Files
wav2vec2-large-japanese/vocab.json

1 line
26 KiB
JSON
Raw Normal View History

{"<pad>": 0, "<s>": 1, "</s>": 2, "<unk>": 3, "|": 4, "-": 5, "C": 6, "P": 7, "々": 8, "ぁ": 9, "あ": 10, "い": 11, "う": 12, "ぇ": 13, "え": 14, "お": 15, "か": 16, "が": 17, "き": 18, "ぎ": 19, "く": 20, "ぐ": 21, "け": 22, "げ": 23, "こ": 24, "ご": 25, "さ": 26, "ざ": 27, "し": 28, "じ": 29, "す": 30, "ず": 31, "せ": 32, "ぜ": 33, "そ": 34, "ぞ": 35, "た": 36, "だ": 37, "ち": 38, "ぢ": 39, "っ": 40, "つ": 41, "づ": 42, "て": 43, "で": 44, "と": 45, "ど": 46, "な": 47, "に": 48, "ぬ": 49, "ね": 50, "の": 51, "は": 52, "ば": 53, "ぱ": 54, "ひ": 55, "び": 56, "ぴ": 57, "ふ": 58, "ぶ": 59, "ぷ": 60, "へ": 61, "べ": 62, "ぺ": 63, "ほ": 64, "ぼ": 65, "ぽ": 66, "ま": 67, "み": 68, "む": 69, "め": 70, "も": 71, "ゃ": 72, "や": 73, "ゅ": 74, "ゆ": 75, "ょ": 76, "よ": 77, "ら": 78, "り": 79, "る": 80, "れ": 81, "ろ": 82, "わ": 83, "を": 84, "ん": 85, "ァ": 86, "ア": 87, "ィ": 88, "イ": 89, "ゥ": 90, "ウ": 91, "ェ": 92, "エ": 93, "ォ": 94, "オ": 95, "カ": 96, "ガ": 97, "キ": 98, "ギ": 99, "ク": 100, "グ": 101, "ケ": 102, "ゲ": 103, "コ": 104, "ゴ": 105, "サ": 106, "ザ": 107, "シ": 108, "ジ": 109, "ス": 110, "ズ": 111, "セ": 112, "ゼ": 113, "ソ": 114, "ゾ": 115, "タ": 116, "ダ": 117, "チ": 118, "ッ": 119, "ツ": 120, "テ": 121, "デ": 122, "ト": 123, "ド": 124, "ナ": 125, "ニ": 126, "ヌ": 127, "ネ": 128, "": 129, "ハ": 130, "バ": 131, "パ": 132, "ヒ": 133, "ビ": 134, "ピ": 135, "フ": 136, "ブ": 137, "プ": 138, "ヘ": 139, "ベ": 140, "ペ": 141, "ホ": 142, "ボ": 143, "ポ": 144, "マ": 145, "ミ": 146, "ム": 147, "メ": 148, "モ": 149, "ャ": 150, "ヤ": 151, "ュ": 152, "ユ": 153, "ョ": 154, "ヨ": 155, "ラ": 156, "リ": 157, "ル": 158, "レ": 159, "ロ": 160, "ワ": 161, "ン": 162, "ヴ": 163, "ヶ": 164, "ー": 165, "一": 166, "丁": 167, "七": 168, "万": 169, "丈": 170, "三": 171, "上": 172, "下": 173, "不": 174, "与": 175, "世": 176, "丘": 177, "両": 178, "並": 179, "中": 180, "丸": 181, "丹": 182, "主": 183, "丼": 184, "乃": 185, "久": 186, "乏": 187, "乖": 188, "乗": 189, "九": 190, "也": 191, "乱": 192, "乳": 193, "乾": 194, "亀": 195, "了": 196, "予": 197, "争": 198, "事": 199, "二": 200, "于": 201, "互": 202, "五": 203, "井": 204, "亘": 205, "亜": 206, "亡": 207, "交": 208, "享": 209, "京": 210, "亭": 211, "人": 212, "仁": 213, "今": 214, "介": 215, "仏": 216, "仕": 217, "他": 218, "付": 219, "仙": 220, "代": 221, "令": 222, "以": 223, "仮": 224, "仰": 225, "仲": 226, "件": 227, "任": 228, "企": 229, "伊": 230, "伏": 231, "休": 232, "会": 233, "伝": 234, "伴": 235, "伸": 236, "似": 237, "伽": 238, "但": 239, "位": 240, "低": 241, "住": 242, "佐": 243, "体": 244, "何": 245, "余": 246, "作": 247, "併": 248, "使": 249, "例": 250, "供": 251, "依": 252, "価": 253, "侮": 254, "侵": 255, "侶": 256, "便": 257, "係": 258, "促": 259, "俊": 260, "俗": 261, "保": 262, "信": 263, "俣": 264, "修": 265, "俳": 266, "俺": 267, "倉": 268, "個": 269, "倍": 270, "倒": 271, "候": 272, "借": 273, "値": 274, "倫": 275, "偉": 276, "偏": 277, "停": 278, "健": 279, "側": 280, "偵": 281, "偶": 282, "偽": 283, "傍": 284, "傘": 285, "備": 286, "催": 287, "債": 288, "傷": 289, "傾": 290, "働": 291, "像": 292, "僕": 293, "僚": 294, "僧": 295, "儀": 296, "億": 297, "儒": 298, "償": 299, "優": 300, "儲": 301, "元": 302, "兄": 303, "充": 304, "先": 305, "光": 306, "免": 307, "児": 308, "党": 309, "兜": 310, "入": 311, "全": 312, "八": 313, "公": 314, "六": 315, "共": 316, "兵": 317, "具": 318, "典": 319, "兼": 320, "内": 321, "円": 322, "冊": 323, "再": 324, "冒": 325, "冗": 326, "写": 327, "冠": 328, "冬": 329, "冷": 330, "凄": 331, "凌": 332, "凍": 333, "凛": 334, "凝": 335, "処": 336, "凶": 337, "出": 338, "刀": 339, "刃": 340, "分": 341, "切": 342, "刈": 343, "刊": 344, "刑": 345, "列": 346, "初": 347, "判": 348, "別": 349, "利":