prows12 commited on
Commit
8c0ff8a
1 Parent(s): c00d54e

add tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<s>": 1436, "</s>": 1437}
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
+ {"…": 1, "、": 2, "。": 3, "々": 4, "〇": 5, "「": 6, "」": 7, "あ": 8, "い": 9, "う": 10, "え": 11, "お": 12, "か": 13, "が": 14, "き": 15, "ぎ": 16, "く": 17, "ぐ": 18, "け": 19, "げ": 20, "こ": 21, "ご": 22, "さ": 23, "ざ": 24, "し": 25, "じ": 26, "す": 27, "ず": 28, "せ": 29, "ぜ": 30, "そ": 31, "ぞ": 32, "た": 33, "だ": 34, "ち": 35, "っ": 36, "つ": 37, "づ": 38, "て": 39, "で": 40, "と": 41, "ど": 42, "な": 43, "に": 44, "ぬ": 45, "ね": 46, "の": 47, "は": 48, "ば": 49, "ぱ": 50, "ひ": 51, "び": 52, "ぴ": 53, "ふ": 54, "ぶ": 55, "ぷ": 56, "へ": 57, "べ": 58, "ぺ": 59, "ほ": 60, "ぼ": 61, "ま": 62, "み": 63, "む": 64, "め": 65, "も": 66, "ゃ": 67, "や": 68, "ゅ": 69, "ゆ": 70, "ょ": 71, "よ": 72, "ら": 73, "り": 74, "る": 75, "れ": 76, "ろ": 77, "わ": 78, "を": 79, "ん": 80, "ァ": 81, "ア": 82, "ィ": 83, "イ": 84, "ウ": 85, "ェ": 86, "エ": 87, "ォ": 88, "オ": 89, "カ": 90, "ガ": 91, "キ": 92, "ギ": 93, "ク": 94, "グ": 95, "ケ": 96, "ゲ": 97, "コ": 98, "ゴ": 99, "サ": 100, "ザ": 101, "シ": 102, "ジ": 103, "ス": 104, "ズ": 105, "セ": 106, "ゼ": 107, "ソ": 108, "タ": 109, "ダ": 110, "チ": 111, "ッ": 112, "ツ": 113, "テ": 114, "デ": 115, "ト": 116, "ド": 117, "ナ": 118, "ニ": 119, "ヌ": 120, "ネ": 121, "ノ": 122, "ハ": 123, "バ": 124, "パ": 125, "ヒ": 126, "ビ": 127, "ピ": 128, "フ": 129, "ブ": 130, "プ": 131, "ヘ": 132, "ベ": 133, "ペ": 134, "ホ": 135, "ボ": 136, "ポ": 137, "マ": 138, "ミ": 139, "ム": 140, "メ": 141, "モ": 142, "ャ": 143, "ヤ": 144, "ュ": 145, "ユ": 146, "ョ": 147, "ヨ": 148, "ラ": 149, "リ": 150, "ル": 151, "レ": 152, "ロ": 153, "ワ": 154, "ン": 155, "ヴ": 156, "ヶ": 157, "ー": 158, "一": 159, "丁": 160, "七": 161, "万": 162, "丈": 163, "三": 164, "上": 165, "下": 166, "不": 167, "与": 168, "世": 169, "両": 170, "並": 171, "中": 172, "丸": 173, "主": 174, "久": 175, "乗": 176, "九": 177, "乱": 178, "乳": 179, "乾": 180, "了": 181, "予": 182, "争": 183, "事": 184, "二": 185, "互": 186, "五": 187, "井": 188, "交": 189, "京": 190, "人": 191, "今": 192, "介": 193, "仏": 194, "仕": 195, "他": 196, "付": 197, "代": 198, "以": 199, "件": 200, "任": 201, "企": 202, "伏": 203, "休": 204, "会": 205, "伝": 206, "伴": 207, "伸": 208, "似": 209, "位": 210, "低": 211, "住": 212, "体": 213, "何": 214, "余": 215, "作": 216, "併": 217, "使": 218, "供": 219, "依": 220, "価": 221, "侵": 222, "便": 223, "係": 224, "保": 225, "信": 226, "修": 227, "俵": 228, "俺": 229, "倉": 230, "個": 231, "倍": 232, "倒": 233, "候": 234, "借": 235, "倫": 236, "偉": 237, "健": 238, "側": 239, "偶": 