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, "N": 1, "F": 2, "P": 3, "H": 4, "R": 5, "S": 6, "'": 7, "O": 8, "E": 10, "Z": 11, "Q": 12, "B": 13, "D": 14, "C": 15, "U": 16, "G": 17, "W": 18, "V": 19, "X": 20, "J": 21, "L": 22, "I": 23, "Y": 24, "A": 25, "T": 26, "K": 27, "|": 9, "[UNK]": 28, "[PAD]": 29}