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