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