add tokenizer

vocab.json

@@ -1 +1 @@
-{"a": 1, "e": 2, "f": 3, "i": 4, "o": 5, "r": 6, "t": 7, "x": 8, "а": 9, "б": 10, "в": 11, "г": 12, "д": 13, "е": 14, "ж": 15, "з": 16, "и": 17, "й": 18, "к": 19, "л": 20, "м": 21, "н": 22, "о": 23, "п": 24, "р": 25, "с": 26, "т": 27, "у": 28, "ф": 29, "х": 30, "ц": 31, "ч": 32, "ш": 33, "щ": 34, "ъ": 35, "ы": 36, "ь": 37, "э": 38, "ю": 39, "я": 40, "ё": 41, "җ": 42, "ң": 43, "ү": 44, "һ": 45, "ә": 46, "ө": 47, "–": 48, "—": 49, "|": 0, "<unk>": 50, "<pad>": 51, "<s>": 52, "</s>": 53}
+{"a": 1, "e": 2, "f": 3, "i": 4, "o": 5, "r": 6, "t": 7, "x": 8, "а": 9, "б": 10, "в": 11, "г": 12, "д": 13, "е": 14, "ж": 15, "з": 16, "и": 17, "й": 18, "к": 19, "л": 20, "м": 21, "н": 22, "о": 23, "п": 24, "р": 25, "с": 26, "т": 27, "у": 28, "ф": 29, "х": 30, "ц": 31, "ч": 32, "ш": 33, "щ": 34, "ъ": 35, "ы": 36, "ь": 37, "э": 38, "ю": 39, "я": 40, "ё": 41, "җ": 42, "ң": 43, "ү": 44, "һ": 45, "ә": 46, "ө": 47, "|": 0, "<unk>": 48, "<pad>": 49, "<s>": 50, "</s>": 51}