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