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