Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 220,
+  "<s>": 219
+}

special_tokens_map.json

@@ -0,0 +1,22 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,222 @@
+{
+  "$": 1,
+  "&": 2,
+  "-": 3,
+  "=": 4,
+  "[PAD]": 219,
+  "[UNK]": 218,
+  "_": 5,
+  "`": 6,
+  "a": 7,
+  "b": 8,
+  "c": 9,
+  "d": 10,
+  "e": 11,
+  "f": 12,
+  "g": 13,
+  "h": 14,
+  "i": 15,
+  "j": 16,
+  "k": 17,
+  "l": 18,
+  "m": 19,
+  "n": 20,
+  "o": 21,
+  "p": 22,
+  "q": 23,
+  "r": 24,
+  "s": 25,
+  "t": 26,
+  "u": 27,
+  "v": 28,
+  "w": 29,
+  "x": 30,
+  "y": 31,
+  "z": 32,
+  "{": 33,
+  "|": 0,
+  "}": 35,
+  "~": 36,
+  "¨": 37,
+  "ª": 38,
+  "«": 39,
+  "®": 40,
+  "°": 41,
+  "´": 42,
+  "·": 43,
+  "»": 44,
+  "ß": 45,
+  "à": 46,
+  "á": 47,
+  "â": 48,
+  "ã": 49,
+  "ä": 50,
+  "å": 51,
+  "æ": 52,
+  "é": 53,
+  "ê": 54,
+  "ë": 55,
+  "ì": 56,
+  "í": 57,
+  "î": 58,
+  "ï": 59,
+  "ð": 60,
+  "ñ": 61,
+  "ò": 62,
+  "ó": 63,
+  "ô": 64,
+  "õ": 65,
+  "ö": 66,
+  "ø": 67,
+  "ù": 68,
+  "ú": 69,
+  "û": 70,
+  "ü": 71,
+  "ý": 72,
+  "þ": 73,
+  "ā": 74,
+  "ă": 75,
+  "ć": 76,
+  "č": 77,
+  "đ": 78,
+  "ė": 79,
+  "ę": 80,
+  "ě": 81,
+  "ğ": 82,
+  "ī": 83,
+  "ı": 84,
+  "ł": 85,
+  "ń": 86,
+  "ō": 87,
+  "ő": 88,
+  "œ": 89,
+  "ř": 90,
+  "ś": 91,
+  "ş": 92,
+  "š": 93,
+  "ū": 94,
+  "ź": 95,
+  "ž": 96,
+  "ș": 97,
+  "ț": 98,
+  "ə": 99,
+  "ʷ": 100,
+  "ʻ": 101,
+  "ʽ": 102,
+  "ʿ": 103,
+  "ː": 104,
+  "́": 105,
+  "̇": 106,
+  "ϙ": 107,
+  "а": 108,
+  "б": 109,
+  "в": 110,
+  "г": 111,
+  "д": 112,
+  "е": 113,
+  "и": 114,
+  "й": 115,
+  "к": 116,
+  "л": 117,
+  "н": 118,
+  "о": 119,
+  "п": 120,
+  "р": 121,
+  "с": 122,
+  "т": 123,
+  "ч": 124,
+  "ш": 125,
+  "ы": 126,
+  "ь": 127,
+  "ю": 128,
+  "я": 129,
+  "ё": 130,
+  "ү": 131,
+  "ө": 132,
+  "ְ": 133,
+  "ִ": 134,
+  "ֵ": 135,
+  "ָ": 136,
+  "ֹ": 137,
+  "ּ": 138,
+  "ב": 139,
+  "ה": 140,
+  "ו": 141,
+  "י": 142,
+  "כ": 143,
+  "ל": 144,
+  "ם": 145,
+  "מ": 146,
+  "נ": 147,
+  "ס": 148,
+  "ק": 149,
+  "ר": 150,
+  "ש": 151,
+  "ת": 152,
+  "ب": 153,
+  "ة": 154,
+  "ذ": 155,
+  "ه": 156,
+  "ي": 157,
+  "ਆ": 158,
+  "ਘ": 159,
+  "ਤ": 160,
+  "ਨ": 161,
+  "ਮ": 162,
+  "ਸ": 163,
+  "ਾ": 164,
+  "ਿ": 165,
+  "ੰ": 166,
+  "ṁ": 167,
+  "ṃ": 168,
+  "ṇ": 169,
+  "ồ": 170,
+  "‐": 171,
+  "‑": 172,
+  "–": 173,
+  "—": 174,
+  "―": 175,
+  "’": 176,
+  "„": 177,
+  "…": 178,
+  "‧": 179,
+  "‹": 180,
+  "›": 181,
+  "→": 182,
+  "≪": 183,
+  "≫": 184,
+  "し": 185,
+  "の": 186,
+  "ひ": 187,
+  "ら": 188,
+  "ゴ": 189,
+  "ヒ": 190,
+  "ミ": 191,
+  "ム": 192,
+  "ラ": 193,
+  "㓁": 194,
+  "口": 195,
+  "周": 196,
+  "山": 197,
+  "戌": 198,
+  "日": 199,
+  "本": 200,
+  "比": 201,
+  "毵": 202,
+  "消": 203,
+  "生": 204,
+  "申": 205,
+  "真": 206,
+  "箱": 207,
+  "网": 208,
+  "罒": 209,
+  "罓": 210,
+  "肋": 211,
+  "肌": 212,
+  "背": 213,
+  "良": 214,
+  "鮓": 215,
+  "鮨": 216,
+  "fi": 217,
+  "": 218
+}