| {"bn": {"<unk>": 0, "য়": 1, "ার": 2, "▁ক": 3, "▁স": 4, "▁ব": 5, "ের": 6, "▁প": 7, "্র": 8, "্য": 9, "ান": 10, "▁এ": 11, "▁আ": 12, "▁ম": 13, "▁হ": 14, "▁ন": 15, "▁দ": 16, "▁কর": 17, "▁ত": 18, "্ত": 19, "য়ে": 20, "েন": 21, "▁অ": 22, "▁জ": 23, "কে": 24, "িন": 25, "াল": 26, "ায়": 27, "তে": 28, "▁প্র": 29, "িক": 30, "▁শ": 31, "ছে": 32, "▁র": 33, "▁য": 34, "াম": 35, "টি": 36, "র্": 37, "বে": 38, "▁বি": 39, "▁গ": 40, "ড়": 41, "লে": 42, "▁চ": 43, "লা": 44, "▁নি": 45, "াস": 46, "▁ভ": 47, "▁ও": 48, "্ব": 49, "তি": 50, "▁উ": 51, "▁পর": 52, "্ট": 53, "াক": 54, "দের": 55, "্ষ": 56, "▁থ": 57, "িত": 58, "াজ": 59, "▁করে": 60, "িল": 61, "ুর": 62, "াই": 63, "▁এক": 64, "ুল": 65, "▁দে": 66, "িয়ে": 67, "াত": 68, "▁বা": 69, "▁সম": 70, "ন্": 71, "্থ": 72, "ির": 73, "্যা": 74, "▁ফ": 75, "▁খ": 76, "▁তা": 77, "য়া": 78, "▁ছ": 79, "নে": 80, "রা": 81, "▁ই": 82, "▁আম": 83, "▁হয়ে": 84, "েশ": 85, "বার": 86, "▁না": 87, "ন্ত": 88, "্প": 89, "োন": 90, "েকে": 91, "▁জন": 92, "বা": 93, "ঙ্": 94, "ছেন": 95, "ক্ষ": 96, "▁সে": 97, "▁থেকে": 98, "িস": 99, "▁তার": 100, "▁হয়": 101, "▁এই": 102, "য়ার": 103, "▁ট": 104, "▁১": 105, "েল": 106, "ভা": 107, "োগ": 108, "কার": 109, "দ্": 110, "িনি": 111, "▁ল": 112, "ঙ্গ": 113, "▁সা": 114, "▁ঘ": 115, "চ্": 116, "টা": 117, "না": 118, "ক্ত": 119, "বি": 120, "নি": 121, "ধ্য": 122, "▁জান": 123, "▁আর": 124, "▁পা": 125, "নের": 126, "▁করা": 127, "▁ধ": 128, "▁অন": 129, "▁পার": 130, "্ম": 131, "▁সং": 132, "ীর": 133, "▁এব": 134, "▁এবং": 135, "▁২": 136, "▁ড": 137, "▁মা": 138, "তা": 139, "▁নে": 140, "ীয়": 141, "▁যে": 142, "দ্ধ": 143, "স্থ": 144, "িশ": 145, "রে": 146, "▁যা": 147, "▁উপ": 148, "ুন": 149, "ষ্": 150, "▁ব্য": 151, "▁তিনি": 152, "▁পরি": 153, "াপ": 154, "ানে": 155, "▁হয়েছে": 156, "▁জন্য": 157, "▁দু": 158, "▁কি": 159, "▁নিয়ে": 160, "দেশ": 161, "▁কার": 162, "ছিল": 163, "▁▁": 164, "া": 165, "ে": 166, "র": 167, "্": 168, "ি": 169, "ন": 170, "ক": 171, "য": 172, "ব": 173, "ত": 174, "স": 175, "ম": 176, "ল": 177, "়": 178, "প": 179, "দ": 180, "ু": 181, "হ": 182, "ট": 183, "জ": 184, "ো": 185, "শ": 186, "গ": 187, "ছ": 188, "এ": 189, "ই": 190, "আ": 191, "ী": 192, "চ": 193, "থ": 194, "ড": 195, "ও": 196, "ভ": 197, "ষ": 198, "ধ": 199, "খ": 200, "অ": 201, "ং": 202, "উ": 203, "ণ": 204, "ফ": 205, "ঠ": 206, "১": 207, "ৃ": 208, "ঁ": 209, "ূ": 210, "ঘ": 211, "ঙ": 212, "২": 213, "০": 214, "ঞ": 215, "৫": 216, "ৈ": 217, "৩": 218, "ৌ": 219, "৯": 220, "৪": 221, "ৎ": 222, "৬": 223, "ঝ": 224, "৮": 225, "৭": 226, "ঢ": 227, "ঃ": 228, "ঐ": 229, "ঈ": 230, "৷": 231, "ঋ": 232, "ঊ": 233, "ঔ": 234, "ৰ": 235, "ৗ": 236, "ৱ": 237, "": 238, "৳": 239, "": 240, "": 241, "": 242, "": 243, "ঌ": 244, "": 245, "ৄ": 246, "ৠ": 247, "": 248, "ঽ": 249, "৴": 250, "৻": 251, "ৡ": 252, "৲": 253, "": 254, "৵": 255, "▁": 256, "<pad>": 257}, "ml": {"<unk>": 0, "ന്": 1, "ക്": 2, "ത്": 3, "▁പ": 4, "ന്ന": 5, "ക്ക": 6, "തി": 7, "▁ക": 8, "്ട": 9, "ും": 10, "▁സ": 11, "▁വ": 12, "യി": 13, "▁അ": 14, "▁മ": 15, "▁ന": 16, "ുന്ന": 17, "ച്": 18, "്പ": 19, "ങ്": 20, "്ര": 21, "്യ": 22, "ാണ": 23, "▁എ": 24, "ത്തി": 25, "രി": 26, "ട്ട": 27, "ത്ത": 28, "പ്പ": 29, "ങ്ങ": 30, "സ്": 31, "ില": 32, "റ്": 33, "ിയ": 34, "ച്ച": 35, "മാ": 36, "ാണ്": 37, "▁ത": 38, "ണ്ട": 39, "▁ഇ": 40, "ുക": 41, "ടെ": 42, "▁ച": 43, "▁ആ": 44, "രു": 45, "്ല": 46, "ിക്ക": 47, "▁പ്ര": 48, "റ്റ": 49, "▁വി": 50, "ിൽ": 51, "ുന്നു": 52, "ാന": 53, "ായി": 54, "്ള": 55, "ള്ള": 56, "റെ": 57, "ഞ്": 58, "ിച്ച": 59, "ാര": 60, "▁ര": 61, "▁ഒ": 62, "▁ജ": 63, "▁ഉ": 64, "െയ": 65, "▁ബ": 66, "ിക": 67, "ക്ക്": 68, "ുടെ": 69, "ടു": 70, "▁നി": 71, "ന്റെ": 72, "ന്ന്": 73, "ായ": 74, "ങ്ങള": 75, "ക്ഷ": 76, "വി": 77, "ല്ല": 78, "ുള്ള": 79, "ത്ര": 80, "▁സ്": 81, "▁ശ": 82, "ദ്": 83, "ഞ്ഞ": 84, "▁പി": 85, "റി": 86, "ാൻ": 87, "ുമ": 88, "െന്ന": 89, "ങ്ങൾ": 90, "▁എന്ന": 91, "ാല": 92, "രുന്നു": 93, "യും": 94, "ിന": 95, "രിക്ക": 96, "▁സം": 97, "മായി": 98, "ടി": 99, "പ്പെ": 100, "ാർ": 101, "ണ്ട്": 102, "▁കു": 103, "▁ല": 104, "യിൽ": 105, "▁ഒരു": 106, "ില്ല": 107, "ങ്ക": 108, "ാവ": 109, "ദേ": 110, "▁ചെയ": 111, "ുന്നത്": 112, "്മ": 113, "യില": 114, "ത്തിൽ": 115, "▁മു": 116, "▁മാ": 117, "വർ": 118, "ണം": 119, "▁ഭ": 120, "ാക്ക": 121, "▁നട": 122, "തു": 123, "▁യ": 124, "ോഗ": 125, "േഷ": 126, "മായ": 127, "ിവ": 128, "ാം": 129, "▁പറ": 130, "മ്മ": 131, "▁ഗ": 132, "▁പോ": 133, "▁ഡ": 134, "ാമ": 135, "ത്തില": 136, "ുവ": 137, "തിന": 138, "ത്യ": 139, "▁ദ": 140, "വും": 141, "▁പു": 142, "ത്ത്": 143, "സി": 144, "ച്ച്": 145, "▁കോ": 146, "െന്ന്": 147, "ത്തെ": 148, "▁സി": 149, "▁കൊ": 150, "വാ": 151, "ുകള": 152, "▁അവ": 153, "രെ": 154, "ാൽ": 155, "▁ഈ": 156, "▁കേ": 157, "സ്ഥ": 158, "ദ്യ": 159, "▁തു": 160, "ന്ത": 161, "യാണ്": 162, "▁ഫ": 163, "ായിരുന്നു": 164, "്": 165, "▁▁": 166, "ി": 167, "ക": 168, "ന": 169, "ു": 170, "ത": 171, "ാ": 172, "യ": 173, "ര": 174, "ട": 175, "പ": 176, "െ": 177, "മ": 178, "വ": 179, "ം": 180, "ല": 181, "സ": 182, "റ": 183, "ച": 184, "ണ": 185, "ള": 186, "ോ": 187, "ങ": 188, "േ": 189, "ർ": 190, "ൽ": 191, "അ": 192, "ദ": 193, "ീ": 194, "എ": 195, "ഷ": 196, "ശ": 197, "ജ": 198, "ൻ": 199, "ഗ": 200, "ൾ": 201, "ധ": 202, "ഞ": 203, "ൂ": 204, "ഇ": 205, "ബ": 206, "ആ": 207, "ഹ": 208, "ൊ": 209, "ഭ": 210, "ഡ": 211, "ഴ": 212, "ഒ": 213, "ഉ": 214, "ഥ": 215, "ൈ": 216, "ഫ": 217, "ൃ": 218, "ഖ": 219, "ഈ": 220, "ഏ": 221, "ഘ": 222, "ൺ": 223, "ഓ": 224, "ൗ": 225, "ഐ": 226, "ഠ": 227, "ഛ": 228, "ഊ": 229, "ഔ": 230, "ൌ": 231, "ഃ": 232, "ഢ": 233, "ഋ": 234, "൪": 235, "ഝ": 236, "൯": 237, "൦": 238, "ഌ": 239, "ൿ": 240, "഼": 241, "ൎ": 242, "ൡ": 243, "൧": 244, "൨": 245, "൫": 246, "൬": 247, "൩": 248, "൭": 249, "ഽ": 250, "൮": 251, "ഺ": 252, "ൟ": 253, "ഩ": 254, "ൠ": 255, "▁": 256, "<pad>": 257}, "hi": {"<unk>": 0, "▁क": 1, "▁स": 2, "▁ह": 3, "▁म": 4, "▁प": 5, "ार": 6, "ने": 7, "ें": 8, "▁ब": 9, "▁के": 10, "्र": 11, "▁है": 12, "▁ज": 13, "या": 14, "▁द": 15, "▁र": 16, "▁में": 17, "▁व": 18, "▁ल": 19, "ों": 20, "▁अ": 21, "▁की": 22, "▁न": 23, "▁को": 24, "▁ग": 25, "ान": 26, "▁आ": 27, "र्": 28, "▁कि": 29, "ता": 30, "▁इ": 31, "▁से": 32, "▁भ": 33, "▁उ": 34, "▁का": 35, "▁कर": 36, "▁त": 37, "ना": 38, "्य": 39, "▁ने": 40, "▁पर": 41, "िक": 42, "ला": 43, "▁श": 44, "▁इस": 45, "▁च": 46, "▁औ": 47, "ही": 48, "▁प्र": 49, "▁और": 50, "स्": 51, "ाल": 52, "▁ए": 53, "क्": 54, "▁हो": 55, "हा": 56, "ड़": 57, "▁जा": 58, "▁हैं": 59, "▁य": 60, "▁थ": 61, "ित": 62, "▁भी": 63, "िया": 64, "ाम": 65, "वा": 66, "िल": 67, "िए": 68, "के": 69, "▁ख": 70, "िय": 71, "ते": 72, "▁बा": 73, "ंग": 74, "हीं": 75, "▁फ": 76, "▁वि": 77, "▁स्": 78, "ेश": 79, "त्र": 80, "▁उन": 81, "कर": 82, "ती": 83, "री": 84, "ले": 85, "िन": 86, "से": 87, "▁सा": 88, "▁नहीं": 89, "▁रा": 90, "रा": 91, "ारी": 92, "▁लिए": 93, "िस": 94, "▁एक": 95, "▁सं": 96, "गा": 97, "्या": 98, "▁ले": 99, "नी": 100, "ुर": 101, "सी": 102, "ोग": 103, "▁सम": 104, "▁ट": 105, "▁ही": 106, "ति": 107, "▁दे": 108, "▁रह": 109, "▁अप": 110, "▁हु": 111, "▁ड": 112, "का": 113, "▁किया": 114, "क्ष": 115, "ंद": 116, "वार": 117, "▁मु": 118, "ुल": 119, "▁कार": 120, "ाय": 121, "▁गया": 122, "▁नि": 123, "ली": 124, "त्": 125, "ियों": 126, "▁पह": 127, "ां": 128, "की": 129, "िला": 130, "्ह": 131, "्ट": 