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": true, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

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