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

vocab.json

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