Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 158,
+  "<s>": 157
+}

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": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,159 @@
+{
+  "+": 1,
+  "[PAD]": 156,
+  "[UNK]": 155,
+  "_": 2,
+  "a": 3,
+  "b": 4,
+  "c": 5,
+  "d": 6,
+  "e": 7,
+  "f": 8,
+  "g": 9,
+  "h": 10,
+  "i": 11,
+  "j": 12,
+  "k": 13,
+  "l": 14,
+  "m": 15,
+  "n": 16,
+  "o": 17,
+  "p": 18,
+  "q": 19,
+  "r": 20,
+  "s": 21,
+  "t": 22,
+  "u": 23,
+  "v": 24,
+  "w": 25,
+  "x": 26,
+  "y": 27,
+  "z": 28,
+  "{": 29,
+  "|": 0,
+  "}": 30,
+  "~": 31,
+  "¡": 32,
+  "«": 33,
+  "´": 34,
+  "µ": 35,
+  "º": 36,
+  "»": 37,
+  "ß": 38,
+  "á": 39,
+  "â": 40,
+  "ã": 41,
+  "å": 42,
+  "æ": 43,
+  "ê": 44,
+  "ë": 45,
+  "î": 46,
+  "ð": 47,
+  "ñ": 48,
+  "ô": 49,
+  "ö": 50,
+  "ø": 51,
+  "û": 52,
+  "þ": 53,
+  "ÿ": 54,
+  "ā": 55,
+  "ą": 56,
+  "ć": 57,
+  "č": 58,
+  "đ": 59,
+  "ė": 60,
+  "ę": 61,
+  "ě": 62,
+  "ğ": 63,
+  "ī": 64,
+  "ı": 65,
+  "ľ": 66,
+  "ł": 67,
+  "ń": 68,
+  "ň": 69,
+  "ō": 70,
+  "ő": 71,
+  "œ": 72,
+  "ř": 73,
+  "ś": 74,
+  "ş": 75,
+  "š": 76,
+  "ū": 77,
+  "ŭ": 78,
+  "ź": 79,
+  "ż": 80,
+  "ž": 81,
+  "ș": 82,
+  "ț": 83,
+  "ə": 84,
+  "ʹ": 85,
+  "ʻ": 86,
+  "ʼ": 87,
+  "ʾ": 88,
+  "ː": 89,
+  "̇": 90,
+  "̨": 91,
+  "а": 92,
+  "б": 93,
+  "д": 94,
+  "е": 95,
+  "и": 96,
+  "к": 97,
+  "л": 98,
+  "м": 99,
+  "н": 100,
+  "о": 101,
+  "с": 102,
+  "т": 103,
+  "у": 104,
+  "ц": 105,
+  "ш": 106,
+  "ъ": 107,
+  "ѐ": 108,
+  "ё": 109,
+  "љ": 110,
+  "ң": 111,
+  "ד": 112,
+  "ה": 113,
+  "ו": 114,
+  "ة": 115,
+  "ر": 116,
+  "س": 117,
+  "ص": 118,
+  "غ": 119,
+  "ل": 120,
+  "ي": 121,
+  "ḥ": 122,
+  "ṇ": 123,
+  "ṛ": 124,
+  "ṣ": 125,
+  "ṭ": 126,
+  "ễ": 127,
+  "‑": 128,
+  "—": 129,
+  "′": 130,
+  "☆": 131,
+  "♭": 132,
+  "♯": 133,
+  "あ": 134,
+  "ア": 135,
+  "カ": 136,
+  "キ": 137,
+  "サ": 138,
+  "ザ": 139,
+  "ノ": 140,
+  "フ": 141,
+  "リ": 142,
+  "ン": 143,
+  "・": 144,
+  "ー": 145,
+  "万": 146,
+  "三": 147,
+  "丰": 148,
+  "古": 149,
+  "多": 150,
+  "峰": 151,
+  "張": 152,
+  "旅": 153,
+  "ꞌ": 154
+}