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