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