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

vocab.json

@@ -0,0 +1 @@
+{"c": 0, "ü": 1, "ë": 2, "r": 3, "b": 4, "u": 5, "f": 6, "â": 7, "̇": 8, "x": 9, "v": 10, "y": 11, "o": 12, "g": 13, "i": 14, "h": 15, "ı": 16, "d": 17, "t": 18, "s": 19, "a": 20, "n": 21, "k": 22, "î": 23, "q": 24, "p": 25, "m": 27, "l": 28, "ö": 29, "z": 30, "w": 31, "e": 32, "ş": 33, "j": 34, "'": 35, "ç": 36, "ğ": 37, "|": 26, "[UNK]": 38, "[PAD]": 39}