132, "▁था": 133, "▁घ": 134, "▁तो": 135, "▁करने": 136, "ास": 137, "ंच": 138, "कार": 139, "▁कहा": 140, "▁कु": 141, "▁सि": 142, "▁बाद": 143, "मा": 144, "▁साथ": 145, "▁यह": 146, "▁उन्ह": 147, "▁रहे": 148, "रो": 149, "▁अध": 150, "्म": 151, "▁लोग": 152, "▁पू": 153, "गी": 154, "ाह": 155, "भा": 156, "ंड": 157, "▁दिया": 158, "▁सु": 159, "▁उस": 160, "▁▁": 161, "ा": 162, "क": 163, "र": 164, "े": 165, "न": 166, "ी": 167, "्": 168, "स": 169, "ि": 170, "ं": 171, "ह": 172, "म": 173, "त": 174, "ल": 175, "ो": 176, "प": 177, "य": 178, "व": 179, "द": 180, "ज": 181, "ब": 182, "ग": 183, "ु": 184, "ै": 185, "श": 186, "ट": 187, "ए": 188, "च": 189, "भ": 190, "ड": 191, "अ": 192, "ू": 193, "इ": 194, "आ": 195, "थ": 196, "ख": 197, "ध": 198, "उ": 199, "फ": 200, "़": 201, "ई": 202, "ष": 203, "औ": 204, "ण": 205, "ौ": 206, "छ": 207, "घ": 208, "ॉ": 209, "ठ": 210, "ओ": 211, "ढ": 212, "ृ": 213, "झ": 214, "ऐ": 215, "ऑ": 216, "ँ": 217, "ञ": 218, "ऊ": 219, "ः": 220, "ऋ": 221, "ॅ": 222, "१": 223, "०": 224, "२": 225, "ऩ": 226, "५": 227, "९": 228, "३": 229, "८": 230, "४": 231, "७": 232, "६": 233, "ऱ": 234, "ङ": 235, "ऎ": 236, "॰": 237, "ळ": 238, "ऍ": 239, "ॐ": 240, "ॢ": 241, "ऽ": 242, "ॆ": 243, "॒": 244, "ॊ": 245, "ॠ": 246, "ॄ": 247, "ऒ": 248, "॑": 249, "॔": 250, "ॽ": 251, "ऌ": 252, "ऴ": 253, "ऺ": 254, "ऻ": 255, "▁": 256, "<pad>": 257}, "doi": {"<unk>": 0, "▁क": 1, "▁द": 2, "▁स": 3, "▁प": 4, "▁ब": 5, "▁ज": 6, "▁म": 7, "▁ह": 8, "▁न": 9, "ें": 10, "▁ग": 11, "▁त": 12, "ार": 13, "▁च": 14, "ां": 15, "▁अ": 16, "ह्": 17, "▁ल": 18, "▁आ": 19, "ान": 20, "▁दे": 21, "िय": 22, "्र": 23, "▁र": 24, "▁कर": 25, "▁ऐ": 26, "ने": 27, "▁इ": 28, "ना": 29, "दा": 30, "▁दी": 31, "क्": 32, "▁उ": 33, "्त": 34, "▁ते": 35, "▁हो": 36, "दे": 37, "न्": 38, "ेई": 39, "▁भ": 40, "्य": 41, "ड़": 42, "▁दा": 43, "ता": 44, "▁पर": 45, "▁ख": 46, "▁गी": 47, "री": 48, "▁श": 49, "दी": 50, "न्न": 51, "र्": 52, "▁बी": 53, "▁व": 54, "ित": 55, "ाल": 56, "▁ए": 57, "▁फ": 58, "▁प्र": 59, "क्ख": 60, "िक": 61, "न्नै": 62, "▁नेई": 63, "▁कन्नै": 64, "▁को": 65, "▁इस": 66, "▁जा": 67, "ास": 68, "▁ओ": 69, "रा": 70, "▁अप": 71, "्ह": 72, "▁की": 73, "नी": 74, "▁ऎ": 75, "्ल": 76, "▁जे": 77, "ंग": 78, "ेआ": 79, "िस": 80, "▁ड": 81, "ती": 82, "▁गै": 83, "ाई": 84, "ाह": 85, "▁कु": 86, "▁दि": 87, "▁सम": 88, "ियां": 89, "▁थ": 90, "गी": 91, "▁के": 92, "▁में": 93, "रे": 94, "ंद": 95, "ारी": 96, "▁नेईं": 97, "्ट": 98, "▁नि": 99, "▁उस": 100, "ैं": 101, "ाम": 102, "ली": 103, "्थ": 104, "स्त": 105, "▁एह्": 106, "्प": 107, "ला": 108, "ियै": 109, "▁घ": 110, "ल्ल": 111, "ों": 112, "▁छ": 113, "्म": 114, "▁सु": 115, "▁इक": 116, "▁ओह्": 117, "▁उप": 118, "ले": 119, "िया": 120, "या": 121, "▁कि": 122, "▁मु": 123, "च्": 124, "▁सक": 125, "ाज": 126, "ंदा": 127, "ात": 128, "▁मे": 129, "▁मि": 130, "▁से": 131, "▁ध": 132, "▁जो": 133, "ति": 134, "▁लेई": 135, "कर": 136, "त्त": 137, "▁औ": 138, "की": 139, "्स": 140, "▁य": 141, "के": 142, "ानी": 143, "ियें": 144, "द्": 145, "क्ष": 146, "▁करने": 147, "ज्": 148, "▁जिस": 149, "ाने": 150, "ड़ी": 151, "ते": 152, "ंदे": 153, "ोग": 154, "ब्": 155, "वि": 156, "वा": 157, "▁सं": 158, "▁कोई": 159, "ही": 160, "▁सा": 161, "▁है": 162, "ूं": 163, "▁ने": 164, "▁अपने": 165, "ंदी": 166, "▁सू": 167, "्ही": 168, "▁तु": 169, "▁होई": 170, "▁दु": 171, "एं": 172, "का": 173, "ित्त": 174, "▁लग": 175, "▁कार": 176, "िर": 177, "जना": 178, "इय": 179, "▁ही": 180, "▁▁": 181, "ा": 182, "े": 183, "र": 184, "्": 185, "न": 186, "ी": 187, "क": 188, "द": 189, "ं": 190, "स": 191, "त": 192, "ि": 193, "ह": 194, "ल": 195, "म": 196, "प": 197, "ज": 198, "ग": 199, "ो": 200, "ै": 201, "ब": 202, "य": 203, "च": 204, "ु": 205, "आ": 206, "ई": 207, "ड": 208, "व": 209, "श": 210, "ख": 211, "ू": 212, "अ": 213, "इ": 214, "ट": 215, "भ": 216, "ऐ": 217, "़": 218, "ए": 219, "ध": 220, "उ": 221, "थ": 222, "फ": 223, "ँ": 224, "ौ": 225, "ओ": 226, "छ": 227, "ऎ": 228, "घ": 229, "ढ": 230, "ष": 231, "ठ": 232, "झ": 233, "ण": 234, "औ": 235, "ऽ": 236, "ृ": 237, "१": 238, "ऊ": 239, "ञ": 240, "ऱ": 241, "ङ": 242, "ॉ": 243, "ः": 244, "॰": 245, "ऋ": 246, "ऑ": 247, "ळ": 248, "ऻ": 249, "ॅ": 250, "ॎ": 251, "०": 252, "२": 253, "३": 254, "८": 255, "▁": 256, "<pad>": 257}, "ur": {"<unk>": 0, "▁ک": 1, "▁ا": 2, "▁م": 3, "▁ہ": 4, "یں": 5, "▁ب": 6, "▁س": 7, "▁ن": 8, "▁ت": 9, "ور": 10, "▁کی": 11, "▁پ": 12, "▁کے": 13, "▁ج": 14, "ان": 15, "▁د": 16, "ار": 17, "▁و": 18, "▁میں": 19, "▁ہے": 20, "یا": 21, "وں": 22, "▁اور": 23, "▁کر": 24, "▁ر": 25, "▁ل": 26, "▁اس": 27, "▁سے": 28, "ال": 29, "▁گ": 30, "▁کا": 31, "▁کو": 32, "ات": 33, "ائ": 34, "▁کہ": 35, "▁ہو": 36, "▁آ": 37, "یک": 38, "ام": 39, "▁ع": 40, "▁ان": 41, "ھی": 42, "▁ح": 43, "نے": 44, "▁خ": 45, "▁پر": 46, "ری": 47, "▁نے": 48, "▁ش": 49, "یہ": 50, "ین": 51, "▁چ": 52, "▁ہیں": 53, "▁ف": 54, "▁نہ": 55, "▁ق": 56, "یر": 57, "اہ": 58, "ئے": 59, "لا": 60, "لی": 61, "▁یہ": 62, "▁بھی": 63, "▁تھ": 64, "تا": 65, "نا": 66, "تے": 67, "ست": 68, "ئی": 69, "اد": 70, "اب": 71, "▁ص": 72, "▁ایک": 73, "▁ط": 74, "تی": 75, "▁ال": 76, "▁نہیں": 77, "▁تو": 78, "▁وہ": 79, "▁رہ": 80, "ون": 81, "ند": 82, "▁اپ": 83, "اک": 84, "سی": 85, "▁ز": 86, "▁کیا": 87, "می": 88, "لہ": 89, "نی": 90, "▁جو": 91, "ید": 92, "▁ای": 93, "ول": 94, "ائی": 95, "▁،": 96, "ود": 97, "▁تھا": 98, "▁لی": 99, "از": 100, "اری": 101, "▁ہم": 102, "گر": 103, "ائے": 104, "ٹی": 105, "وم": 106, "▁دی": 107, "▁ڈ": 108, "▁▁": 109, "ا": 110, "ی": 111, "ک": 112, "ر": 113, "و": 114, "ہ": 115, "ن": 116, "ے": 117, "م": 118, "ت": 119, "س": 120, "ل": 121, "ب": 122, "د": 123, "ں": 124, "ھ": 125, "ج": 126, "پ": 127, "ع": 128, "گ": 129, "ئ": 130, "ق": 131, "ف": 132, "ش": 133, "ح": 134, "ز": 135, "ٹ": 136, "خ": 137, "چ": 138, "ص": 139, "،": 140, "آ": 141, "ط": 142, "ڈ": 143, "ض": 144, "ڑ": 145, "ظ": 146, "غ": 147, "ذ": 148, "ث": 149, "ِ": 150, "ُ": 151, "ؤ": 152, "ي": 153, "ٰ": 154, "ء": 155, "؟": 156, "َ": 157, "ك": 158, "ّ": 159, "ً": 160, "ه": 161, "ـ": 162, "ۃ": 163, "ى": 164, "ْ": 165, "ؓ": 166, "ۂ": 167, "ؒ": 168, "ژ": 169, "؛": 170, "ؐ": 171, "ؔ": 172, "٭": 173, "ۓ": 174, "أ": 175, "ؑ": 176, "ٴ": 177, "ة": 178, "١": 179, "ٗ": 180, "ٔ": 181, "٢": 182, "إ": 183, "٠": 184, "٣": 185, "ٖ": 186, "٤": 187, "٥": 188, "؎": 189, "٩": 190, "ٍ": 191, "ٓ": 192, "٨": 193, "٦": 194, "٧": 195, "ٌ": 196, "؍": 197, "ۆ": 198, "٬": 199, "ٲ": 200, "٫": 201, "ێ": 202, "ٕ": 203, "ۍ": 204, "٘": 205, "ۀ": 206, "ٙ": 207, "٪": 208, "ڪ": 209, "ڻ": 210, "ې": 211, "ړ": 212, "ە": 213, "ٮ": 214, "ٱ": 215, "ٛ": 216, "ۅ": 217, "ٚ": 218, "ښ": 219, "؞": 220, "ڄ": 221, "ۏ": 222, "څ": 223, "ڳ": 224, "ؕ": 225, "ٽ": 226, "ڊ": 227, "ڙ": 228, "ٻ": 229, "ځ": 230, "ڃ": 231, "ږ": 232, "ڷ": 233, "؏": 234, "ٟ": 235, "ڽ": 236, "ۇ": 237, "ٞ": 238, "ګ": 239, "ڼ": 240, "ټ": 241, "ډ": 242, "ڦ": 243, "ٿ": 244, "ڋ": 245, "ڌ": 246, "ڍ": 247, "ڎ": 248, "ڏ": 249, "ڥ": 250, "ۉ": 251, "ۑ": 252, "ؠ": 253, "ٝ": 254, "ٺ": 255, "▁": 256, "<pad>": 257}, "mr": {"<unk>": 0, "या": 1, "्या": 2, "▁क": 3, "▁आ": 4, "▁प": 5, "▁स": 6, "▁म": 7, "ार": 8, "्र": 9, "▁त": 10, "▁अ": 11, "ला": 12, "▁व": 13, "▁ह": 14, "ना": 15, "ात": 16, "▁द": 17, "हे": 18, "र्": 19, "▁या": 20, "▁आहे": 