240, "偽": 241, "傘": 242, "備": 243, "催": 244, "傷": 245, "働": 246, "像": 247, "僕": 248, "償": 249, "優": 250, "元": 251, "兄": 252, "充": 253, "先": 254, "光": 255, "免": 256, "児": 257, "入": 258, "全": 259, "八": 260, "公": 261, "六": 262, "共": 263, "具": 264, "兼": 265, "内": 266, "円": 267, "冊": 268, "再": 269, "冒": 270, "写": 271, "冠": 272, "冬": 273, "冷": 274, "凍": 275, "几": 276, "凡": 277, "処": 278, "出": 279, "分": 280, "切": 281, "刊": 282, "刑": 283, "列": 284, "初": 285, "別": 286, "利": 287, "制": 288, "券": 289, "刺": 290, "則": 291, "前": 292, "剤": 293, "剥": 294, "割": 295, "劇": 296, "力": 297, "功": 298, "加": 299, "劣": 300, "助": 301, "努": 302, "労": 303, "効": 304, "勇": 305, "勉": 306, "動": 307, "務": 308, "勝": 309, "勢": 310, "勤": 311, "包": 312, "化": 313, "北": 314, "匠": 315, "匹": 316, "区": 317, "医": 318, "十": 319, "千": 320, "午": 321, "半": 322, "卒": 323, "協": 324, "南": 325, "単": 326, "占": 327, "印": 328, "危": 329, "却": 330, "卵": 331, "厚": 332, "原": 333, "厳": 334, "去": 335, "参": 336, "及": 337, "友": 338, "反": 339, "収": 340, "叔": 341, "取": 342, "受": 343, "口": 344, "古": 345, "叩": 346, "可": 347, "台": 348, "史": 349, "右": 350, "号": 351, "司": 352, "各": 353, "合": 354, "吉": 355, "同": 356, "名": 357, "吐": 358, "向": 359, "君": 360, "否": 361, "含": 362, "吸": 363, "吹": 364, "呆": 365, "告": 366, "周": 367, "味": 368, "呼": 369, "命": 370, "和": 371, "咲": 372, "品": 373, "員": 374, "唯": 375, "商": 376, "問": 377, "善": 378, "喜": 379, "喫": 380, "喰": 381, "営": 382, "噂": 383, "器": 384, "四": 385, "回": 386, "因": 387, "団": 388, "困": 389, "囲": 390, "図": 391, "固": 392, "国": 393, "園": 394, "土": 395, "圧": 396, "在": 397, "地": 398, "坂": 399, "均": 400, "坊": 401, "型": 402, "垢": 403, "埋": 404, "城": 405, "域": 406, "堂": 407, "報": 408, "場": 409, "塀": 410, "塁": 411, "塩": 412, "塵": 413, "境": 414, "墓": 415, "増": 416, "壁": 417, "壊": 418, "士": 419, "壮": 420, "声": 421, "売": 422, "変": 423, "夏": 424, "夕": 425, "外": 426, "多": 427, "夜": 428, "夢": 429, "大": 430, "天": 431, "太": 432, "夫": 433, "央": 434, "失": 435, "奇": 436, "奈": 437, "奏": 438, "奥": 439, "女": 440, "好": 441, "妃": 442, "妙": 443, "妬": 444, "妹": 445, "妻": 446, "姉": 447, "始": 448, "姿": 449, "威": 450, "娘": 451, "婚": 452, "婦": 453, "嫌": 454, "嬉": 455, "子": 456, "字": 457, "存": 458, "季": 459, "学": 460, "孫": 461, "宅": 462, "宇": 463, "守": 464, "安": 465, "完": 466, "官": 467, "宙": 468, "定": 469, "宝": 470, "実": 471, "客": 472, "室": 473, "宮": 474, "害": 475, "宴": 476, "家": 477, "容": 478, "宿": 479, "寄": 480, "密": 481, "富": 482, "寒": 483, "寓": 484, "寝": 485, "寵": 486, "寸": 487, "寺": 