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