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 @@
+{"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}