21, "ले": 22, "ां": 23, "्य": 24, "च्या": 25, "▁ज": 26, "▁न": 27, "ही": 28, "▁र": 29, "ली": 30, "ती": 31, "ून": 32, "▁ब": 33, "ल्या": 34, "▁त्या": 35, "चा": 36, "ने": 37, "िक": 38, "▁अस": 39, "▁श": 40, "▁कर": 41, "वा": 42, "ता": 43, "ची": 44, "ण्या": 45, "चे": 46, "▁प्र": 47, "▁ग": 48, "क्": 49, "▁हो": 50, "नी": 51, "▁का": 52, "्ह": 53, "▁के": 54, "वर": 55, "स्": 56, "ंत": 57, "सा": 58, "▁भ": 59, "▁आण": 60, "▁घ": 61, "ाज": 62, "▁उ": 63, "ते": 64, "▁आणि": 65, "▁वि": 66, "▁ना": 67, "ित": 68, "ाव": 69, "▁ए": 70, "▁यां": 71, "ेत": 72, "▁य": 73, "ंद": 74, "ील": 75, "▁दि": 76, "ान": 77, "▁झ": 78, "ध्य": 79, "▁ल": 80, "ठी": 81, "त्": 82, "▁पा": 83, "क्ष": 84, "▁नि": 85, "▁च": 86, "का": 87, "▁सं": 88, "▁झा": 89, "▁ख": 90, "री": 91, "▁वा": 92, "▁मा": 93, "णा": 94, "्ट": 95, "ळे": 96, "ास": 97, "साठी": 98, "▁फ": 99, "▁सु": 100, "मु": 101, "हि": 102, "कार": 103, "ध्ये": 104, "▁त्यां": 105, "▁दे": 106, "▁मु": 107, "▁स्": 108, "णार": 109, "मा": 110, "णी": 111, "रा": 112, "▁ला": 113, "▁को": 114, "ण्यात": 115, "▁नाही": 116, "मध्ये": 117, "रो": 118, "्यां": 119, "ाय": 120, "▁ट": 121, "▁आहेत": 122, "शी": 123, "कर": 124, "मुळे": 125, "ंग": 126, "णे": 127, "▁म्ह": 128, "▁जा": 129, "▁हे": 130, "▁रा": 131, "्री": 132, "▁ठ": 133, "▁एक": 134, "लं": 135, "▁ते": 136, "वि": 137, "वे": 138, "द्": 139, "▁इ": 140, "ष्ट": 141, "डे": 142, "▁पर": 143, "▁सा": 144, "से": 145, "▁आप": 146, "ळी": 147, "▁तर": 148, "▁पु": 149, "▁यांनी": 150, "▁राज": 151, "ारी": 152, "ल्": 153, "▁ये": 154, "▁मह": 155, "र्व": 156, "्हा": 157, "▁कार": 158, "▁मि": 159, "▁मो": 160, "▁▁": 161, "ा": 162, "्": 163, "र": 164, "े": 165, "त": 166, "य": 167, "ी": 168, "क": 169, "ल": 170, "न": 171, "स": 172, "व": 173, "ि": 174, "ह": 175, "ं": 176, "म": 177, "च": 178, "प": 179, "ण": 180, "ो": 181, "द": 182, "आ": 183, "ु": 184, "ज": 185, "ग": 186, "श": 187, "अ": 188, "ट": 189, "ू": 190, "ब": 191, "ड": 192, "ध": 193, "ळ": 194, "ष": 195, "भ": 196, "ख": 197, "ठ": 198, "घ": 199, "थ": 200, "उ": 201, "झ": 202, "ए": 203, "फ": 204, "ई": 205, "ढ": 206, "ॉ": 207, "इ": 208, "ृ": 209, "ै": 210, "ऊ": 211, "१": 212, "ऱ": 213, "०": 214, "ॅ": 215, "२": 216, "ौ": 217, "ँ": 218, "ओ": 219, "५": 220, "छ": 221, "३": 222, "४": 223, "९": 224, "ऑ": 225, "६": 226, "८": 227, "७": 228, "ञ": 229, "ः": 230, "़": 231, "ऐ": 232, "औ": 233, "ऋ": 234, "ऍ": 235, "ॲ": 236, "ङ": 237, "ऽ": 238, "ॆ": 239, "ॊ": 240, "ॄ": 241, "ॐ": 242, "ऴ": 243, "ॕ": 244, "ऩ": 245, "ऎ": 246, "ॠ": 247, "॑": 248, "ऒ": 249, "॰": 250, "॓": 251, "॔": 252, "ॽ": 253, "ऌ": 254, "ऺ": 255, "▁": 256, "<pad>": 257}, "gu": {"<unk>": 0, "▁ક": 1, "મા": 2, "▁પ": 3, "▁સ": 4, "વા": 5, "ને": 6, "ના": 7, "▁ત": 8, "્ય": 9, "▁આ": 10, "▁છ": 11, "▁જ": 12, "માં": 13, "▁અ": 14, "્ર": 15, "ાર": 16, "▁છે": 17, "▁હ": 18, "ની": 19, "▁મ": 20, "▁ર": 21, "▁વ": 22, "▁બ": 23, "ું": 24, "▁કર": 25, "તા": 26, "▁તે": 27, "▁દ": 28, "ર્": 29, "▁ન": 30, "લા": 31, "▁એ": 32, "▁શ": 33, "થી": 34, "▁અને": 35, "▁મા": 36, "▁ગ": 37, "▁કે": 38, "▁લ": 39, "રા": 40, "્ટ": 41, "્યા": 42, "નો": 43, "▁આવ": 44, "રી": 45, "▁હત": 46, "યા": 47, "▁પ્ર": 48, "▁સા": 49, "▁થ": 50, "▁ભ": 51, "ટે": 52, "િક": 53, "▁પર": 54, "▁ચ": 55, "▁ખ": 56, "હે": 57, "સ્": 58, "▁વિ": 59, "▁ફ": 60, "▁ઉ": 61, "લી": 62, "ક્": 63, "ન્": 64, "ાય": 65, "ાવ": 66, "▁કો": 67, "▁પણ": 68, "મે": 69, "▁જે": 70, "ંગ": 71, "કો": 72, "▁માટે": 73, "▁રા": 74, "ંત": 75, "વામાં": 76, "નું": 77, "શે": 78, "િત": 79, "▁કરી": 80, "▁એક": 81, "વી": 82, "▁પા": 83, "રો": 84, "▁જો": 85, "▁હો": 86, "▁સ્": 87, "્યો": 88, "રે": 89, "હી": 90, "યો": 91, "્યું": 92, "▁પો": 93, "લ્": 94, "કે": 95, "િયા": 96, "કા": 97, "ણી": 98, "▁વા": 99, "ડી": 100, "▁તેમ": 101, "ારે": 102, "▁ટ": 103, "▁આપ": 104, "ામ": 105, "તી": 106, "થે": 107, "▁ઘ": 108, "ેશ": 109, "▁બા": 110, "▁સં": 111, "ત્": 112, "▁કાર": 113, "▁મો": 114, "▁સાથે": 115, "▁ધ": 116, "ાન": 117, "લે": 118, "▁હતી": 119, "▁ડ": 120, "કાર": 121, "▁સુ": 122, "ણે": 123, "▁લો": 124, "▁ના": 125, "તિ": 126, "્રી": 127, "▁સમ": 128, "▁લા": 129, "ભા": 130, "▁વધ": 131, "જી": 132, "વે": 133, "ડા": 134, "તે": 135, "ંધ": 136, "▁મુ": 137, "▁તો": 138, "▁બે": 139, "ક્ષ": 140, "ાલ": 141, "▁રહ": 142, "ટી": 143, "▁જા": 144, "ંદ": 145, "સે": 146, "▁મળ": 147, "▁કરવા": 148, "ત્ર": 149, "ારી": 150, "▁હતા": 151, "▁ઓ": 152, "ાસ": 153, "િવ": 154, "▁હતો": 155, "▁ઉપ": 156, "રૂ": 157, "સા": 158, "▁નિ": 159, "કી": 160, "▁નથી": 161, "્યારે": 162, "▁મહ": 163, "દી": 164, "▁આવે": 165, "▁તમા": 166, "▁આવી": 167, "તો": 168, "જા": 169, "સ્ટ": 170, "સી": 171, "▁▁": 172, "ા": 173, "ે": 174, "ર": 175, "ન": 176, "ી": 177, "્": 178, "ક": 179, "મ": 180, "ત": 181, "વ": 182, "ો": 183, "ં": 184, "સ": 185, "પ": 186, "ય": 187, "િ": 188, "લ": 189, "જ": 190, "ુ": 191, "હ": 192, "ટ": 193, "દ": 194, "ગ": 195, "છ": 196, "આ": 197, "થ": 198, "બ": 199, "શ": 200, "અ": 201, "ણ": 202, "ડ": 203, "ધ": 204, "એ": 205, "ચ": 206, "ખ": 207, "ભ": 208, "ૂ": 209, "ળ": 210, "ફ": 211, "ઈ": 212, "ઓ": 213, "ષ": 214, "ઇ": 215, "ઉ": 216, "ઘ": 217, "ઝ": 218, "ઠ": 219, "૦": 220, "૧": 221, "ૃ": 222, "ૈ": 223, "૨": 224, "ૌ": 225, "ઢ": 226, "૫": 227, "૩": 228, "૪": 229, "૬": 230, "૯": 231, "૮": 232, "૭": 233, "ૉ": 234, "ઃ": 235, "ઊ": 236, "ઞ": 237, "ૅ": 238, "ઑ": 239, "ઔ": 240, "ઋ": 241, "ઐ": 242, "ઍ": 243, "ઙ": 244, "ઁ": 245, "઼": 246, "ૐ": 247, "ૠ": 248, "ૢ": 249, "ૄ": 250, "ઽ": 251, "": 252, "": 253, "૱": 254, "": 255, "▁": 256, "<pad>": 257}, "kn": {"<unk>": 0, "▁ಮ": 1, "▁ಸ": 2, "ತ್": 3, "ಲ್": 4, "▁ಕ": 5, "ಿದ": 6, "ಾರ": 7, "ಲ್ಲ": 8, "▁ನ": 9, "ನ್": 10, "▁ಅ": 11, "ಂದ": 12, "ಾಗ": 13, "ರು": 14, "ತ್ತ": 15, "▁ಪ": 16, "▁ಹ": 17, "ನ್ನ": 18, "್ರ": 19, "ಿಸ": 20, "▁ಬ": 21, "ಗಳ": 22, "್ಯ": 23, "ಕ್": 24, "▁ವ": 25, "ಗೆ": 26, "್ದ": 27, "ಲ್ಲಿ": 28, "ರ್": 29, "ನ್ನು": 30, "ರಿ": 31, "▁ಆ": 32, "▁ತ": 33, "ೆಯ": 34, "▁ಇ": 35, "▁ಎ": 36, "ಿದ್ದ": 37, "ಿಯ": 38, "ುವ": 39, "ಿಕ": 40, "್ಟ": 41, "▁ಮಾ": 42, "ುತ್ತ": 43, "ಸ್": 44, "ದು": 45, "▁ಪ್ರ": 46, "▁ರ": 47, "▁ಜ": 48, "ಾಗಿ": 49, "ಿದೆ": 50, "ಂತ": 51, "ಕ್ಕ": 52, "▁ದ": 53, "ಿನ": 54, "ಂದು": 55, "ವು": 56, "ರೆ": 57, "▁ಗ": 58, "▁ಶ": 59, "ಾನ": 60, "ತ್ತು": 61, "ಂಡ": 62, "▁ವಿ": 63, "▁ನಿ": 64, "ಾಯ": 65, "▁ಮಾಡ": 66, "ಾದ": 67, "ತಿ": 68, "▁ಈ": 69, "ದಲ್ಲಿ": 70, "ಲು": 71, "ಗಳು": 72, "ಿಗೆ": 73, "▁ಅವ": 74, "ಟ್ಟ": 75, "ಾರೆ": 76, "ಕ್ಷ": 77, "▁ಉ": 78, "್ಮ": 79, "▁ನೀ": 80, "▁ಚ": 81, "ದೆ": 82, "▁ಸಂ": 83, "▁ಒ": 84, "ಿಂದ": 85, "ಿತ": 86, "ಾಲ": 87, "▁ಮತ್ತು": 88, "▁ಭ": 89, "▁ಯ": 90, "ಾಮ": 91, "ಕ್ಕೆ": 92, "ೇಕ": 93, "ತ್ರ": 94, "▁ಮು": 95, "ಾವ": 96, "ನೆ": 97, "ಿಲ್ಲ": 98, "▁ಸ್": 99, "ಿದ್ದಾರೆ": 100, "ಮ್ಮ": 101, "ಡಿ": 102, "ೊಳ": 103, "ಗಳನ್ನು": 104, "ಂಬ": 105, "್ಳ": 106, "ಡೆ": 107, "ಷ್ಟ": 108, "ರುವ": 109, "ಚ್": 110, "ವಾಗಿ": 111, "▁ಎಂದು": 112, "ಾಜ": 113, "ೇಶ": 114, "ಂಗ": 115, "ವನ್ನು": 116, "ುದ": 117, "ಿವ": 118, "ಾಗಿದೆ": 119, "ಪ್": 120, "▁ಕೆ": 121, "ುದು": 122, "▁ಕಾರ": 123, "ರಿಸ": 124, "ಬೇಕ": 125, "ಚ್ಚ": 126, "ೊಂಡ": 127, "ಾಸ": 128, "ೇಳ": 129, "ಾರಿ": 130, "▁ಹೆ": 131, "▁ಆದ": 132, "ಿದರು": 133, "▁ಇದ": 134, "ತೆ": 135, "▁ಹೊ": 136, "ಲೆ": 137, "▁ಸಮ": 138, "▁ಬೆ": 139, "ನಾ": 140, "ುತ್ತದೆ": 141, "ೋಗ": 142, "ೊಳ್ಳ": 143, "ಾಣ": 144, "ಧ್ಯ": 145, "ಾರ್": 146, "▁ನೀಡ": 147, "ಿಸಿ": 148, "▁ಬಿ": 149, "ವೆ": 150, "ನು": 151, "▁ಸಾ": 