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 +1,12 @@
+{
+  "bos_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "max_length": 512,
+  "pad_token": "[PAD]",
+  "padding": "max_length",
+  "replace_word_delimiter_char": " ",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,75 @@
+{
+  "0": 48,
+  "1": 49,
+  "2": 55,
+  "3": 15,
+  "4": 35,
+  "8": 66,
+  "[PAD]": 72,
+  "[UNK]": 71,
+  "a": 24,
+  "c": 67,
+  "d": 26,
+  "e": 20,
+  "f": 41,
+  "i": 19,
+  "j": 62,
+  "m": 0,
+  "n": 6,
+  "o": 56,
+  "p": 23,
+  "r": 5,
+  "s": 40,
+  "t": 47,
+  "u": 39,
+  "v": 44,
+  "|": 21,
+  "ㄱ": 11,
+  "ㄲ": 43,
+  "ㄴ": 8,
+  "ㄵ": 45,
+  "ㄶ": 38,
+  "ㄷ": 63,
+  "ㄸ": 65,
+  "ㄹ": 29,
+  "ㄺ": 69,
+  "ㄻ": 25,
+  "ㄼ": 70,
+  "ㄾ": 52,
+  "ㅀ": 59,
+  "ㅁ": 16,
+  "ㅂ": 4,
+  "ㅃ": 61,
+  "ㅄ": 36,
+  "ㅅ": 10,
+  "ㅆ": 7,
+  "ㅇ": 64,
+  "ㅈ": 68,
+  "ㅉ": 2,
+  "ㅊ": 34,
+  "ㅋ": 3,
+  "ㅌ": 37,
+  "ㅍ": 30,
+  "ㅎ": 12,
+  "ㅏ": 13,
+  "ㅐ": 42,
+  "ㅑ": 22,
+  "ㅒ": 54,
+  "ㅓ": 17,
+  "ㅔ": 57,
+  "ㅕ": 1,
+  "ㅖ": 50,
+  "ㅗ": 51,
+  "ㅘ": 14,
+  "ㅙ": 46,
+  "ㅚ": 27,
+  "ㅛ": 32,
+  "ㅜ": 31,
+  "ㅝ": 9,
+  "ㅞ": 18,
+  "ㅟ": 28,
+  "ㅠ": 58,
+  "ㅡ": 33,
+  "ㅢ": 53,
+  "ㅣ": 60
+}