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": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

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