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