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, "f": 1, "u": 2, "t": 3, "y": 4, "i": 5, "r": 6, "w": 7, "g": 8, "e": 9, "o": 10, "b": 11, "c": 12, "p": 13, "k": 14, "a": 15, "x": 16, "l": 18, "v": 19, "h": 20, "d": 21, "s": 22, "n": 23, "|": 17, "[UNK]": 24, "[PAD]": 25}