152, "ರಿಗೆ": 153, "ತ್ಯ": 154, "▁ಕು": 155, "ಪ್ಪ": 156, "ವಿ": 157, "ಂತೆ": 158, "ಕಾರ": 159, "▁ಹಾಗ": 160, "▁ಮೂ": 161, "ಡ್": 162, "ರಣ": 163, "▁ಲ": 164, "ೆಯಲ್ಲಿ": 165, "ಬ್": 166, "ಗ್": 167, "▁ಸಿ": 168, "್ಣ": 169, "ವಾ": 170, "▁ತಿ": 171, "ಟ್": 172, "▁▁": 173, "್": 174, "ಿ": 175, "ರ": 176, "ು": 177, "ದ": 178, "ಾ": 179, "ನ": 180, "ೆ": 181, "ತ": 182, "ಕ": 183, "ಲ": 184, "ಗ": 185, "ವ": 186, "ಸ": 187, "ಯ": 188, "ಮ": 189, "ಂ": 190, "ಳ": 191, "ಪ": 192, "ಡ": 193, "ಬ": 194, "ಹ": 195, "ೇ": 196, "ಟ": 197, "ಅ": 198, "ೂ": 199, "ೊ": 200, "ೀ": 201, "ಜ": 202, "ಚ": 203, "ಣ": 204, "ಶ": 205, "ೋ": 206, "ಷ": 207, "ಆ": 208, "ಧ": 209, "ಎ": 210, "ಇ": 211, "ಭ": 212, "ಥ": 213, "ೈ": 214, "ಈ": 215, "ಖ": 216, "ಉ": 217, "ಒ": 218, "ೃ": 219, "ಫ": 220, "ೌ": 221, "ಘ": 222, "ಠ": 223, "ಏ": 224, "ಐ": 225, "ಞ": 226, "ಓ": 227, "ಛ": 228, "೦": 229, "ಊ": 230, "ಃ": 231, "ಢ": 232, "ೕ": 233, "ಔ": 234, "೧": 235, "ಝ": 236, "೨": 237, "೯": 238, "ಋ": 239, "೫": 240, "೩": 241, "೮": 242, "೪": 243, "೬": 244, "೭": 245, "಼": 246, "ಙ": 247, "ಱ": 248, "ೖ": 249, "ಽ": 250, "ೞ": 251, "ೄ": 252, "": 253, "ಌ": 254, "ೠ": 255, "▁": 256, "<pad>": 257}, "mni": {"<unk>": 0, "ꯁꯤ": 1, "▁ꯃ": 2, "▁ꯑ": 3, "ꯁꯤꯡ": 4, "▁ꯃꯁꯤꯡ": 5, "ꯅꯤ": 6, "ꯒꯤ": 7, "▁ꯆ": 8, "▁ꯑꯃ": 9, "▁ꯑꯁꯤ": 10, "▁ꯂ": 11, "▁ꯀ": 12, "▁ꯍ": 13, "ꯅꯤ꯫": 14, "ꯟꯅ": 15, "▁ꯗ": 16, "ꯨꯡ": 17, "ꯥꯎ": 18, "▁꯫": 19, "꯰꯰": 20, "ꯀꯤ": 21, "▁ꯆꯥꯎ": 22, "▁ꯆꯩ": 23, "▁ꯁ": 24, "▁ꯍꯦ": 25, "ꯥꯢ": 26, "ꯔꯤ": 27, "▁ꯍꯦꯟꯅ": 28, "ꯌꯥ": 29, "▁ꯇ": 30, "▁ꯏ": 31, "▁꯱": 32, "ꯅꯨꯡ": 33, "▁ꯄ": 34, "▁ꯑꯃꯅꯤ꯫": 35, "ꯂꯤ": 36, "▁ꯃꯅꯨꯡ": 37, "▁ꯆꯩꯁꯤꯡ": 38, "▁ꯆꯥꯎꯕ": 39, "ꯣꯏ": 40, "▁ꯂꯩ": 41, "ꯌꯦ": 42, "▁ꯃꯁꯤ": 43, "▁ꯑꯃꯅꯤ": 44, "ꯣꯟ": 45, "▁ꯅ": 46, "▁꯲": 47, "ꯗꯒꯤ": 48, "ꯗꯨ": 49, "ꯅꯥ": 50, "▁ꯃꯇ": 51, "▁ꯃꯤ": 52, "ꯥꯏ": 53, "ꯦꯝ": 54, "ꯗꯤ": 55, "ꯥꯛ": 56, "▁ꯀꯥ": 57, "▁ꯊ": 58, "ꯁꯨ": 59, "ꯂꯣꯟ": 60, "ꯋꯥ": 61, "ꯧꯕ": 62, "▁ꯑꯦ": 63, "ꯌꯥꯝ": 64, "꯰꯰꯰": 65, "▁ꯑꯗꯨ": 66, "▁ꯅꯤ꯫": 67, "ꯣꯢ": 68, "▁ꯗꯤ": 69, "ꯡꯂ": 70, "▁ꯐ": 71, "▁ꯂꯥꯢ": 72, "ꯜꯂꯤ": 73, "ꯔꯤꯕ": 74, "▁ꯑꯣꯏ": 75, "ꯕꯤ": 76, "▁ꯌꯦ": 77, "▁ꯈ": 78, "▁ꯗꯒꯤ": 79, "ꯦ꯫": 80, "ꯇꯩ": 81, "ꯗꯥ": 82, "▁꯴": 83, "ꯥꯟ": 84, "▁ꯃꯇꯝ": 85, "ꯤꯡ": 86, "▁ꯍꯥꯏ": 87, "▁ꯑꯃꯒꯤ": 88, "▁ꯀꯧꯕ": 89, "▁ꯃꯤꯇꯩ": 90, "ꯨꯝ": 91, "▁꯳": 92, "▁ꯆꯜꯂꯤ": 93, "▁ꯁꯤ": 94, "ꯇꯤ": 95, "ꯈꯟ": 96, "▁ꯀꯥꯈꯟ": 97, "▁ꯑꯆ": 98, "ꯂꯩ": 99, "ꯈꯤ": 100, "ꯣꯛ": 101, "ꯁꯤꯡꯒꯤ": 102, "ꯕꯥ": 103, "▁ꯇꯤ": 104, "▁ꯄꯨ": 105, "▁ꯃꯁꯤꯗꯒꯤ": 106, "ꯂꯩꯄ": 107, "▁ꯂꯩꯕ": 108, "ꯅꯤꯡ": 109, "▁ꯌꯥꯝ": 110, "▁ꯃꯊ": 111, "ꯑꯣꯏ": 112, "ꯌꯦꯛ": 113, "▁ꯃꯍ": 114, "ꯥꯡ": 115, "▁ꯁꯦꯝ": 116, "▁ꯋꯥ": 117, "꯭ꯔ": 118, "▁ꯑꯣꯢ": 119, "ꯂꯨ": 120, "▁ꯑꯗꯨꯒ": 121, "▁ꯌꯦꯡꯂ": 122, "▁꯲꯰꯰꯰": 123, "▁ꯃꯊꯪ": 124, "▁ꯃꯅꯨꯡꯗꯒꯤ": 125, "ꯧꯄ": 126, "ꯄꯇꯤ": 127, "▁ꯃꯥ": 128, "▁ꯑꯃꯁꯨ": 129, "▁ꯏꯌꯦꯛ": 130, "▁ꯆꯥꯎꯄ": 131, "▁ꯍꯥꯏꯄꯇꯤ": 132, "▁ꯇꯀꯤ": 133, "ꯑꯣꯏꯄ": 134, "▁ꯃꯂꯨ": 135, "▁ꯑꯆꯧꯄ": 136, "▁꯴ꯂꯩꯄ": 137, "▁ꯃꯂꯨꯑꯣꯏꯄ": 138, "▁ꯃꯊꯪꯀꯤ": 139, "▁ꯁꯦꯝꯄ": 140, "▁ꯏꯌꯦꯛꯅ": 141, "▁ꯃꯤꯇꯩꯀꯤ": 142, "▁ꯃꯇꯝꯅꯤ": 143, "ꯆꯠ": 144, "▁ꯗꯅ": 145, "ꯃꯤ": 146, "▁ꯏꯁ": 147, "ꯂꯦꯝ": 148, "ꯨꯞ": 149, "ꯦꯛ": 150, "▁ꯃꯍꯥꯛ": 151, "ꯣꯡ": 152, "▁ꯏꯁꯩ": 153, "▁ꯎ": 154, "▁ꯆꯩꯁꯤꯡꯂꯣꯟ": 155, "▁ꯆꯩꯆꯠ": 156, "▁ꯌꯦꯡꯂꯗꯤ": 157, "▁ꯒꯤ": 158, "ꯇꯥ": 159, "ꯣꯔ": 160, "▁ꯃꯅꯨꯡꯗ": 161, "▁ꯃꯥꯂꯦꯝ": 162, "ꯂꯣꯟꯒꯤ": 163, "ꯔꯦ": 164, "ꯅꯦ꯫": 165, "ꯄꯤ": 166, "▁ꯃꯃ": 167, "▁ꯂꯤ": 168, "▁ꯁꯥ": 169, "ꯂꯝ": 170, "ꯔꯕ": 171, "▁ꯄꯨꯋꯥ": 172, "▁ꯌ": 173, "▁ꯃꯇꯨꯡ": 174, "ꯂꯥ": 175, "ꯛꯇ": 176, "ꯦꯟ": 177, "▁ꯑꯃꯗꯤ": 178, "ꯖꯤ": 179, "ꯥꯟꯕ": 180, "ꯄꯥꯛ": 181, "▁ꯀꯨꯝ": 182, "ꯋꯥꯢ": 183, "▁ꯀꯥꯡꯂ": 184, "▁ꯀꯥꯡꯂꯨꯞ": 185, "ꯄꯥ": 186, "ꯗꯝ": 187, "ꯚꯤ": 188, "▁ꯑꯣꯏ꯫": 189, "▁ꯁꯦꯝꯄꯅꯤ꯫": 190, "ꯈꯤ꯫": 191, "ꯨꯔ": 192, "▁ꯀ꯭": 193, "▁ꯉ": 194, "ꯁ꯭": 195, "▁▁": 196, "ꯤ": 197, "ꯃ": 198, "ꯁ": 199, "ꯥ": 200, "ꯅ": 201, "ꯡ": 202, "ꯑ": 203, "ꯂ": 204, "ꯨ": 205, "ꯗ": 206, "ꯦ": 207, "ꯕ": 208, "ꯒ": 209, "ꯆ": 210, "꯫": 211, "ꯣ": 212, "ꯟ": 213, "ꯀ": 214, "ꯩ": 215, "ꯄ": 216, "ꯇ": 217, "ꯔ": 218, "ꯝ": 219, "ꯏ": 220, "ꯍ": 221, "ꯌ": 222, "꯰": 223, "ꯛ": 224, "ꯎ": 225, "ꯢ": 226, "ꯈ": 227, "꯱": 228, "ꯊ": 229, "ꯧ": 230, "꯭": 231, "ꯜ": 232, "ꯠ": 233, "꯲": 234, "ꯋ": 235, "꯴": 236, "ꯐ": 237, "ꯪ": 238, "꯳": 239, "ꯖ": 240, "ꯞ": 241, "꯵": 242, "ꯉ": 243, "꯹": 244, "꯷": 245, "꯸": 246, "꯶": 247, "ꯚ": 248, "ꯓ": 249, "꫰": 250, "ꯙ": 251, "ꯘ": 252, "꫱": 253, "꯬": 254, "ꫡ": 255, "▁": 256, "<pad>": 257}, "sd": {"<unk>": 0, "▁म": 1, "▁ज": 2, "▁क": 3, "▁ह": 4, "▁स": 5, "▁प": 6, "▁व": 7, "हि": 8, "▁आ": 9, "नि": 10, "▁ख": 11, "ां": 12, "▁त": 13, "ार": 14, "▁ब": 15, "ें": 16, "▁जे": 17, "▁अ": 18, "▁ल": 19, "हे": 20, "ूं": 21, "▁र": 22, "▁कर": 23, "▁हि": 24, "यो": 25, "▁में": 26, "▁आहे": 27, "ंद": 28, "ाइ": 29, "ड़": 30, "्र": 31, "▁खे": 32, "▁जो": 33, "▁न": 34, "▁मु": 35, "▁श": 36, "▁जी": 37, "▁थ": 38, "▁हु": 39, "क़": 40, "हिं": 41, "िय": 42, "▁ग": 43, "▁हिक": 44, "्त": 45, "ान": 46, "ाल": 47, "िल": 48, "▁लाइ": 49, "फ़": 50, "▁ऐ": 51, "▁हिकु": 52, "ज़": 53, "▁ड": 54, "▁द": 55, "▁ऐं": 56, "ंहिं": 57, "▁छ": 58, "र्": 59, "री": 60, "▁ते": 61, "▁सां": 62, "णु": 63, "वा": 64, "ाए": 65, "या": 66, "ंहिंज": 67, "ाम": 68, "्ह": 69, "खे": 70, "▁हुन": 71, "▁मूं": 72, "ेल": 73, "▁इ": 74, "▁ई": 75, "▁करे": 76, "▁खां": 77, "ीं": 78, "▁च": 79, "ुनि": 80, "▁करु": 81, "ु॒": 82, "▁छा": 83, "▁आहि": 84, "लु": 85, "ंग": 86, "▁घ": 87, "्य": 88, "▁मूंखे": 89, "ाण": 90, "ियो": 91, "ाई": 92, "▁भ": 93, "▁बि": 94, "स्": 95, "िन": 96, "ीअ": 97, "▁सु": 98, "▁सभ": 99, "रु": 100, "ानी": 101, "हिड़": 102, "▁थी": 103, "े॒": 104, "हिर": 105, "▁लग": 106, "▁उ": 107, "▁ट": 108, "▁कहिड़": 109, "▁मुंहिंज": 110, "ा॒": 111, "▁पो": 112, "दि": 113, "▁अल": 114, "▁कयो": 115, "▁हिन": 116, "▁श्र": 117, "दा": 118, "ारी": 119, "्ट": 120, "क़्त": 121, "जे": 122, "▁ए": 123, "▁आहिनि": 124, "िर": 125, "ारम": 126, "▁अलारम": 127, "▁वक़्त": 128, "ात": 129, "ाब": 130, "िक": 131, "▁हू": 132, "ास": 133, "▁सघ": 134, "मेल": 135, "▁बै": 136, "बानी": 137, "▁पोइ": 138, "▁महिर": 139, "▁महिरबानी": 140, "जी": 141, "▁ठ": 142, "▁कु": 143, "▁ज़": 144, "▁ईमेल": 145, "ली": 146, "ाय": 147, "ेक": 148, "▁क़": 149, "▁बैदि": 150, "▁पंहिंज": 151, "दी": 152, "्म": 153, "ंदो": 154, "▁अज": 155, "▁ख़": 156, "ंदड़": 157, "ि॒": 158, "▁थो": 159, "▁पर": 160, "ला": 161, "▁फ": 162, "▁या": 163, "▁मुक़": 164, "हु": 165, "्यू": 166, "▁जेक": 167, "▁प्र": 168, "रर": 169, "िस": 170, "ेश": 171, "ारु": 172, "ाहि": 173, "▁रा": 174, "▁हो": 175, "▁मां": 176, "▁वार": 177, "एं": 178, "दो": 179, "ीक": 180, "ुर": 181, "▁मुक़रर": 182, "ख़": 183, "ोक": 184, "▁गो": 185, "▁वध": 186, "▁▁": 187, "ा": 188, "े": 189, "ि": 190, "र": 191, "ं": 192, "ह": 193, "ु": 194, "क": 195, "म": 196, "ी": 197, "ज": 198, "न": 199, "ो": 200, "ल": 201, "्": 202, "स": 203, "त": 204, "़": 205, "य": 206, "व": 207, "द": 208, "ब": 209, "प": 210, "ख": 211, "ू": 212, "ड": 213, "आ": 214, "ग": 215, "ण": 216, "ट": 217, "अ": 218, "इ": 219, "॒": 220, "श": 221, "ई": 222, "थ": 223, "ए": 224, "फ": 225, "भ": 226, "च": 227, "ध": 228, "छ": 229, "घ": 230, "ै": 231, "ठ": 232, "ऐ": 233, "उ": 234, "ौ": 235, "झ": 236, "ॾ": 237, "ढ": 238, "ॉ": 239, "ञ": 240, "ॻ": 241, "ॿ": 242, "ृ": 243, "ओ": 244, "ष": 245, "ऑ": 246, "ॼ": 247, "ऱ": 248, "औ": 249, "ङ": 250, "ॅ": 251, "ँ": 252, "ऊ": 253, "ऍ": 254, "ऩ": 255, "▁": 256, "<pad>": 257}, "or": {"<unk>": 0, "▁କ": 1, "▁ସ": 2, "▁ପ": 3, "ାର": 4, "▁ବ": 5, "୍ର": 6, "୍ତ": 7, "ରେ": 