init commit - 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 +1,11 @@
+{
+  "bos_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,110 @@
+{
+  "0": 41,
+  "1": 21,
+  "2": 95,
+  "3": 76,
+  "4": 88,
+  "5": 91,
+  "6": 99,
+  "7": 34,
+  "8": 61,
+  "9": 17,
+  "AA0": 16,
+  "AA1": 0,
+  "AA2": 38,
+  "AE0": 102,
+  "AE1": 26,
+  "AE2": 29,
+  "AH0": 93,
+  "AH1": 78,
+  "AH2": 42,
+  "AO0": 106,
+  "AO1": 50,
+  "AO2": 68,
+  "AW0": 43,
+  "AW1": 89,
+  "AW2": 19,
+  "AY0": 40,
+  "AY1": 101,
+  "AY2": 49,
+  "B": 90,
+  "CH": 103,
+  "D": 51,
+  "DH": 5,
+  "EH0": 73,
+  "EH1": 47,
+  "EH2": 104,
+  "ER0": 48,
+  "ER1": 32,
+  "ER2": 3,
+  "EY0": 53,
+  "EY1": 84,
+  "EY2": 67,
+  "F": 18,
+  "G": 60,
+  "HH": 74,
+  "IH0": 31,
+  "IH1": 33,
+  "IH2": 30,
+  "IY0": 64,
+  "IY1": 44,
+  "IY2": 24,
+  "JH": 72,
+  "K": 39,
+  "L": 75,
+  "M": 59,
+  "N": 4,
+  "NG": 70,
+  "OW0": 1,
+  "OW1": 13,
+  "OW2": 52,
+  "OY0": 28,
+  "OY1": 63,
+  "OY2": 11,
+  "P": 86,
+  "R": 87,
+  "S": 25,
+  "SH": 69,
+  "T": 92,
+  "TH": 79,
+  "UH0": 62,
+  "UH1": 10,
+  "UH2": 57,
+  "UW0": 105,
+  "UW1": 23,
+  "UW2": 81,
+  "V": 27,
+  "W": 100,
+  "Y": 35,
+  "Z": 45,
+  "ZH": 46,
+  "[PAD]": 56,
+  "[UNK]": 20,
+  "a": 83,
+  "b": 12,
+  "c": 8,
+  "d": 6,
+  "e": 98,
+  "f": 37,
+  "g": 107,
+  "h": 7,
+  "i": 58,
+  "j": 85,
+  "k": 14,
+  "l": 66,
+  "m": 82,
+  "n": 9,
+  "o": 36,
+  "p": 15,
+  "q": 65,
+  "r": 77,
+  "s": 55,
+  "t": 22,
+  "u": 94,
+  "v": 54,
+  "w": 80,
+  "x": 96,
+  "y": 97,
+  "z": 71,
+  "|": 2
+}