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 @@
+{"4": 0, "z": 1, "m": 2, "d": 3, "t": 4, "q": 5, "g": 6, "p": 7, "w": 8, "l": 9, "9": 10, "x": 11, "u": 12, "6": 13, "7": 14, "8": 15, "j": 16, "s": 17, "'": 18, "c": 19, "2": 20, "i": 21, "n": 22, "b": 23, "a": 24, "%": 25, "1": 27, "h": 28, "k": 29, "o": 30, "3": 31, "e": 32, "5": 33, "y": 34, "v": 35, "f": 36, "0": 37, "r": 38, "|": 26, "[UNK]": 39, "[PAD]": 40}