8, "୍ୟ": 9, "▁ମ": 10, "ଙ୍": 11, "ିବ": 12, "▁ଏ": 13, "ଙ୍କ": 14, "▁କର": 15, "ାନ": 16, "▁ନ": 17, "▁ଅ": 18, "▁ଦ": 19, "▁ହ": 20, "ାଇ": 21, "ିଲ": 22, "▁ଆ": 23, "ର୍": 24, "ନ୍ତ": 25, "ହି": 26, "▁ର": 27, "ିକ": 28, "ିବା": 29, "▁ଜ": 30, "ଛି": 31, "କୁ": 32, "▁ପ୍ର": 33, "▁ତ": 34, "ଥିଲ": 35, "▁ଗ": 36, "▁ବି": 37, "▁ଭ": 38, "ନ୍": 39, "▁ଯ": 40, "ିତ": 41, "ନ୍ତି": 42, "▁କରି": 43, "▁ସେ": 44, "ରୁ": 45, "▁ଲ": 46, "େବ": 47, "୍ଷ": 48, "▁ଓ": 49, "ମ୍": 50, "▁ଶ": 51, "ନା": 52, "▁ଚ": 53, "ଛନ୍ତି": 54, "ଟି": 55, "ହା": 56, "ୋଇ": 57, "▁ଉ": 58, "ାରେ": 59, "▁ହୋଇ": 60, "ଡ଼": 61, "ଥିବା": 62, "▁ନି": 63, "ଲି": 64, "ଷ୍": 65, "ାମ": 66, "ଥିଲେ": 67, "େଇ": 68, "ଣ୍": 69, "ତି": 70, "୍ୱ": 71, "୍ଥ": 72, "ରି": 73, "ଙ୍କୁ": 74, "ାସ": 75, "କ୍ଷ": 76, "ାବ": 77, "ମାନ": 78, "ଧ୍ୟ": 79, "▁ପାଇ": 80, "ନ୍ଦ": 81, "▁ଏହି": 82, "ାତ": 83, "▁ରା": 84, "୍ୟା": 85, "▁ସମ": 86, "ସି": 87, "ାଯ": 88, "▁ଅନ": 89, "ଥିଲା": 90, "▁ତା": 91, "େଶ": 92, "ୋଗ": 93, "୍ଚ": 94, "ବା": 95, "▁୧": 96, "▁ମଧ୍ୟ": 97, "▁ଖ": 98, "▁ଘ": 99, "▁ପାଇଁ": 100, "ିନ": 101, "ଡି": 102, "୍ରୀ": 103, "▁କି": 104, "ାଗ": 105, "▁ଟ": 106, "୍ଲ": 107, "ୁର": 108, "ଦ୍": 109, "ାପ": 110, "▁ଜଣ": 111, "କାର": 112, "▁୨": 113, "▁ଏବ": 114, "ାଳ": 115, "ାୟ": 116, "କ୍ତ": 117, "▁ଫ": 118, "▁କରାଯ": 119, "ାର୍": 120, "ଙ୍ଗ": 121, "ୋଲି": 122, "େଳ": 123, "ସ୍ତ": 124, "▁ସଂ": 125, "ାରୁ": 126, "▁ହେ": 127, "ଷ୍ଟ": 128, "▁ରାଜ": 129, "ଯ୍ୟ": 130, "ୋକ": 131, "▁ଏହା": 132, "▁ମୁ": 133, "ତା": 134, "▁ଏକ": 135, "ାଲ": 136, "ଭି": 137, "ଳି": 138, "ାଣ": 139, "▁ମି": 140, "▁ସହ": 141, "▁ସୁ": 142, "▁ହେବ": 143, "▁ପର": 144, "▁କରିବା": 145, "ାଉ": 146, "ଡ଼ି": 147, "ାରି": 148, "▁କେ": 149, "▁ଉପ": 150, "ଣ୍ଡ": 151, "ଥା": 152, "ସ୍ଥ": 153, "କ୍ର": 154, "ାନ୍ତ": 155, "ଦ୍ଧ": 156, "ଲେ": 157, "ୀୟ": 158, "ଞ୍ଚ": 159, "▁ଏବଂ": 160, "▁ଯେ": 161, "ୃତ": 162, "▁ଧ": 163, "▁ପରେ": 164, "▁ସମ୍": 165, "େଳେ": 166, "ାଇଛି": 167, "▁▁": 168, "ା": 169, "ି": 170, "ର": 171, "୍": 172, "କ": 173, "େ": 174, "ନ": 175, "ବ": 176, "ତ": 177, "ସ": 178, "ୁ": 179, "ପ": 180, "ମ": 181, "ହ": 182, "ଲ": 183, "ୟ": 184, "ଦ": 185, "ୋ": 186, "ଇ": 187, "ଥ": 188, "ଜ": 189, "ଗ": 190, "ଟ": 191, "ୀ": 192, "ଣ": 193, "ଏ": 194, "ଶ": 195, "ଙ": 196, "ଛ": 197, "ଯ": 198, "ଆ": 199, "ଳ": 200, "ଭ": 201, "ଷ": 202, "ଅ": 203, "ଚ": 204, "ଧ": 205, "ଡ": 206, "ଉ": 207, "ଖ": 208, "ଁ": 209, "ଂ": 210, "ଓ": 211, "ୂ": 212, "଼": 213, "ଠ": 214, "ୱ": 215, "ଫ": 216, "ୃ": 217, "୧": 218, "ଘ": 219, "୨": 220, "୦": 221, "ଞ": 222, "୩": 223, "୫": 224, "୪": 225, "୯": 226, "ଢ": 227, "୬": 228, "ୌ": 229, "୭": 230, "୮": 231, "ୈ": 232, "ଝ": 233, "ଵ": 234, "ଃ": 235, "ଋ": 236, "ଔ": 237, "ଈ": 238, "ଐ": 239, "ଊ": 240, "": 241, "ୢ": 242, "ୖ": 243, "ୠ": 244, "ୄ": 245, "": 246, "ୗ": 247, "୰": 248, "ଽ": 249, "ଌ": 250, "": 251, "୲": 252, "୳": 253, "": 254, "": 255, "▁": 256, "<pad>": 257}, "mai": {"<unk>": 0, "▁क": 1, "▁स": 2, "▁म": 3, "▁अ": 4, "▁प": 5, "▁ज": 6, "्र": 7, "▁ब": 8, "ार": 9, "▁न": 10, "▁आ": 11, "▁द": 12, "▁छ": 13, "▁र": 14, "ेल": 15, "हि": 16, "▁व": 17, "्य": 18, "▁भ": 19, "▁ल": 20, "▁ग": 21, "▁ह": 22, "▁अछ": 23, "▁ए": 24, "▁अछि": 25, "ान": 26, "▁के": 27, "िक": 28, "▁त": 29, "मे": 30, "र्": 31, "न्": 32, "ाल": 33, "ाक": 34, "▁मे": 35, "ित": 36, "िल": 37, "▁प्र": 38, "ना": 39, "्त": 40, "▁च": 41, "▁एक": 42, "▁वि": 43, "ास": 44, "▁कर": 45, "ाम": 46, "▁श": 47, "▁ओ": 48, "िय": 49, "▁सं": 50, "्व": 51, "रा": 52, "ैत": 53, "▁जे": 54, "▁उ": 55, "▁सम": 56, "▁रह": 57, "▁छल": 58, "▁पर": 59, "ाज": 60, "्ष": 61, "त्र": 62, "▁जा": 63, "▁सँ": 64, "ुर": 65, "▁छी": 66, "▁से": 67, "▁ई": 68, "▁गेल": 69, "ता": 70, "ति": 71, "ने": 72, "स्": 73, "नक": 74, "ीक": 75, "ड़": 76, "ला": 77, "▁दे": 78, "▁मु": 79, "नि": 80, "▁सु": 81, "▁ख": 82, "▁अप": 83, "▁बा": 84, "▁हम": 85, "▁लेल": 86, "पाल": 87, "▁हो": 88, "न्द": 89, "▁य": 90, "▁फ": 91, "▁ध": 92, "ाह": 93, "ाय": 94, "▁रहल": 95, "थिल": 96, "▁ने": 97, "टा": 98, "▁छै": 99, "सँ": 100, "ाँ": 101, "▁भेल": 102, "हो": 103, "▁को": 104, "ोक": 105, "ंग": 106, "थि": 107, "हु": 108, "▁नहि": 109, "ाव": 110, "्च": 111, "▁कि": 112, "▁एहि": 113, "▁नि": 114, "ाग": 115, "्ट": 116, "के": 117, "िन": 118, "्म": 119, "रि": 120, "्या": 121, "▁इ": 122, "▁कह": 123, "कार": 124, "▁सेहो": 125, "▁सभ": 126, "▁२": 127, "▁१": 128, "▁राज": 129, "दा": 130, "▁कए": 131, "था": 132, "▁अपन": 133, "▁घ": 134, "ाद": 135, "री": 136, "▁सब": 137, "▁मि": 138, "मा": 139, "▁स्": 140, "सभ": 141, "▁नेपाल": 142, "ेश": 143, "िया": 144, "▁अन": 145, "क्ष": 146, "इत": 147, "ती": 148, "▁मै": 149, "बाक": 150, "▁सा": 151, "ाष": 152, "▁विक": 153, "▁बे": 154, "▁कार": 155, "म्": 156, "द्": 157, "▁▁": 158, "ा": 159, "क": 160, "र": 161, "ि": 162, "्": 163, "े": 164, "न": 165, "ल": 166, "स": 167, "म": 168, "त": 169, "ह": 170, "प": 171, "ी": 172, "य": 173, "व": 174, "द": 175, "ज": 176, "ब": 177, "ु": 178, "ो": 179, "छ": 180, "ग": 181, "अ": 182, "ं": 183, "भ": 184, "ै": 185, "ए": 186, "ँ": 187, "आ": 188, "च": 189, "श": 190, "ट": 191, "थ": 192, "ख": 193, "ू": 194, "ध": 195, "ष": 196, "ड": 197, "ण": 198, "इ": 199, "उ": 200, "ओ": 201, "ई": 202, "ौ": 203, "़": 204, "फ": 205, "ठ": 206, "१": 207, "घ": 208, "ऽ": 209, "०": 210, "ृ": 211, "२": 212, "झ": 213, "ञ": 214, "ढ": 215, "ॅ": 216, "ङ": 217, "९": 218, "३": 219, "६": 220, "८": 221, "४": 222, "५": 223, "७": 224, "ॉ": 225, "ः": 226, "ऐ": 227, "औ": 228, "ऊ": 229, "ऋ": 230, "ऑ": 231, "ळ": 232, "॰": 233, "ॆ": 234, "ॊ": 235, "ॐ": 236, "ॾ": 237, "ऱ": 238, "ॄ": 239, "ॻ": 240, "ॠ": 241, "ऩ": 242, "ॼ": 243, "ऒ": 244, "॓": 245, "॒": 246, "ॱ": 247, "ऎ": 248, "ॿ": 249, "ऍ": 250, "ॴ": 251, "॑": 252, "॔": 253, "ॲ": 254, "ऴ": 255, "▁": 256, "<pad>": 257}, "kok": {"<unk>": 0, "्य": 1, "्या": 2, "▁क": 3, "▁आ": 4, "▁त": 5, "▁म": 6, "▁प": 7, "▁स": 8, "ला": 9, "▁ह": 10, "▁अ": 11, "▁व": 12, "ार": 13, "ां": 14, "▁न": 15, "्र": 16, "ात": 17, "ले": 18, "▁ज": 19, "▁द": 20, "▁ब": 21, "ही": 22, "ाच": 23, "र्": 24, "ून": 25, "ाय": 26, "▁ग": 27, "ली": 28, "▁त्या": 29, "ाव": 30, "्ह": 31, "ान": 32, "ल्या": 33, "▁अस": 34, "▁य": 35, "▁हो": 36, "च्या": 37, "ती": 38, "▁र": 39, "हे": 40, "ता": 41, "▁श": 42, "ाही": 43, "▁आहे": 44, "▁च": 45, "▁कर": 46, "क्": 47, "▁उ": 48, "स्": 49, "▁ए": 50, "▁भ": 51, "▁प्र": 52, "▁घ": 53, "ते": 54, "चे": 55, "▁आण": 56, "ची": 57, "नी": 58, "▁ख": 59, "ंत": 60, "ना": 61, "▁का": 62, "▁आणि": 63, "िक": 64, "▁एक": 65, "री": 66, "सा": 67, "लो": 68, "चा": 69, "▁वा": 70, "▁फ": 71, "वा": 72, "ने": 73, "▁म्ह": 74, "ाण": 75, "▁ते": 76, "▁वि": 77, "▁नाही": 78, "▁ला": 79, "ित": 80, "वर": 81, "▁के": 82, "▁झ": 83, "ेत": 84, "▁दि": 85, "▁मा": 86, "▁हे": 87, "ाज": 88, "ल्": 89, "▁म्हण": 90, "ाक": 91, "त्": 92, "▁इ": 93, "ंद": 94, "▁स्": 95, "क्ष": 96, "▁झा": 97, "ांत": 98, "▁सु": 99, "शी": 100, "▁ल": 101, "ंग": 102, "ण्या": 103, "▁तर": 104, "▁आप": 105, "ेव": 106, "ास": 107, "▁पु": 108, "▁पण": 109, "तो": 110, "ळे": 111, "ाह": 112, "▁नि": 113, "डे": 114, "ाल": 115, "्ट": 116, "द्": 117, "कार": 118, "▁कि": 119, "▁लाग": 120, "▁पर": 121, "ाला": 122, "▁मु": 123, "ाम": 124, "ाचे": 125, "स्त": 126, "▁ट": 127, "▁को": 128, "▁सं": 129, "लं": 130, "▁तु": 131, "▁ध": 132, "▁काही": 133, "रे": 134, "ठी": 135, "▁जा": 136, "तात": 137, "▁तो": 138, "▁या": 139, "▁असे": 140, "णी": 141, "▁त्यां": 142, "ांग": 