Upload tokenizer

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,102 @@
+{
+  "&": 1,
+  "[PAD]": 99,
+  "[UNK]": 98,
+  "\\": 2,
+  "_": 3,
+  "`": 4,
+  "a": 5,
+  "b": 6,
+  "c": 7,
+  "d": 8,
+  "e": 9,
+  "f": 10,
+  "g": 11,
+  "h": 12,
+  "i": 13,
+  "j": 14,
+  "k": 15,
+  "l": 16,
+  "m": 17,
+  "n": 18,
+  "o": 19,
+  "p": 20,
+  "q": 21,
+  "r": 22,
+  "s": 23,
+  "t": 24,
+  "u": 25,
+  "v": 26,
+  "w": 27,
+  "x": 28,
+  "y": 29,
+  "z": 30,
+  "|": 0,
+  "©": 32,
+  "«": 33,
+  "¬": 34,
+  "´": 35,
+  "µ": 36,
+  "»": 37,
+  "ë": 38,
+  "ò": 39,
+  "ó": 40,
+  "õ": 41,
+  "ü": 42,
+  "ģ": 43,
+  "ı": 44,
+  "ş": 45,
+  "ƣ": 46,
+  "ƶ": 47,
+  "ʙ": 48,
+  "ʻ": 49,
+  "ʼ": 50,
+  "а": 51,
+  "б": 52,
+  "в": 53,
+  "г": 54,
+  "д": 55,
+  "е": 56,
+  "ж": 57,
+  "з": 58,
+  "и": 59,
+  "й": 60,
+  "к": 61,
+  "л": 62,
+  "м": 63,
+  "н": 64,
+  "о": 65,
+  "п": 66,
+  "р": 67,
+  "с": 68,
+  "т": 69,
+  "у": 70,
+  "ф": 71,
+  "х": 72,
+  "ч": 73,
+  "ш": 74,
+  "ъ": 75,
+  "ы": 76,
+  "ь": 77,
+  "э": 78,
+  "ё": 79,
+  "ј": 80,
+  "ў": 81,
+  "ғ": 82,
+  "қ": 83,
+  "ҳ": 84,
+  "ӯ": 85,
+  "‒": 86,
+  "–": 87,
+  "—": 88,
+  "―": 89,
+  "’": 90,
+  "„": 91,
+  "•": 92,
+  "…": 93,
+  "−": 94,
+  "♂": 95,
+  "✅": 96,
+  "✔": 97,
+  "️": 98
+}