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 @@
-{"i": 0, "k": 1, "b": 2, "s": 3, "o": 4, "g": 5, "u": 6, "q": 7, "m": 8, "h": 9, "v": 10, "r": 11, "ü": 12, "l": 13, "p": 14, "ä": 15, "z": 17, "n": 18, "ö": 19, "y": 20, "t": 21, "d": 22, "w": 23, "a": 24, "x": 25, "f": 26, "e": 27, "j": 28, "c": 29, "|": 16, "[UNK]": 30, "[PAD]": 31}
+{"y": 0, "g": 1, "k": 2, "n": 3, "a": 5, "m": 6, "ü": 7, "o": 8, "c": 9, "z": 10, "w": 11, "e": 12, "t": 13, "h": 14, "l": 15, "i": 16, "b": 17, "ä": 18, "ö": 19, "v": 20, "d": 21, "x": 22, "r": 23, "q": 24, "p": 25, "s": 26, "j": 27, "f": 28, "u": 29, "|": 4, "[UNK]": 30, "[PAD]": 31}