add tokenizer

vocab.json

@@ -1 +1 @@
-{"с": 0, "р": 1, "ю": 2, "ж": 3, "щ": 4, "ё": 5, "и": 6, "я": 7, "й": 8, "д": 9, "ч": 10, "ь": 12, "г": 13, "ш": 14, "е": 15, "х": 16, "т": 17, "н": 18, "ы": 19, "б": 20, "у": 21, "л": 22, "в": 23, "к": 24, "э": 25, "з": 26, "о": 27, "ф": 28, "ъ": 29, "м": 30, "ц": 31, "а": 32, "п": 33, "|": 11, "[UNK]": 34, "[PAD]": 35}
+{"ш": 0, "ж": 2, "с": 3, "д": 4, "я": 5, "и": 6, "ь": 7, "х": 8, "н": 9, "е": 10, "к": 11, "ф": 12, "ъ": 13, "б": 14, "у": 15, "ц": 16, "ю": 17, "м": 18, "п": 19, "й": 20, "ы": 21, "ё": 22, "в": 23, "о": 24, "з": 25, "а": 26, "р": 27, "т": 28, "щ": 29, "ч": 30, "л": 31, "г": 32, "э": 33, "|": 1, "[UNK]": 34, "[PAD]": 35}