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