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