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