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": "|", "replace_word_delimiter_char": " ", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

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