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