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