "龐": 2653, "龜": 2654, "!": 2655, ",": 2656, ":": 2657, ";": 2658, "?": 2659, "a": 2660, "b": 2661, "f": 2662, "g": 2663, "i": 2664, "n": 2665, "p": 2666, "t": 2667, "~": 2668, "|": 0, "[UNK]": 2669, "[PAD]": 2670}