143, "▁मी": 144, "णार": 145, "ुन": 146, "व्ह": 147, "ाच्या": 148, "▁वे": 149, "▁मि": 150, "णे": 151, "डी": 152, "ाची": 153, "रा": 154, "▁ति": 155, "ळी": 156, "का": 157, "्ये": 158, "▁काय": 159, "▁आम": 160, "▁होते": 161, "▁▁": 162, "ा": 163, "्": 164, "त": 165, "र": 166, "े": 167, "ी": 168, "य": 169, "क": 170, "ल": 171, "न": 172, "स": 173, "व": 174, "ं": 175, "ह": 176, "च": 177, "म": 178, "ि": 179, "प": 180, "ो": 181, "ण": 182, "द": 183, "आ": 184, "ग": 185, "ु": 186, "ज": 187, "ब": 188, "ू": 189, "ट": 190, "श": 191, "अ": 192, "ड": 193, "ळ": 194, "ध": 195, "ख": 196, "भ": 197, "ष": 198, "घ": 199, "थ": 200, "ठ": 201, "उ": 202, "ए": 203, "फ": 204, "झ": 205, "इ": 206, "ढ": 207, "ई": 208, "ै": 209, "ॉ": 210, "ऊ": 211, "१": 212, "ॅ": 213, "ृ": 214, "०": 215, "छ": 216, "ओ": 217, "२": 218, "ौ": 219, "ऱ": 220, "५": 221, "ः": 222, "ँ": 223, "३": 224, "ऑ": 225, "९": 226, "ऐ": 227, "४": 228, "ञ": 229, "६": 230, "८": 231, "७": 232, "़": 233, "औ": 234, "ॆ": 235, "ऋ": 236, "॑": 237, "ऍ": 238, "ऽ": 239, "ॊ": 240, "ॄ": 241, "ङ": 242, "ऴ": 243, "ॲ": 244, "ऎ": 245, "ऩ": 246, "ऒ": 247, "ॐ": 248, "ॕ": 249, "॒": 250, "ॠ": 251, "॰": 252, "॔": 253, "॓": 254, "ॢ": 255, "▁": 256, "<pad>": 257}, "brx": {"<unk>": 0, "ाय": 1, "▁ब": 2, "नि": 3, "▁स": 4, "ान": 5, "▁म": 6, "▁ह": 7, "ाव": 8, "ार": 9, "▁ज": 10, "▁ग": 11, "ोन": 12, "▁क": 13, "ों": 14, "्र": 15, "ां": 16, "▁आ": 17, "▁द": 18, "ोर": 19, "▁बि": 20, "ला": 21, "खौ": 22, "नाय": 23, "▁न": 24, "▁थ": 25, "▁प": 26, "▁फ": 27, "▁र": 28, "नो": 29, "दों": 30, "▁बे": 31, "▁ख": 32, "▁ल": 33, "थि": 34, "फोर": 35, "से": 36, "ाम": 37, "ुं": 38, "ानै": 39, "ाब": 40, "ारि": 41, "िर": 42, "लि": 43, "▁अ": 44, "न्": 45, "ना": 46, "▁जा": 47, "▁ए": 48, "ाद": 49, "▁गो": 50, "▁होन": 51, "▁आर": 52, "बो": 53, "या": 54, "▁के": 55, "▁मोन": 56, "सि": 57, "ानाय": 58, "ाख": 59, "▁आरो": 60, "ें": 61, "नानै": 62, "ाज": 63, "थाय": 64, "ाग": 65, "ाह": 66, "ुब": 67, "▁उ": 68, "▁भ": 69, "ोग": 70, "ाइ": 71, "ानि": 72, "▁सि": 73, "मोन": 74, "्ला": 75, "ोल": 76, "जों": 77, "आव": 78, "▁है": 79, "िरि": 80, "लाम": 81, "ास": 82, "▁नि": 83, "गिरि": 84, "ायो": 85, "▁जि": 86, "▁खा": 87, "▁बिथ": 88, "ेर": 89, "र्": 90, "्रि": 91, "ोम": 92, "▁दि": 93, "▁सम": 94, "दि": 95, "ाल": 96, "▁इ": 97, "सा": 98, "यो": 99, "ायाव": 100, "ुर": 101, "▁थाख": 102, "्रा": 103, "▁व": 104, "▁खालाम": 105, "▁में": 106, "ने": 107, "▁ला": 108, "▁हो": 109, "गोन": 110, "ुलि": 111, "▁लोग": 112, "फोरा": 113, "ुन": 114, "▁थाखाय": 115, "फ्र": 116, "टि": 117, "ान्": 118, "ेल": 119, "स्": 120, "बि": 121, "▁को": 122, "क्": 123, "▁औ": 124, "▁से": 125, "ोब": 126, "▁सुब": 127, "पि": 128, "▁लोगो": 129, "▁फोर": 130, "खा": 131, "▁और": 132, "्ल": 133, "▁च": 134, "▁की": 135, "▁कर": 136, "हा": 137, "्य": 138, "▁मि": 139, "▁त": 140, "▁पि": 141, "▁सोर": 142, "▁कि": 143, "ाङ": 144, "याव": 145, "▁सा": 146, "ुम": 147, "ाया": 148, "▁खौ": 149, "नायनि": 150, "▁प्र": 151, "ानो": 152, "▁ने": 153, "ता": 154, "▁बिथां": 155, "बाय": 156, "▁दै": 157, "दोंमोन": 158, "▁माव": 159, "▁पुलि": 160, "▁सुबुं": 161, "ेन": 162, "ब्ला": 163, "ेज": 164, "फ्राय": 165, "▁आस": 166, "राय": 167, "खार": 168, "▁बिज": 169, "▁बुं": 170, "ांग": 171, "ानानै": 172, "ति": 173, "▁श": 174, "▁▁": 175, "ा": 176, "न": 177, "ि": 178, "ो": 179, "र": 180, "ब": 181, "स": 182, "य": 183, "म": 184, "ं": 185, "े": 186, "्": 187, "ल": 188, "ग": 189, "ज": 190, "द": 191, "ह": 192, "ख": 193, "व": 194, "ु": 195, "क": 196, "थ": 197, "फ": 198, "ै": 199, "आ": 200, "प": 201, "त": 202, "ौ": 203, "ी": 204, "ए": 205, "ट": 206, "इ": 207, "उ": 208, "अ": 209, "भ": 210, "ङ": 211, "ड": 212, "श": 213, "च": 214, "ध": 215, "ष": 216, "ू": 217, "औ": 218, "ओ": 219, "ई": 220, "ण": 221, "़": 222, "झ": 223, "घ": 224, "छ": 225, "ृ": 226, "ठ": 227, "ढ": 228, "ॉ": 229, "ँ": 230, "ऐ": 231, "ः": 232, "ऑ": 233, "ऊ": 234, "ञ": 235, "०": 236, "ऱ": 237, "ऋ": 238, "२": 239, "१": 240, "ऩ": 241, "३": 242, "ॽ": 243, "६": 244, "ॆ": 245, "४": 246, "५": 247, "८": 248, "ॅ": 249, "॔": 250, "७": 251, "ऴ": 252, "ऽ": 253, "९": 254, "ॺ": 255, "▁": 256, "<pad>": 257}, "sa": {"<unk>": 0, "्य": 1, "्र": 2, "्त": 3, "्व": 4, "▁स": 5, "▁प": 6, "▁त": 7, "▁व": 8, "ान": 9, "र्": 10, "ति": 11, "म्": 12, "▁क": 13, "▁न": 14, "त्": 15, "्या": 16, "ित": 17, "▁अ": 18, "न्": 19, "मा": 20, "▁य": 21, "▁प्र": 22, "▁द": 23, "▁च": 24, "▁म": 25, "ार": 26, "ाद": 27, "ष्": 28, "▁श": 29, "स्य": 30, "क्": 31, "▁भ": 32, "▁वि": 33, "न्त": 34, "स्त": 35, "क्ष": 36, "त्व": 37, "ाव": 38, "त्र": 39, "▁इ": 40, "ाय": 41, "स्": 42, "द्": 43, "ां": 44, "ेन": 45, "्च": 46, "र्व": 47, "▁१": 48, "ाम": 49, "ते": 50, "त्त": 51, "प्र": 52, "वि": 53, "त्य": 54, "क्त": 55, "▁ज": 56, "रा": 57, "▁ग": 58, "ेव": 59, "▁ह": 60, "▁ब": 61, "र्थ": 62, "नि": 63, "ङ्": 64, "▁ए": 65, "ाप": 66, "ष्ट": 67, "ना": 68, "या": 69, "▁२": 70, "मि": 71, "न्द": 72, "ेष": 73, "्ञ": 74, "ता": 75, "▁आ": 76, "श्च": 77, "द्ध": 78, "ुर": 79, "िक": 80, "यो": 81, "भि": 82, "पि": 83, "▁र": 84, "ात्": 85, "था": 86, "▁उ": 87, "▁नि": 88, "रि": 89, "ान्": 90, "▁०": 91, "च्": 92, "वा": 93, "▁इति": 94, "ज्ञ": 95, "▁स्व": 96, "तः": 97, "मु": 98, "▁वा": 99, "दा": 100, "▁सर्व": 101, "दि": 102, "ङ्ग": 103, "▁ध": 104, "ाः": 105, "नु": 106, "▁३": 107, "र्त": 108, "र्म": 109, "ेद": 110, "ूप": 111, "तो": 112, "ती": 113, "ाध": 114, "च्छ": 115, "▁ल": 116, "्म": 117, "ाल": 118, "ैव": 119, "ान्त": 120, "कार": 121, "ेश": 122, "न्य": 123, "ास": 124, "मान": 125, "तु": 126, "ये": 127, "्रि": 128, "▁एव": 129, "द्व": 130, "भाव": 131, "▁भव": 132, "्यं": 133, "▁सु": 134, "्रह": 135, "▁पु": 136, "▁४": 137, "ग्": 138, "▁श्र": 139, "ने": 140, "ादि": 141, "ोऽ": 142, "कृ": 143, "ेण": 144, "▁पर": 145, "रण": 146, "ानि": 147, "ाह": 148, "ाण": 149, "द्य": 150, "न्न": 151, "ञ्च": 152, "न्ध": 153, "▁मह": 154, "ब्": 155, "ष्ठ": 156, "▁सं": 157, "सि": 158, "्वा": 159, "व्य": 160, "ोप": 161, "्": 162, "▁▁": 163, "ा": 164, "त": 165, "र": 166, "ि": 167, "य": 168, "व": 169, "न": 170, "म": 171, "स": 172, "प": 173, "े": 174, "द": 175, "क": 176, "ु": 177, "ं": 178, "ो": 179, "ः": 180, "श": 181, "ष": 182, "च": 183, "भ": 184, "ह": 185, "ध": 186, "ण": 187, "ग": 188, "॒": 189, "ी": 190, "ज": 191, "ल": 192, "थ": 193, "॑": 194, "ृ": 195, "अ": 196, "ू": 197, "ै": 198, "ब": 199, "१": 200, "इ": 201, "२": 202, "ट": 203, "०": 204, "ञ": 205, "ऽ": 206, "३": 207, "ङ": 208, "ए": 209, "ौ": 210, "४": 211, "ख": 212, "आ": 213, "५": 214, "६": 215, "उ": 216, "७": 217, "छ": 218, "ड": 219, "८": 220, "९": 221, "ठ": 222, "घ": 223, "फ": 224, "ॐ": 225, "ऋ": 226, "ढ": 227, "ई": 228, "ँ": 229, "ओ": 230, "ऊ": 231, "ऐ": 232, "॰": 233, "ळ": 234, "ॄ": 235, "़": 236, "झ": 237, "औ": 238, "ॢ": 239, "ॉ": 240, "ॆ": 241, "ऱ": 242, "ऌ": 243, "ऎ": 244, "ॊ": 245, "ॠ": 246, "ॅ": 247, "ऴ": 248, "ऩ": 249, "ऑ": 250, "ॡ": 251, "ऍ": 252, "ॣ": 253, "ऒ": 254, "ॖ": 255, "▁": 256, "<pad>": 257}, "sat": {"<unk>": 0, "▁ᱠ": 1, "ᱱᱟ": 2, "▁ᱨ": 3, "▁ᱟ": 4, "▁ᱥ": 5, "▁ᱨᱮ": 6, "▁ᱫ": 7, "▁ᱵ": 8, "ᱟᱹ": 9, "▁ᱢ": 10, "▁ᱦ": 11, "ᱚᱱ": 12, "▁ᱛ": 13, "ᱟᱨ": 14, "▁ᱯ": 15, "▁ᱡ": 16, "▁᱾": 17, "▁ᱞ": 18, "▁ᱫᱚ": 19, "ᱭᱟ": 20, "▁ᱜ": 21, "▁ᱠᱚ": 22, "▁ᱠᱟ": 23, "▁ᱮ": 