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