add tokenizer

tokenizer_config.json

@@ -1 +1 @@
-{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|", "replace_word_delimiter_char": " ", "tokenizer_class": "Wav2Vec2CTCTokenizer", "processor_class": "Wav2Vec2Processor"}
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|", "replace_word_delimiter_char": " ", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

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