24, "ᱚᱨ": 25, "ᱷᱟ": 26, "ᱠᱟ": 27, "ᱱᱟᱜ": 28, "▁ᱱ": 29, "ᱚᱛ": 30, "▁ᱟᱨ": 31, "▁ᱥᱟ": 32, "ᱟᱦ": 33, "ᱤᱫ": 34, "ᱣᱟ": 35, "▁ᱞᱮ": 36, "▁ᱚ": 37, "▁ᱦᱚ": 38, "ᱢᱟ": 39, "▁ᱵᱟ": 40, "▁ᱠᱟᱱᱟ": 41, "▁ᱪ": 42, "ᱤᱱ": 43, "▁ᱢᱮ": 44, "▁ᱱᱚ": 45, "▁ᱥᱮ": 46, "ᱚᱢ": 47, "ᱩᱨ": 48, "ᱞᱟ": 49, "▁ᱩ": 50, "▁ᱨᱮᱱᱟᱜ": 51, "ᱛᱮ": 52, "▁ᱠᱷ": 53, "ᱟᱭ": 54, "ᱤᱥ": 55, "ᱭᱟᱜ": 56, "ᱼᱟ": 57, "ᱚᱱᱚᱛ": 58, "ᱤᱭ": 59, "ᱟᱜ": 60, "▁ᱛᱮ": 61, "ᱤᱨ": 62, "ᱟᱱ": 63, "ᱮᱫ": 64, "ᱚᱜ": 65, "ᱰᱤ": 66, "▁ᱨᱮᱭᱟᱜ": 67, "ᱟᱦᱮ": 68, "▁ᱴ": 69, "▁ᱛᱟᱦᱮ": 70, "ᱨᱤ": 71, "▁ᱦᱚᱲ": 72, "▁ᱠᱷᱚᱱ": 73, "▁᱑": 74, "ᱤᱡ": 75, "ᱤᱞ": 76, "▁ᱧ": 77, "▁ᱢᱤᱫ": 78, "▁ᱦᱚᱱᱚᱛ": 79, "ᱟᱲ": 80, "▁ᱥᱤ": 81, "ᱩᱭ": 82, "▁ᱜᱮ": 83, "ᱟᱣ": 84, "▁ᱟᱠᱟ": 85, "▁ᱛᱟᱦᱮᱸ": 86, "ᱥᱤ": 87, "ᱚᱸ": 88, "ᱟᱢ": 89, "▁ᱟᱹ": 90, "▁ᱢᱮᱱᱟᱜ": 91, "▁᱒": 92, "ᱟᱝ": 93, "▁ᱱᱚᱣᱟ": 94, "ᱚᱦ": 95, "ᱡᱽ": 96, "ᱨᱮ": 97, "▁ᱵᱮ": 98, "ᱟᱸ": 99, "ᱱᱤ": 100, "ᱟᱞ": 101, "▁ᱞᱮᱠᱟ": 102, "ᱠᱷᱟ": 103, "ᱠᱚ": 104, "ᱩᱜ": 105, "ᱚᱞ": 106, "ᱤᱛ": 107, "ᱟᱹᱨ": 108, "ᱤᱭᱟ": 109, "ᱟᱹᱜ": 110, "ᱮᱥ": 111, "ᱚᱵ": 112, "ᱩᱢ": 113, "ᱚᱴ": 114, "▁ᱰ": 115, "ᱟᱥ": 116, "▁ᱵᱷ": 117, "ᱮᱞ": 118, "▁ᱡᱚ": 119, "ᱮᱱ": 120, "ᱤᱭᱟᱹ": 121, "▁ᱨᱟ": 122, "▁ᱱᱟ": 123, "ᱠᱷ": 124, "ᱨᱚ": 125, "▁ᱟᱡ": 126, "▁ᱦᱩᱭ": 127, "ᱨᱟ": 128, "▁᱒᱐": 129, "ᱫᱟ": 130, "ᱛᱤ": 131, "ᱫᱽ": 132, "ᱤᱠ": 133, "▁ᱦᱚᱸ": 134, "ᱶᱟ": 135, "▁ᱚᱱᱟ": 136, "▁ᱥᱟᱶ": 137, "▁ᱢᱮᱱᱟᱜᱼᱟ": 138, "ᱩᱞ": 139, "ᱚᱲ": 140, "ᱩᱛ": 141, "ᱢᱤ": 142, "▁ᱯᱷ": 143, "ᱮᱛ": 144, "ᱯᱩᱨ": 145, "▁ᱢᱩ": 146, "▁ᱥᱤᱧ": 147, "ᱲᱟ": 148, "▁ᱠᱟᱹ": 149, "ᱜᱟ": 150, "ᱷᱟᱨ": 151, "▁ᱢᱟ": 152, "▁ᱠᱟᱛᱮ": 153, "▁ᱱᱚᱶᱟ": 154, "▁ᱡᱟ": 155, "▁ᱥᱤᱧᱚᱛ": 156, "▁ᱞᱟ": 157, "▁᱑᱙": 158, "▁ᱞᱟᱹᱜ": 159, "▁ᱨᱤᱱ": 160, "▁ᱩᱱᱤ": 161, "ᱱᱟᱣ": 162, "᱐ᱮ": 163, "ᱢᱟᱱ": 164, "▁ᱥᱮᱨ": 165, "▁ᱟᱠᱟᱱᱟ": 166, "ᱫᱚ": 167, "▁ᱵᱟᱝ": 168, "▁ᱯᱟ": 169, "▁ᱟᱭ": 170, "ᱚᱠ": 171, "▁ᱥᱮᱨᱢᱟ": 172, "ᱷᱤ": 173, "ᱵᱟ": 174, "ᱞᱮ": 175, "▁ᱞᱮᱠᱟᱛᱮ": 176, "ᱩᱱ": 177, "ᱴᱤ": 178, "▁ᱡᱮ": 179, "▁ᱠᱚᱣᱟ": 180, "▁ᱤ": 181, "▁ᱡᱟᱦ": 182, "▁ᱫᱤᱥ": 183, "▁ᱞᱮᱱᱟ": 184, "▁ᱫᱷ": 185, "▁ᱦᱟ": 186, "▁ᱮᱱᱟ": 187, "▁ᱯᱚᱱᱚᱛ": 188, "▁ᱜᱟ": 189, "ᱮᱨ": 190, "▁ᱞᱟᱹᱜᱤᱫ": 191, "ᱮᱡ": 192, "ᱷᱟᱱ": 193, "▁ᱢᱟᱨ": 194, "▁ᱠᱩ": 195, "ᱛᱟ": 196, "▁ᱯᱟᱹᱨ": 197, "▁᱒᱐᱑": 198, "ᱚᱥ": 199, "▁ᱛᱟᱭ": 200, "▁ᱞᱮᱠᱷᱟ": 201, "ᱚᱭ": 202, "▁ᱧᱩᱛ": 203, "▁ᱛᱟ": 204, "▁ᱯᱟᱹᱨᱥᱤ": 205, "ᱰᱟ": 206, "▁▁": 207, "ᱟ": 208, "ᱚ": 209, "ᱮ": 210, "ᱨ": 211, "ᱱ": 212, "ᱤ": 213, "ᱠ": 214, "ᱜ": 215, "ᱥ": 216, "ᱫ": 217, "ᱛ": 218, "ᱢ": 219, "ᱞ": 220, "ᱩ": 221, "ᱭ": 222, "ᱦ": 223, "ᱵ": 224, "ᱷ": 225, "ᱡ": 226, "ᱯ": 227, "ᱹ": 228, "᱾": 229, "ᱴ": 230, "ᱣ": 231, "ᱲ": 232, "ᱸ": 233, "ᱰ": 234, "ᱪ": 235, "ᱝ": 236, "ᱽ": 237, "᱐": 238, "ᱧ": 239, "᱑": 240, "ᱼ": 241, "ᱳ": 242, "ᱶ": 243, "᱒": 244, "᱙": 245, "ᱬ": 246, "᱕": 247, "᱘": 248, "᱔": 249, "᱓": 250, "᱖": 251, "᱗": 252, "ᱺ": 253, "ᱻ": 254, "᱿": 255, "▁": 256, "<pad>": 257}, "as": {"<unk>": 0, "▁ক": 1, "য়": 2, "াৰ": 3, "▁প": 4, "▁ব": 5, "▁স": 6, "্ৰ": 7, "▁আ": 8, "্য": 9, "ৰা": 10, "ৰি": 11, "▁ম": 12, "্ত": 13, "▁অ": 14, "▁ন": 15, "▁হ": 16, "▁দ": 17, "ান": 18, "▁এ": 19, "▁বি": 20, "▁প্ৰ": 21, "তি": 22, "▁চ": 23, "তে": 24, "ৰ্": 25, "▁গ": 26, "িল": 27, "▁ল": 28, "▁জ": 29, "াল": 30, "িত": 31, "▁কৰি": 32, "ৰু": 33, "ছে": 34, "ীয়": 35, "িক": 36, "াই": 37, "্ব": 38, "▁উ": 39, "ন্": 40, "▁শ": 41, "▁য": 42, "াত": 43, "্ষ": 44, "ৰে": 45, "োৱ": 46, "▁ভ": 47, "ষ্": 48, "াব": 49, "▁সম": 50, "ন্ত": 51, "▁আৰু": 52, "াক": 53, "ায়": 54, "্থ": 55, "িয়": 56, "▁হৈ": 57, "াম": 58, "▁ত": 59, "▁ৰা": 60, "ক্ষ": 61, "ছিল": 62, "▁নি": 63, "লৈ": 64, "▁এই": 65, "ীৰ": 66, "নৰ": 67, "াহ": 68, "ুল": 69, "▁তে": 70, "ষ্ট": 71, "াগ": 72, "িব": 73, "াস": 74, "াপ": 75, "োক": 76, "▁ই": 77, "▁পৰা": 78, "লে": 79, "▁কৰা": 80, "▁পৰি": 81, "জন": 82, "▁সং": 83, "িন": 84, "াদ": 85, "ন্দ": 86, "কা": 87, "োৱা": 88, "কাৰ": 89, "▁খ": 90, "োগ": 91, "▁ৰ": 92, "ওঁ": 93, "িৰ": 94, "ুৰ": 95, "েই": 96, "▁থ": 97, "্প": 98, "ুৱ": 99, "▁কৰে": 100, "টো": 101, "্ধ": 102, "সম": 103, "▁তেওঁ": 104, "াজ": 105, "েশ": 106, "ুক": 107, "▁১": 108, "▁ধ": 109, "স্থ": 110, "▁ঘ": 111, "▁অন": 112, "্চ": 113, "াবে": 114, "▁হয়": 115, "না": 116, "টা": 117, "কল": 118, "▁ড": 119, "▁কৰিব": 120, "দ্ধ": 121, "েল": 122, "্ৰী": 123, "▁আৰ": 124, "খন": 125, "▁বাবে": 126, "াৰে": 127, "▁হৈছে": 128, "ণ্": 129, "▁প্ৰতি": 130, "ীয়ে": 131, "▁লগ": 132, "▁ফ": 133, "াৱ": 134, "▁ব্য": 135, "্র": 136, "ুলি": 137, "ীয়া": 138, "ভি": 139, "ৰাক": 140, "োৰ": 141, "▁অসম": 142, "▁২": 143, "াধ": 144, "▁দু": 145, "োন": 146, "ৰ্ম": 147, "▁ৰাজ": 148, "েত": 149, "▁কৰ": 150, "িছ": 151, "ৰ্ব": 152, "ৃত": 153, "নি": 154, "খ্য": 155, "ৰত": 156, "▁উপ": 157, "মান": 158, "▁জন": 159, "▁ট": 160, "াট": 161, "▁কে": 162, "▁এক": 163, "নে": 164, "▁কাৰ": 165, "ষ্ঠ": 166, "▁আহ": 167, "▁মহ": 168, "▁লোক": 169, "▁অনু": 170, "▁ছ": 171, "▁বুলি": 172, "াঁ": 173, "▁মু": 174, "▁▁": 175, "ৰ": 176, "া": 177, "্": 178, "ি": 179, "ক": 180, "ত": 181, "ন": 182, "ে": 183, "ব": 184, "য": 185, "ল": 186, "প": 187, "ম": 188, "স": 189, "ু": 190, "দ": 191, "়": 192, "হ": 193, "ী": 194, "ো": 195, "গ": 196, "জ": 197, "আ": 198, "ই": 199, "চ": 200, "ট": 201, "ৱ": 202, "ছ": 203, "শ": 204, "ষ": 205, "ৈ": 206, "ভ": 207, "অ": 208, "ধ": 209, "থ": 210, "খ": 211, "ণ": 212, "এ": 213, "ং": 214, "উ": 215, "ও": 216, "ড": 217, "ঁ": 218, "ূ": 219, "ৃ": 220, "ঘ": 221, "ঠ": 222, "ফ": 223, "১": 224, "০": 225, "র": 226, "ঞ": 227, "২": 228, "৷": 229, "ৎ": 230, "ঙ": 231, "৯": 232, "৫": 233, "৩": 234, "৪": 235, "ৌ": 236, "ঃ": 237, "ঢ": 238, "৬": 239, "৮": 240, "৭": 241, "ঝ": 242, "ঐ": 243, "ঔ": 244, "ঋ": 245, "ঈ": 246, "ঊ": 247, "৹": 248, "৲": 249, "ৗ": 250, "ৄ": 251, "৺": 252, "৻": 253, "ঌ": 254, "ৠ": 255, "▁": 256, "<pad>": 257}, "ks": {"<unk>": 0, "▁ا": 1, "▁چ": 2, "▁چھ": 3, "▁ک": 4, "َن": 5, "▁م": 6, "ان": 7, "▁اَ": 8, "▁ی": 9, "ہٕ": 10, "▁ت": 11, "▁چھِ": 12, "ہِ": 13, "ٛز": 14, "َر": 15, "کھ": 16, "▁س": 17, "▁مَن": 18, "ار": 19, "▁مَنٛز": 20, "▁پ": 21, "▁اَکھ": 22, "▁ب": 23, "یٖ": 24, "▁چھُ": 25, "ست": 26, "▁و": 27, "ِل": 28, "اک": 29, "▁ف": 30, "▁کَر": 31, "ند": 32, "نؠ": 33, "مَن": 34, "تھ": 35, "▁کٲ": 36, "▁آ": 37, "▁تہٕ": 38, "ۄس": 39, "ٲنؠ": 40, "▁یۄس": 41, "▁کَران": 42, "▁ن": 43, "ستٲنؠ": 44, "▁کٲم": 45, "▁ہ": 46, "▁اَد": 47, "▁گ": 48, "ارہ": 49, "▁ہِ": 50, "▁فِل": 51, "َس": 52, "نٛ": 53, "▁اَداک": 54, "▁اَداکارہ": 55, "▁فِلمَن": 56, "▁ر": 57, "▁د": 58, "ام": 59, "▁ش": 60, "▁ج": 61, "وٗ": 62, "ندو": 63, "▁ہِندو": 64, "ری": 65, "▁ہِندوستٲنؠ": 66, "او": 67, "نٛد": 68, "ال": 69, "یا": 70, "▁ز": 71, "ین": 72, "▁یِ": 73, "یٖر": 74, "▁ع": 75, "نہٕ": 76, "▁کٔ": 77, "▁خ": 78, "ُک": 79, "▁ل": 80, "ور": 81, "ٹھ": 82, "▁اِ": 83, "َل": 84, "وان": 85, "▁یہِ": 86, "▁ح": 87, "َم": 88, "▁کٔش": 89, "▁ہُ": 90, "ِس": 91, "َتھ": 92, "اد": 93, "یر": 94, "نی": 95, "▁کٔشیٖر": 96, "▁مُ": 97, "لی": 98, "▁ہُنٛد": 99, "▁پاک": 100, "▁پاکِ": 101, "▁مَ": 102, "یو": 103, "▁آس": 104, "▁یِوان": 105, "را": 106, "▁ض": 107, "وس": 108, "ِم": 109, "نٛز": 110, "ؠٹھ": 111, "ُن": 112, "رِ": 113, "▁ص": 114, "رٛ": 115, "َب": 116, "▁پاکِستٲنؠ": 117, "می": 118, "▁ای": 119, "▁پؠٹھ": 120, "اق": 121, "▁ق": 122, "▁تہ": 123, "▁کھ": 124, "ژھ": 125, "تؠ": 126, "▁جۆ": 127, "▁یا": 128, "ستان": 129, "تی": 130, "▁ٹ": 131, "اب": 132, "▁ضِل": 133, "▁آر": 134, "یٖن": 135, "ِک": 136, "▁جۆم": 137, "ول": 138, "تہٕ": 