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": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

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