488, "対": 489, "寿": 490, "封": 491, "専": 492, "射": 493, "将": 494, "尋": 495, "導": 496, "小": 497, "少": 498, "尺": 499, "局": 500, "屈": 501, "届": 502, "屋": 503, "属": 504, "層": 505, "山": 506, "岡": 507, "岩": 508, "岬": 509, "岸": 510, "島": 511, "崩": 512, "嶋": 513, "川": 514, "州": 515, "巡": 516, "工": 517, "左": 518, "巧": 519, "差": 520, "己": 521, "巻": 522, "市": 523, "布": 524, "希": 525, "帝": 526, "師": 527, "席": 528, "帯": 529, "帰": 530, "帳": 531, "常": 532, "帽": 533, "幅": 534, "幌": 535, "干": 536, "平": 537, "年": 538, "幸": 539, "幼": 540, "庁": 541, "広": 542, "床": 543, "底": 544, "店": 545, "府": 546, "度": 547, "座": 548, "庫": 549, "庭": 550, "康": 551, "廊": 552, "延": 553, "建": 554, "弁": 555, "弊": 556, "式": 557, "引": 558, "弟": 559, "弱": 560, "張": 561, "強": 562, "弾": 563, "当": 564, "形": 565, "彩": 566, "影": 567, "役": 568, "彼": 569, "往": 570, "待": 571, "後": 572, "徐": 573, "徒": 574, "従": 575, "得": 576, "御": 577, "復": 578, "微": 579, "徴": 580, "徹": 581, "心": 582, "必": 583, "忍": 584, "志": 585, "忘": 586, "忙": 587, "応": 588, "忠": 589, "念": 590, "怒": 591, "怖": 592, "思": 593, "怠": 594, "急": 595, "性": 596, "怪": 597, "恋": 598, "恐": 599, "息": 600, "恵": 601, "悔": 602, "患": 603, "悩": 604, "悪": 605, "悲": 606, "情": 607, "惑": 608, "想": 609, "意": 610, "愛": 611, "感": 612, "態": 613, "慌": 614, "慕": 615, "慢": 616, "慮": 617, "慰": 618, "憐": 619, "憩": 620, "憶": 621, "懐": 622, "懸": 623, "懺": 624, "成": 625, "我": 626, "戦": 627, "戸": 628, "戻": 629, "房": 630, "所": 631, "扇": 632, "扉": 633, "手": 634, "打": 635, "払": 636, "扱": 637, "扶": 638, "承": 639, "技": 640, "抑": 641, "抒": 642, "投": 643, "折": 644, "抜": 645, "押": 646, "拍": 647, "招": 648, "拝": 649, "拠": 650, "拡": 651, "拷": 652, "持": 653, "指": 654, "挙": 655, "振": 656, "捕": 657, "捨": 658, "掃": 659, "授": 660, "掌": 661, "排": 662, "掘": 663, "掛": 664, "採": 665, "探": 666, "接": 667, "描": 668, "揚": 669, "握": 670, "揮": 671, "援": 672, "揺": 673, "搬": 674, "携": 675, "撃": 676, "撮": 677, "擦": 678, "擬": 679, "支": 680, "改": 681, "攻": 682, "放": 683, "政": 684, "故": 685, "救": 686, "敗": 687, "教": 688, "散": 689, "数": 690, "整": 691, "敷": 692, "文": 693, "料": 694, "新": 695, "方": 696, "施": 697, "旅": 698, "旋": 699, "族": 700, "既": 701, "日": 702, "旧": 703, "早": 704, "昇": 705, "明": 706, "易": 707, "昔": 708, "星": 709, "映": 710, "春": 711, "昭": 712, "昼": 713, "時": 714, "晩": 715, "普": 716, "景": 717, "晴": 718, "暇": 719, "暑": 720, "暖": 721, "暗": 722, "暮": 723, "暴": 724, "曇": 725, "曜": 726, "曲": 727, "更": 728, "書": 729, "替": 730, "最": 731, "月": 732, "有": 733, "服": 734, "望": 735, "朝": 