20220517-010959 / vocab.json
lilitket's picture
add tokenizer
2b02dac
raw
history blame contribute delete
424 Bytes
{"-": 1, "ա": 2, "բ": 3, "գ": 4, "դ": 5, "ե": 6, "զ": 7, "է": 8, "ը": 9, "թ": 10, "ժ": 11, "ի": 12, "լ": 13, "խ": 14, "ծ": 15, "կ": 16, "հ": 17, "ձ": 18, "ղ": 19, "ճ": 20, "մ": 21, "յ": 22, "ն": 23, "շ": 24, "ո": 25, "չ": 26, "պ": 27, "ջ": 28, "ռ": 29, "ս": 30, "վ": 31, "տ": 32, "ր": 33, "ց": 34, "ւ": 35, "փ": 36, "ք": 37, "օ": 38, "ֆ": 39, "և": 40, "|": 0, "[UNK]": 41, "[PAD]": 42}