add tokenizer

special_tokens_map.json

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

tokenizer_config.json

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

vocab.json

@@ -0,0 +1 @@
+{"O": 0, "q": 1, "K": 2, "r": 3, "P": 4, "c": 5, "n": 6, "H": 7, "?": 8, "o": 9, "h": 10, "T": 11, "t": 12, "i": 13, "!": 14, "u": 15, "z": 16, "\"": 17, "j": 18, "V": 19, ",": 20, "m": 21, "b": 22, "x": 23, "g": 24, "L": 25, "D": 26, "U": 27, "F": 28, "l": 29, "w": 30, "e": 31, ";": 32, "M": 33, "a": 34, "R": 35, "y": 37, "S": 38, "J": 39, "'": 40, "d": 41, "Q": 42, "A": 43, "k": 44, "N": 45, "p": 46, "G": 47, "Y": 48, "W": 49, "-": 50, "C": 51, "E": 52, "v": 53, "B": 54, "X": 55, "s": 56, ":": 57, "I": 58, ".": 59, "f": 60, "|": 36, "[UNK]": 61, "[PAD]": 62}