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 @@
+{"a": 0, "p": 1, "e": 2, "9": 3, "o": 4, "3": 5, "h": 6, "n": 7, "w": 8, "y": 9, "k": 10, "1": 11, "x": 12, "0": 13, "v": 14, "g": 15, "f": 16, "2": 17, "i": 18, "5": 19, "c": 20, "d": 21, "m": 22, "7": 23, "l": 24, "6": 25, "s": 26, "u": 28, "b": 29, "j": 30, "r": 31, "t": 32, "z": 33, "|": 27, "[UNK]": 34, "[PAD]": 35}