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 @@
+{"b": 0, "t": 1, "m": 2, "o": 3, "s": 4, "f": 5, "y": 6, "h": 7, "g": 8, "e": 9, "d": 10, "l": 11, "r": 12, "c": 13, "p": 14, "u": 15, "w": 16, "n": 17, "k": 18, "i": 19, "a": 21, "|": 20, "[UNK]": 22, "[PAD]": 23}