add tokenizer

added_tokens.json

@@ -1 +1 @@
-{"<s>": 67, "</s>": 68}
+{"<s>": 66, "</s>": 67}

vocab.json

@@ -1 +1 @@
-{"'": 1, "।": 2, "ঁ": 3, "ং": 4, "ঃ": 5, "অ": 6, "আ": 7, "ই": 8, "ঈ": 9, "উ": 10, "এ": 11, "ঐ": 12, "ও": 13, "ঔ": 14, "ক": 15, "খ": 16, "গ": 17, "ঘ": 18, "ঙ": 19, "চ": 20, "ছ": 21, "জ": 22, "ঝ": 23, "ঞ": 24, "ট": 25, "ঠ": 26, "ড": 27, "ঢ": 28, "ণ": 29, "ত": 30, "থ": 31, "দ": 32, "ধ": 33, "ন": 34, "প": 35, "ফ": 36, "ব": 37, "ভ": 38, "ম": 39, "য": 40, "র": 41, "ল": 42, "শ": 43, "ষ": 44, "স": 45, "হ": 46, "়": 47, "া": 48, "ি": 49, "ী": 50, "ু": 51, "ূ": 52, "ৃ": 53, "ে": 54, "ৈ": 55, "ো": 56, "ৌ": 57, "্": 58, "ৎ": 59, "ড়": 60, "ঢ়": 61, "য়": 62, "ৰ": 63, "ৱ": 64, "|": 0, "[UNK]": 65, "[PAD]": 66}
+{"।": 1, "ঁ": 2, "ং": 3, "ঃ": 4, "অ": 5, "আ": 6, "ই": 7, "ঈ": 8, "উ": 9, "এ": 10, "ঐ": 11, "ও": 12, "ঔ": 13, "ক": 14, "খ": 15, "গ": 16, "ঘ": 17, "ঙ": 18, "চ": 19, "ছ": 20, "জ": 21, "ঝ": 22, "ঞ": 23, "ট": 24, "ঠ": 25, "ড": 26, "ঢ": 27, "ণ": 28, "ত": 29, "থ": 30, "দ": 31, "ধ": 32, "ন": 33, "প": 34, "ফ": 35, "ব": 36, "ভ": 37, "ম": 38, "য": 39, "র": 40, "ল": 41, "শ": 42, "ষ": 43, "স": 44, "হ": 45, "়": 46, "া": 47, "ি": 48, "ী": 49, "ু": 50, "ূ": 51, "ৃ": 52, "ে": 53, "ৈ": 54, "ো": 55, "ৌ": 56, "্": 57, "ৎ": 58, "ড়": 59, "ঢ়": 60, "য়": 61, "ৰ": 62, "ৱ": 63, "|": 0, "[UNK]": 64, "[PAD]": 65}