add 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 +1,114 @@
+{
+  "!": 30,
+  ".": 46,
+  "1": 85,
+  "2": 75,
+  "3": 7,
+  "4": 60,
+  "8": 66,
+  "?": 4,
+  "A": 96,
+  "B": 33,
+  "C": 1,
+  "D": 41,
+  "E": 48,
+  "F": 101,
+  "G": 39,
+  "H": 59,
+  "I": 69,
+  "J": 104,
+  "K": 68,
+  "L": 32,
+  "M": 11,
+  "N": 20,
+  "O": 53,
+  "P": 15,
+  "Q": 55,
+  "R": 70,
+  "S": 0,
+  "T": 78,
+  "U": 43,
+  "V": 3,
+  "W": 52,
+  "X": 94,
+  "Y": 106,
+  "Z": 84,
+  "[PAD]": 111,
+  "[UNK]": 110,
+  "a": 40,
+  "b": 92,
+  "c": 51,
+  "d": 91,
+  "e": 8,
+  "f": 6,
+  "g": 65,
+  "h": 35,
+  "i": 72,
+  "j": 77,
+  "k": 49,
+  "l": 61,
+  "m": 108,
+  "n": 19,
+  "o": 54,
+  "p": 56,
+  "q": 2,
+  "r": 79,
+  "s": 107,
+  "t": 67,
+  "u": 57,
+  "v": 100,
+  "w": 34,
+  "x": 95,
+  "y": 27,
+  "z": 83,
+  "|": 36,
+  "ㄱ": 71,
+  "ㄲ": 86,
+  "ㄳ": 97,
+  "ㄴ": 17,
+  "ㄵ": 64,
+  "ㄶ": 93,
+  "ㄷ": 12,
+  "ㄸ": 42,
+  "ㄹ": 22,
+  "ㄺ": 99,
+  "ㄻ": 58,
+  "ㄼ": 47,
+  "ㄾ": 73,
+  "ㅀ": 18,
+  "ㅁ": 87,
+  "ㅂ": 25,
+  "ㅃ": 31,
+  "ㅄ": 38,
+  "ㅅ": 80,
+  "ㅆ": 90,
+  "ㅇ": 50,
+  "ㅈ": 13,
+  "ㅉ": 28,
+  "ㅊ": 88,
+  "ㅋ": 26,
+  "ㅌ": 81,
+  "ㅍ": 16,
+  "ㅎ": 105,
+  "ㅏ": 24,
+  "ㅐ": 74,
+  "ㅑ": 63,
+  "ㅒ": 14,
+  "ㅓ": 62,
+  "ㅔ": 10,
+  "ㅕ": 37,
+  "ㅖ": 82,
+  "ㅗ": 29,
+  "ㅘ": 9,
+  "ㅙ": 98,
+  "ㅚ": 89,
+  "ㅛ": 102,
+  "ㅜ": 45,
+  "ㅝ": 5,
+  "ㅞ": 76,
+  "ㅟ": 44,
+  "ㅠ": 23,
+  "ㅡ": 109,
+  "ㅢ": 103,
+  "ㅣ": 21
+}