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