736, "期": 737, "木": 738, "末": 739, "本": 740, "札": 741, "机": 742, "材": 743, "村": 744, "束": 745, "条": 746, "来": 747, "杯": 748, "東": 749, "松": 750, "板": 751, "林": 752, "枚": 753, "果": 754, "枝": 755, "枠": 756, "柄": 757, "染": 758, "柔": 759, "柱": 760, "査": 761, "栄": 762, "栓": 763, "校": 764, "核": 765, "根": 766, "格": 767, "案": 768, "械": 769, "棋": 770, "棚": 771, "森": 772, "植": 773, "検": 774, "業": 775, "極": 776, "楽": 777, "概": 778, "構": 779, "様": 780, "標": 781, "模": 782, "横": 783, "樫": 784, "橋": 785, "機": 786, "欠": 787, "次": 788, "欧": 789, "欲": 790, "歌": 791, "歓": 792, "止": 793, "正": 794, "歩": 795, "歯": 796, "歳": 797, "歴": 798, "死": 799, "殊": 800, "残": 801, "殖": 802, "段": 803, "殻": 804, "殿": 805, "母": 806, "毎": 807, "毒": 808, "比": 809, "毛": 810, "氏": 811, "民": 812, "気": 813, "水": 814, "氷": 815, "永": 816, "氾": 817, "求": 818, "汗": 819, "汚": 820, "池": 821, "決": 822, "沈": 823, "河": 824, "油": 825, "治": 826, "沼": 827, "沿": 828, "況": 829, "泊": 830, "法": 831, "波": 832, "泣": 833, "泥": 834, "注": 835, "泳": 836, "洋": 837, "洒": 838, "洗": 839, "活": 840, "派": 841, "流": 842, "浄": 843, "浅": 844, "浜": 845, "浮": 846, "浴": 847, "海": 848, "浸": 849, "消": 850, "涙": 851, "涼": 852, "淋": 853, "淡": 854, "深": 855, "淵": 856, "混": 857, "済": 858, "減": 859, "渠": 860, "渡": 861, "温": 862, "港": 863, "湖": 864, "湯": 865, "満": 866, "源": 867, "準": 868, "溜": 869, "溢": 870, "滅": 871, "滑": 872, "滴": 873, "漁": 874, "漆": 875, "漏": 876, "演": 877, "漢": 878, "潜": 879, "潤": 880, "激": 881, "濃": 882, "濫": 883, "濯": 884, "瀬": 885, "火": 886, "灯": 887, "灰": 888, "炎": 889, "点": 890, "為": 891, "無": 892, "焦": 893, "然": 894, "焼": 895, "照": 896, "熊": 897, "熱": 898, "燃": 899, "燐": 900, "爆": 901, "父": 902, "片": 903, "版": 904, "牛": 905, "物": 906, "牲": 907, "特": 908, "牽": 909, "犠": 910, "犬": 911, "状": 912, "狩": 913, "独": 914, "狭": 915, "猟": 916, "猫": 917, "獅": 918, "獲": 919, "玄": 920, "率": 921, "玉": 922, "王": 923, "珍": 924, "現": 925, "球": 926, "理": 927, "琉": 928, "璧": 929, "瓶": 930, "甘": 931, "生": 932, "産": 933, "用": 934, "田": 935, "由": 936, "男": 937, "町": 938, "画": 939, "界": 940, "畑": 941, "留": 942, "略": 943, "番": 944, "異": 945, "畳": 946, "疲": 947, "病": 948, "症": 949, "痛": 950, "痢": 951, "痴": 952, "療": 953, "癖": 954, "発": 955, "登": 956, "白": 957, "百": 958, "的": 959, "皆": 960, "皮": 961, "皿": 962, "盛": 963, "監": 964, "盤": 965, "目": 966, "直": 967, "相": 968, "省": 969, "県": 970, "真": 971, "眠": 972, "眺": 973, "眼": 974, "着": 975, "睡": 976, "瞬": 977, "瞳": 978, "知": 979, "短": 980, "石": 981, "砂": 982, "研": 983, "砲": 