add tokenizer

tokenizer_config.json

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

vocab.json

@@ -1 +1 @@
-{"[PAD]": 0, "p": 1, "q": 2, "u": 3, "v": 4, "l": 5, "3": 6, "5": 7, "j": 8, "o": 9, "r": 10, "f": 11, "g": 12, "6": 13, "m": 14, "d": 15, "8": 16, "y": 17, "e": 18, "h": 19, "t": 20, "k": 21, "i": 22, "4": 23, "0": 24, "x": 25, "'": 26, "1": 27, "n": 28, "w": 29, "s": 30, "c": 32, "a": 33, "b": 34, "9": 35, "z": 36, "|": 31, "[UNK]": 37, "2": 38}
+{"9": 0, "4": 1, "'": 2, "u": 3, "g": 4, "1": 5, "v": 6, "8": 7, "w": 8, "r": 9, "i": 10, "k": 11, "b": 12, "d": 13, "n": 14, "c": 15, "j": 16, "y": 17, "x": 18, "5": 19, "6": 20, "0": 21, "s": 22, "3": 23, "e": 24, "f": 25, "a": 26, "l": 27, "q": 28, "o": 29, "m": 30, "z": 31, "h": 32, "2": 33, "t": 34, "p": 35, "|": 36, "[UNK]": 37, "[PAD]": 38}