Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 169,
+  "<s>": 168
+}

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 +1,13 @@
+{
+  "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": " ",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,170 @@
+{
+  "$": 160,
+  "&": 116,
+  "'": 32,
+  "(": 80,
+  ")": 73,
+  "+": 40,
+  "=": 120,
+  "[": 147,
+  "[PAD]": 167,
+  "[UNK]": 166,
+  "]": 107,
+  "`": 157,
+  "a": 2,
+  "b": 119,
+  "c": 83,
+  "d": 109,
+  "e": 67,
+  "f": 49,
+  "g": 72,
+  "h": 57,
+  "i": 102,
+  "j": 18,
+  "k": 15,
+  "l": 94,
+  "m": 21,
+  "n": 1,
+  "o": 144,
+  "p": 64,
+  "q": 86,
+  "r": 90,
+  "s": 26,
+  "t": 137,
+  "u": 43,
+  "v": 17,
+  "w": 108,
+  "x": 130,
+  "y": 85,
+  "z": 76,
+  "|": 48,
+  "¡": 31,
+  "«": 14,
+  "´": 93,
+  "µ": 24,
+  "»": 141,
+  "ß": 12,
+  "à": 103,
+  "á": 159,
+  "â": 16,
+  "ã": 105,
+  "ä": 124,
+  "å": 78,
+  "æ": 60,
+  "ç": 164,
+  "é": 28,
+  "ê": 69,
+  "ë": 101,
+  "ì": 118,
+  "í": 115,
+  "î": 9,
+  "ï": 20,
+  "ð": 0,
+  "ñ": 133,
+  "ò": 45,
+  "ó": 128,
+  "ô": 35,
+  "õ": 123,
+  "ö": 88,
+  "ø": 59,
+  "ù": 152,
+  "ú": 61,
+  "û": 113,
+  "ü": 44,
+  "ý": 91,
+  "þ": 139,
+  "ā": 104,
+  "ă": 145,
+  "ą": 79,
+  "ć": 163,
+  "č": 98,
+  "ď": 10,
+  "đ": 156,
+  "ē": 39,
+  "ė": 25,
+  "ę": 127,
+  "ě": 89,
+  "ğ": 140,
+  "ġ": 111,
+  "ħ": 117,
+  "ī": 34,
+  "ı": 62,
+  "ł": 52,
+  "ń": 51,
+  "ņ": 3,
+  "ň": 84,
+  "ō": 36,
+  "ŏ": 11,
+  "ő": 165,
+  "œ": 162,
+  "ř": 56,
+  "ś": 50,
+  "ş": 155,
+  "š": 129,
+  "ť": 82,
+  "ū": 41,
+  "ů": 47,
+  "ź": 65,
+  "ż": 6,
+  "ž": 53,
+  "ǐ": 81,
+  "ș": 23,
+  "ț": 125,
+  "ə": 135,
+  "ʻ": 122,
+  "ʿ": 74,
+  "̆": 150,
+  "̇": 38,
+  "а": 110,
+  "в": 154,
+  "е": 143,
+  "и": 37,
+  "к": 142,
+  "м": 106,
+  "о": 153,
+  "р": 68,
+  "с": 7,
+  "ф": 27,
+  "ч": 146,
+  "ш": 33,
+  "ѹ": 112,
+  "་": 75,
+  "ན": 97,
+  "ḫ": 121,
+  "ṟ": 63,
+  "ṣ": 55,
+  "ṭ": 5,
+  "ạ": 95,
+  "ả": 151,
+  "ắ": 158,
+  "ằ": 29,
+  "ế": 132,
+  "ễ": 46,
+  "ộ": 126,
+  "‑": 8,
+  "–": 131,
+  "—": 114,
+  "’": 134,
+  "‚": 138,
+  "„": 87,
+  "‟": 77,
+  "…": 148,
+  "′": 71,
+  "″": 58,
+  "‹": 42,
+  "›": 4,
+  "→": 100,
+  "−": 22,
+  "≡": 30,
+  "⟨": 19,
+  "⟩": 70,
+  "カ": 54,
+  "临": 99,
+  "孙": 13,
+  "尣": 96,
+  "支": 161,
+  "比": 149,
+  "無": 92,
+  "臣": 66,
+  "道": 136
+}