hrdipto's picture
add tokenizer
b117a5a
{"0": 1, "1": 2, "2": 3, "3": 4, "4": 5, "5": 6, "8": 7, "9": 8, "a": 9, "b": 10, "c": 11, "d": 12, "e": 13, "f": 14, "g": 15, "h": 16, "i": 17, "j": 18, "k": 19, "l": 20, "m": 21, "n": 22, "o": 23, "p": 24, "r": 25, "s": 26, "t": 27, "u": 28, "v": 29, "w": 30, "x": 31, "y": 32, "z": 33, "“": 34, "”": 35, "।": 36, "ঁ": 37, "ং": 38, "ঃ": 39, "অ": 40, "আ": 41, "ই": 42, "ঈ": 43, "উ": 44, "ঊ": 45, "ঋ": 46, "এ": 47, "ঐ": 48, "ও": 49, "ঔ": 50, "ক": 51, "খ": 52, "গ": 53, "ঘ": 54, "ঙ": 55, "চ": 56, "ছ": 57, "জ": 58, "ঝ": 59, "ঞ": 60, "ট": 61, "ঠ": 62, "ড": 63, "ঢ": 64, "ণ": 65, "ত": 66, "থ": 67, "দ": 68, "ধ": 69, "ন": 70, "প": 71, "ফ": 72, "ব": 73, "ভ": 74, "ম": 75, "য": 76, "র": 77, "ল": 78, "শ": 79, "ষ": 80, "স": 81, "হ": 82, "়": 83, "া": 84, "ি": 85, "ী": 86, "ু": 87, "ূ": 88, "ৃ": 89, "ে": 90, "ৈ": 91, "ো": 92, "ৌ": 93, "্": 94, "ৎ": 95, "ৗ": 96, "ড়": 97, "ঢ়": 98, "য়": 99, "০": 100, "১": 101, "২": 102, "৩": 103, "৪": 104, "৫": 105, "৬": 106, "৭": 107, "৮": 108, "৯": 109, "‌": 110, "‍": 111, "‎": 112, "|": 0, "[UNK]": 113, "[PAD]": 114}