984, "破": 985, "硬": 986, "碑": 987, "確": 988, "磨": 989, "示": 990, "社": 991, "祖": 992, "神": 993, "票": 994, "祭": 995, "福": 996, "禰": 997, "秀": 998, "私": 999, "秋": 1000, "秘": 1001, "称": 1002, "移": 1003, "程": 1004, "税": 1005, "種": 1006, "稿": 1007, "積": 1008, "穴": 1009, "究": 1010, "空": 1011, "突": 1012, "窒": 1013, "窓": 1014, "立": 1015, "章": 1016, "端": 1017, "競": 1018, "竹": 1019, "笑": 1020, "笛": 1021, "符": 1022, "筆": 1023, "筋": 1024, "筒": 1025, "答": 1026, "策": 1027, "算": 1028, "管": 1029, "箱": 1030, "節": 1031, "築": 1032, "米": 1033, "粉": 1034, "粧": 1035, "精": 1036, "糖": 1037, "糸": 1038, "系": 1039, "糾": 1040, "約": 1041, "紅": 1042, "紋": 1043, "純": 1044, "紙": 1045, "級": 1046, "紛": 1047, "素": 1048, "紫": 1049, "細": 1050, "終": 1051, "組": 1052, "経": 1053, "結": 1054, "絡": 1055, "給": 1056, "絵": 1057, "絶": 1058, "絹": 1059, "継": 1060, "続": 1061, "綴": 1062, "綿": 1063, "緊": 1064, "総": 1065, "緑": 1066, "緒": 1067, "線": 1068, "編": 1069, "練": 1070, "縁": 1071, "縦": 1072, "縫": 1073, "縮": 1074, "繁": 1075, "繊": 1076, "繋": 1077, "繕": 1078, "纏": 1079, "罅": 1080, "置": 1081, "署": 1082, "羊": 1083, "美": 1084, "群": 1085, "義": 1086, "羽": 1087, "翌": 1088, "習": 1089, "翻": 1090, "老": 1091, "考": 1092, "者": 1093, "耐": 1094, "耳": 1095, "聖": 1096, "聞": 1097, "職": 1098, "肉": 1099, "肋": 1100, "肌": 1101, "肘": 1102, "肝": 1103, "肥": 1104, "肩": 1105, "育": 1106, "胃": 1107, "背": 1108, "胴": 1109, "胸": 1110, "能": 1111, "脅": 1112, "脈": 1113, "脚": 1114, "脱": 1115, "脳": 1116, "腐": 1117, "腕": 1118, "腫": 1119, "腸": 1120, "腹": 1121, "膜": 1122, "膝": 1123, "臓": 1124, "自": 1125, "致": 1126, "興": 1127, "舗": 1128, "舞": 1129, "舟": 1130, "航": 1131, "般": 1132, "舶": 1133, "船": 1134, "艇": 1135, "良": 1136, "色": 1137, "花": 1138, "芸": 1139, "苑": 1140, "苗": 1141, "若": 1142, "苦": 1143, "英": 1144, "茂": 1145, "茶": 1146, "草": 1147, "荷": 1148, "菌": 1149, "菓": 1150, "菜": 1151, "落": 1152, "葉": 1153, "葬": 1154, "蔵": 1155, "薄": 1156, "薬": 1157, "藩": 1158, "虚": 1159, "虜": 1160, "虫": 1161, "融": 1162, "血": 1163, "衆": 1164, "行": 1165, "術": 1166, "街": 1167, "衛": 1168, "衣": 1169, "表": 1170, "袋": 1171, "裂": 1172, "装": 1173, "裏": 1174, "裕": 1175, "補": 1176, "製": 1177, "裾": 1178, "複": 1179, "襞": 1180, "襲": 1181, "西": 1182, "要": 1183, "覆": 1184, "見": 1185, "規": 1186, "視": 1187, "覚": 1188, "親": 1189, "観": 1190, "角": 1191, "解": 1192, "触": 1193, "言": 1194, "計": 1195, "訓": 1196, "記": 1197, "訪": 1198, "設": 1199, "許": 1200, "訳": 1201, "証": 1202, "評": 1203, "試": 1204, "詰": 1205, "話": 1206, "誌": 1207, "認": 1208, "誕": 1209, "語": 1210, "説": 