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