add tokenizer

vocab.json

@@ -1 +1 @@
-{"a": 1, "b": 2, "c": 3, "d": 4, "e": 5, "f": 6, "g": 7, "h": 8, "i": 9, "j": 10, "k": 11, "l": 12, "m": 13, "n": 14, "o": 15, "p": 16, "r": 17, "s": 18, "t": 19, "u": 20, "v": 21, "w": 22, "x": 23, "y": 24, "z": 25, "“": 26, "”": 27, "।": 28, "ঁ": 29, "ং": 30, "ঃ": 31, "অ": 32, "আ": 33, "ই": 34, "ঈ": 35, "উ": 36, "ঊ": 37, "ঋ": 38, "এ": 39, "ঐ": 40, "ও": 41, "ঔ": 42, "ক": 43, "খ": 44, "গ": 45, "ঘ": 46, "ঙ": 47, "চ": 48, "ছ": 49, "জ": 50, "ঝ": 51, "ঞ": 52, "ট": 53, "ঠ": 54, "ড": 55, "ঢ": 56, "ণ": 57, "ত": 58, "থ": 59, "দ": 60, "ধ": 61, "ন": 62, "প": 63, "ফ": 64, "ব": 65, "ভ": 66, "ম": 67, "য": 68, "র": 69, "ল": 70, "শ": 71, "ষ": 72, "স": 73, "হ": 74, "়": 75, "া": 76, "ি": 77, "ী": 78, "ু": 79, "ূ": 80, "ৃ": 81, "ে": 82, "ৈ": 83, "ো": 84, "ৌ": 85, "্": 86, "ৎ": 87, "ৗ": 88, "ড়": 89, "ঢ়": 90, "য়": 91, "ৰ": 92, "‌": 93, "‍": 94, "‎": 95, "|": 0, "[UNK]": 96, "[PAD]": 97}
+{"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}