add tokenizer

added_tokens.json

@@ -1 +1 @@
-{"<s>": 65, "</s>": 66}
+{"<s>": 67, "</s>": 68}

vocab.json

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