jfealko's picture
add tokenizer
8ec41cd
raw
history blame
526 Bytes
{"a": 1, "b": 2, "c": 3, "e": 4, "f": 5, "g": 6, "h": 7, "i": 8, "k": 9, "l": 10, "m": 11, "n": 12, "o": 13, "p": 14, "r": 15, "s": 16, "t": 17, "x": 18, "z": 19, "а": 20, "б": 21, "в": 22, "г": 23, "д": 24, "е": 25, "ж": 26, "з": 27, "и": 28, "й": 29, "к": 30, "л": 31, "м": 32, "н": 33, "о": 34, "п": 35, "р": 36, "с": 37, "т": 38, "у": 39, "ф": 40, "х": 41, "ц": 42, "ч": 43, "ш": 44, "щ": 45, "ъ": 46, "ы": 47, "ь": 48, "э": 49, "ю": 50, "я": 51, "ё": 52, "|": 0, "[UNK]": 53, "[PAD]": 54}