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