add tokenizer

vocab.json

@@ -1 +1 @@
-{"ც": 0, "რ": 2, "კ": 3, "ჩ": 4, "ქ": 5, "ტ": 6, "ჭ": 7, "„": 8, "უ": 9, "ა": 10, "ღ": 11, "ნ": 12, "ჟ": 13, "ი": 14, "პ": 15, "ძ": 16, "თ": 17, "ვ": 18, "ო": 19, "ფ": 20, "წ": 21, "ლ": 22, "ს": 23, "ე": 24, "ხ": 25, "ჯ": 26, "–": 27, "ყ": 28, "ბ": 29, "ზ": 30, "მ": 31, "შ": 32, "გ": 33, "ჰ": 34, "დ": 35, "|": 1, "[UNK]": 36, "[PAD]": 37}
+{"в": 0, "ч": 1, "ы": 3, "ө": 4, "г": 5, "щ": 6, "у": 7, "л": 8, "ш": 9, "т": 10, "н": 11, "м": 12, "о": 13, "–": 14, "ӊ": 15, "х": 16, "ц": 17, "й": 18, "с": 19, "ё": 20, "ф": 21, "ю": 22, "э": 23, "ң": 24, "ь": 25, "я": 26, "и": 27, "⅛": 28, "д": 29, "б": 30, "п": 31, "ж": 32, "к": 33, "—": 34, "е": 35, "ъ": 36, "ү": 37, "а": 38, "р": 39, "з": 40, "|": 2, "[UNK]": 41, "[PAD]": 42}