1211, "読": 1212, "誰": 1213, "調": 1214, "談": 1215, "論": 1216, "諸": 1217, "謙": 1218, "講": 1219, "識": 1220, "警": 1221, "議": 1222, "譲": 1223, "護": 1224, "豆": 1225, "豊": 1226, "豚": 1227, "象": 1228, "負": 1229, "財": 1230, "貧": 1231, "販": 1232, "責": 1233, "買": 1234, "貸": 1235, "費": 1236, "貿": 1237, "賀": 1238, "賂": 1239, "賃": 1240, "賄": 1241, "資": 1242, "賑": 1243, "賛": 1244, "賞": 1245, "賢": 1246, "質": 1247, "赤": 1248, "走": 1249, "赴": 1250, "起": 1251, "超": 1252, "越": 1253, "足": 1254, "距": 1255, "跡": 1256, "路": 1257, "踊": 1258, "踏": 1259, "躇": 1260, "躊": 1261, "躍": 1262, "身": 1263, "車": 1264, "軌": 1265, "軍": 1266, "軒": 1267, "転": 1268, "軽": 1269, "輪": 1270, "輸": 1271, "辛": 1272, "辞": 1273, "農": 1274, "辺": 1275, "込": 1276, "迎": 1277, "近": 1278, "返": 1279, "追": 1280, "退": 1281, "送": 1282, "逃": 1283, "逆": 1284, "透": 1285, "途": 1286, "通": 1287, "速": 1288, "造": 1289, "連": 1290, "週": 1291, "進": 1292, "遂": 1293, "遅": 1294, "遇": 1295, "遊": 1296, "運": 1297, "遍": 1298, "過": 1299, "道": 1300, "達": 1301, "違": 1302, "遠": 1303, "適": 1304, "遭": 1305, "選": 1306, "遺": 1307, "避": 1308, "邦": 1309, "邪": 1310, "郊": 1311, "郡": 1312, "部": 1313, "郵": 1314, "郷": 1315, "都": 1316, "配": 1317, "酒": 1318, "酷": 1319, "酸": 1320, "醜": 1321, "里": 1322, "重": 1323, "野": 1324, "量": 1325, "金": 1326, "釣": 1327, "鉄": 1328, "鉛": 1329, "鉢": 1330, "銀": 1331, "銘": 1332, "鋼": 1333, "錨": 1334, "鍵": 1335, "鎮": 1336, "鏡": 1337, "長": 1338, "門": 1339, "閉": 1340, "開": 1341, "間": 1342, "関": 1343, "闇": 1344, "闘": 1345, "阪": 1346, "防": 1347, "降": 1348, "限": 1349, "院": 1350, "除": 1351, "陥": 1352, "陸": 1353, "隊": 1354, "階": 1355, "隔": 1356, "際": 1357, "障": 1358, "隣": 1359, "雄": 1360, "集": 1361, "雑": 1362, "離": 1363, "難": 1364, "雨": 1365, "雪": 1366, "雰": 1367, "雲": 1368, "零": 1369, "電": 1370, "需": 1371, "震": 1372, "霧": 1373, "露": 1374, "青": 1375, "静": 1376, "非": 1377, "面": 1378, "靴": 1379, "鞄": 1380, "音": 1381, "響": 1382, "預": 1383, "頑": 1384, "領": 1385, "頭": 1386, "頼": 1387, "題": 1388, "顔": 1389, "願": 1390, "類": 1391, "顧": 1392, "風": 1393, "飄": 1394, "飛": 1395, "食": 1396, "飯": 1397, "飲": 1398, "飾": 1399, "養": 1400, "餐": 1401, "餓": 1402, "館": 1403, "首": 1404, "馬": 1405, "駅": 1406, "駐": 1407, "騒": 1408, "験": 1409, "骨": 1410, "高": 1411, "髣": 1412, "髪": 1413, "髴": 1414, "魚": 1415, "鮮": 1416, "鯨": 1417, "鰻": 1418, "鳥": 1419, "鳴": 1420, "鵜": 1421, "麗": 1422, "麦": 1423, "黄": 1424, "黒": 1425, "黙": 1426, "鼻": 1427, "齢": 1428, ".": 1429, "?": 1430, "d": 1431, "g": 1432, "p": 1433, "|": 0, "[UNK]": 1434, "[PAD]": 1435}