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