139, "▁بَ": 140, "ای": 141, "ون": 142, "▁اوس": 143, "▁ط": 144, "▁سی": 145, "یاہ": 146, "رٕ": 147, "اہ": 148, "▁تَ": 149, "▁چھے": 150, "ُل": 151, "▁أ": 152, "رن": 153, "▁وار": 154, "ُس": 155, "▁گام": 156, "▁یِم": 157, "چھ": 158, "سی": 159, "▁ڈ": 160, "▁▁": 161, "ا": 162, "ن": 163, "َ": 164, "ی": 165, "ِ": 166, "ر": 167, "م": 168, "ک": 169, "ہ": 170, "ھ": 171, "س": 172, "و": 173, "ت": 174, "چ": 175, "ل": 176, "د": 177, "ٕ": 178, "ُ": 179, "ٛ": 180, "ز": 181, "ٲ": 182, "ب": 183, "ؠ": 184, "پ": 185, "ش": 186, "گ": 187, "ٹ": 188, "ف": 189, "ۄ": 190, "ٖ": 191, "ج": 192, "ٔ": 193, "آ": 194, "ع": 195, "ق": 196, "ڈ": 197, "،": 198, "ٗ": 199, "ص": 200, "خ": 201, "ح": 202, "ے": 203, "ٚ": 204, "ژ": 205, "ط": 206, "ۆ": 207, "ض": 208, "أ": 209, "ظ": 210, "غ": 211, "ٟ": 212, "ڑ": 213, "ث": 214, "ذ": 215, "ؤ": 216, "ك": 217, "ي": 218, "ۍ": 219, "ۅ": 220, "ێ": 221, "ئ": 222, "ٮ": 223, "ْ": 224, "ۂ": 225, "ں": 226, "إ": 227, "ه": 228, "ٰ": 229, "ّ": 230, "ى": 231, "؛": 232, "؟": 233, "ې": 234, "ؙ": 235, "ـ": 236, "ٍ": 237, "؍": 238, "١": 239, "ۓ": 240, "ؐ": 241, "ً": 242, "٩": 243, "ٓ": 244, "٢": 245, "٥": 246, "ؒ": 247, "ء": 248, "٣": 249, "ٳ": 250, "ة": 251, "٤": 252, "٧": 253, "٨": 254, "ٱ": 255, "▁": 256, "<pad>": 257}, "te": {"<unk>": 0, "▁ప": 1, "ని": 2, "ార": 3, "▁క": 4, "్ర": 5, "▁వ": 6, "న్": 7, "▁అ": 8, "▁స": 9, "▁మ": 10, "ంద": 11, "లు": 12, "ర్": 13, "▁చ": 14, "లో": 15, "స్": 16, "▁త": 17, "కు": 18, "్య": 19, "న్న": 20, "ాల": 21, "ంచ": 22, "ారు": 23, "గా": 24, "▁ర": 25, "ను": 26, "క్": 27, "ంది": 28, "తు": 29, "ట్": 30, "▁ప్ర": 31, "▁ఆ": 32, "రి": 33, "▁ఉ": 34, "డు": 35, "ల్": 36, "▁ద": 37, "ంట": 38, "▁ఇ": 39, "▁చే": 40, "▁న": 41, "ిన": 42, "ంత": 43, "కి": 44, "ాయ": 45, "ించ": 46, "▁బ": 47, "రు": 48, "▁వి": 49, "డి": 50, "ప్": 51, "త్": 52, "▁ఎ": 53, "▁గ": 54, "▁జ": 55, "ంలో": 56, "లి": 57, "టి": 58, "తి": 59, "ప్ప": 60, "డా": 61, "ంగా": 62, "లా": 63, "మా": 64, "▁ఈ": 65, "సు": 66, "ార్": 67, "▁ని": 68, "టు": 69, "స్తు": 70, "లే": 71, "స్త": 72, "ద్": 73, "ాయి": 74, "చ్": 75, "ది": 76, "నే": 77, "▁కా": 78, "దు": 79, "▁రా": 80, "న్ని": 81, "న్నారు": 82, "ష్": 83, "ాలు": 84, "చ్చ": 85, "ండ": 86, "గు": 87, "వా": 88, "▁తె": 89, "సి": 90, "▁భ": 91, "ిత": 92, "▁స్": 93, "ందు": 94, "టీ": 95, "ంగ": 96, "్యా": 97, "తో": 98, "వు": 99, "డ్": 100, "▁హ": 101, "నికి": 102, "ిక": 103, "పు": 104, "▁శ": 105, "▁చె": 106, "ళ్": 107, "యా": 108, "రో": 109, "▁ఏ": 110, "▁మీ": 111, "ైన": 112, "▁ఒ": 113, "▁కూ": 114, "ామ": 115, "క్క": 116, "▁కొ": 117, "▁సి": 118, "▁మా": 119, "క్ష": 120, "ారి": 121, "▁పె": 122, "ేశ": 123, "▁ఉన్న": 124, "ాల్": 125, "పో": 126, "ంతో": 127, "▁ము": 128, "మ్": 129, "▁లే": 130, "ంచి": 131, "▁కూడా": 132, "▁వె": 133, "కో": 134, "వి": 135, "త్ర": 136, "ట్ట": 137, "▁సం": 138, "▁తీ": 139, "▁కో": 140, "పై": 141, "▁పో": 142, "ాడు": 143, "▁కే": 144, "▁ఫ": 145, "ష్ట": 146, "డం": 147, "ప్పు": 148, "రా": 149, "▁అయ": 150, "లకు": 151, "▁ను": 152, "ింది": 153, "ారం": 154, "లను": 155, "కా": 156, "ద్ద": 157, "▁ఒక": 158, "▁లో": 159, "మి": 160, "లీ": 161, "నా": 162, "యం": 163, "్వ": 164, "▁పా": 165, "మె": 166, "నీ": 167, "▁కు": 168, "▁సమ": 169, "త్త": 170, "యు": 171, "పీ": 172, "▁▁": 173, "్": 174, "ి": 175, "ా": 176, "ు": 177, "ర": 178, "న": 179, "ం": 180, "ల": 181, "క": 182, "త": 183, "ప": 184, "స": 185, "వ": 186, "ద": 187, "మ": 188, "ే": 189, "ో": 190, "య": 191, "ట": 192, "చ": 193, "డ": 194, "గ": 195, "ీ": 196, "ె": 197, "అ": 198, "జ": 199, "బ": 200, "ూ": 201, "శ": 202, "ై": 203, "ష": 204, "ఆ": 205, "ధ": 206, "ఉ": 207, "హ": 208, "భ": 209, "ొ": 210, "ఇ": 211, "ణ": 212, "ఎ": 213, "ళ": 214, "ఈ": 215, "థ": 216, "ఫ": 217, "ఖ": 218, "ఏ": 219, "ఒ": 220, "ృ": 221, "ౌ": 222, "ఓ": 223, "ఘ": 224, "ఐ": 225, "ఠ": 226, "ఛ": 227, "ఊ": 228, "ఢ": 229, "ఞ": 230, "ఔ": 231, "ః": 232, "౦": 233, "ఝ": 234, "ఋ": 235, "ఁ": 236, "ఱ": 237, "ఙ": 238, "ౄ": 239, "౩": 240, "౧": 241, "ఽ": 242, "౨": 243, "౹": 244, "ౖ": 245, "౯": 246, "౫": 247, "౮": 248, "ౠ": 249, "౬": 250, "౭": 251, "ఌ": 252, "ౙ": 253, "౪": 254, "": 255, "▁": 256, "<pad>": 257}, "pa": {"<unk>": 0, "▁ਸ": 1, "▁ਕ": 2, "▁ਦ": 3, "▁ਹ": 4, "▁ਨ": 5, "▁ਵ": 6, "ਾਂ": 7, "▁ਪ": 8, "▁ਜ": 9, "▁ਮ": 10, "ਾਰ": 11, "▁ਅ": 12, "▁ਇ": 13, "▁ਤ": 14, "▁ਬ": 15, "▁ਦੇ": 16, "▁ਲ": 17, "▁ਹੈ": 18, "▁ਵਿ": 19, "ਾਲ": 20, "ੂੰ": 21, "ਿਆ": 22, "▁ਰ": 23, "▁ਦੀ": 24, "▁ਨੂੰ": 25, "▁ਕਿ": 26, "▁ਉ": 27, "ਸ਼": 28, "▁ਗ": 29, "ਿੰ": 30, "▁ਕਰ": 31, "ਤੇ": 32, "ਾਨ": 33, "▁ਆ": 34, "ੋਂ": 35, "੍ਰ": 36, "ਆਂ": 37, "▁ਅਤੇ": 38, "▁ਹੋ": 39, "ੱਚ": 40, "ਤੀ": 41, "ਦਾ": 42, "▁ਚ": 43, "▁ਇਸ": 44, "▁ਦਾ": 45, "ਤਾ": 46, "ਰੀ": 47, "ਹੀ": 48, "▁ਨੇ": 49, "ਿੱ": 50, "੍ਹ": 51, "ਦੇ": 52, "▁ਵਿੱਚ": 53, "▁ਲਈ": 54, "ਜ਼": 55, "▁ਕੀ": 56, "▁ਖ": 57, "▁ਸਿੰ": 58, "▁ਨਾਲ": 59, "ੱਕ": 60, "▁ਸਿੰਘ": 61, "ਲਾ": 62, "▁ਪ੍ਰ": 63, "ਹਿ": 64, "▁ਹਨ": 65, "ਹਾ": 66, "▁ਸ਼": 67, "ਦੀ": 68, "▁ਤੋਂ": 69, "▁ਭ": 70, "▁ਜਾ": 71, "▁ਵਿਚ": 72, "▁ਵੀ": 73, "▁ਫ": 74, "ਰਾ": 75, "ਵਾ": 76, "▁ਤੇ": 77, "ਣਾ": 78, "੍ਹਾਂ": 79, "▁ਇਹ": 80, "ੁਰ": 81, "ੀਆਂ": 82, "ਨਾ": 83, "ਕਾਰ": 84, "ੁੱ": 85, "ਵੇ": 86, "▁ਸੀ": 87, "▁ਡ": 88, "▁ਸਕ": 89, "ਦਰ": 90, "ਟੀ": 91, "ਨ੍ਹਾਂ": 92, "ਸੀ": 93, "▁ਕੇ": 94, "ੱਲ": 95, "ਹੀਂ": 96, "▁ਸਮ": 97, "▁ਇੱਕ": 98, "ਿਸ": 99, "▁ਕਰਨ": 100, "▁ਐ": 101, "ਾਈ": 102, "▁ਨਹੀਂ": 103, "ੁੰ": 104, "ਨੀ": 105, "ਿਆਂ": 106, "▁ਜਾਂ": 107, "ਕੇ": 108, "▁ਆਪ": 109, "▁ਕੋ": 110, "▁ਸੰ": 111, "ਿਲ": 112, "▁ਸਾ": 113, "ੈਂ": 114, "▁ਪਰ": 115, "▁ਉਹ": 116, "▁ਬਾ": 117, "ਕਾ": 118, "▁ਉਨ੍ਹਾਂ": 119, "ਲੇ": 120, "ਲੀ": 121, "▁ਦਿੱ": 122, "▁ਹੀ": 123, "ਗਾ": 124, "▁ਸਰ": 125, "▁ਰਾ": 126, "ਣੇ": 127, "ਜਾ": 128, "▁ਕੀਤਾ": 129, "ਿਰ": 130, "▁ਉਸ": 131, "ਰੇ": 132, "▁ਜ਼": 133, "▁ਮੁ": 134, "ੱਖ": 135, "▁ਲੋ": 136, "▁ਤੁ": 137, "▁ਘ": 138, "ਤਰ": 139, "ੰਗ": 140, "▁ਟ": 141, "▁ਗਿਆ": 142, "ਣੀ": 143, "ਾਇ": 144, "▁ਕਿਸ": 145, "ੱਸ": 146, "▁ਕੁ": 147, "ਿਕ": 148, "▁ਜੋ": 149, "ੌਰ": 150, "▁ਕਿਹਾ": 151, "ਜੀ": 152, "▁ਇਕ": 153, "ਡੀ": 154, "▁ਕੀਤੀ": 155, "▁ਪੰ": 156, "▁ਵਾਲ": 157, "ਨਾਂ": 158, "▁ਕਾਰ": 159, "ਾਰੇ": 160, "▁ਯ": 161, "ਹੇ": 162, "▁ਸੁ": 163, "▁ਤਾਂ": 164, "▁ਪਾ": 165, "▁ਨਾ": 166, "ਉਣ": 167, "ਟਰ": 168, "▁ਧ": 169, "▁ਮਾ": 170, "ਮੀ": 171, "ਾਰੀ": 172, "ੂਰ": 173, "ਹੁ": 174, "ਫ਼": 175, "ੰਤ": 176, "▁▁": 177, "ਾ": 178, "ਰ": 179, "ੀ": 180, "ਸ": 181, "ਿ": 182, "ੇ": 183, "ਕ": 184, "ਨ": 185, "ਦ": 186, "ਹ": 187, "ਤ": 188, "ਲ": 189, "ਂ": 190, "ਵ": 191, "ੰ": 192, "ਮ": 193, "ਜ": 194, "ਪ": 195, "ੋ": 196, "ੱ": 197, "ਆ": 198, "ੁ": 199, "ਗ": 200, "ਬ": 201, "਼": 202, "ੈ": 203, "ੂ": 204, "ਇ": 205, "ਅ": 206, "ਚ": 207, "ਣ": 208, "ਟ": 209, "ਈ": 210, "ਉ": 211, "੍": 212, "ਖ": 213, "ਡ": 214, "ਧ": 215, "ਫ": 216, "ਭ": 217, "ਘ": 218, "ੜ": 219, "ੌ": 220, "ਥ": 221, "ਏ": 222, "ਐ": 223, "ਯ": 224, "ਛ": 225, "ਝ": 226, "ਠ": 227, "ਓ": 228, "ਢ": 229, "ਊ": 230, "੫": 231, "ਔ": 232, "੧": 233, "੨": 234, "੩": 235, "ੳ": 236, "ੲ": 237, "੪": 238, "੦": 239, "੯": 240, "੭": 241, "੬": 242, "੮": 243, "ਞ": 244, "ਙ": 245, "ੴ": 246, "ਃ": 247, "ੑ": 248, "ੵ": 249, "ਁ": 250, "": 251, "": 252, "": 253, "": 254, "": 255, "▁": 256, "<pad>": 257}, "ta": {"<unk>": 0, "்க": 1, "்த": 2, "ம்": 3, "ல்": 4, "▁ப": 5, "ன்": 6, "க்க": 7, "▁க": 8, "்ட": 9, "▁வ": 10, "▁ம": 11, "த்த": 12, "்ப": 13, "▁அ": 14, "ும்": 15, "▁த": 16, "▁ச": 17, "ள்": 18, "ிய": 19, "▁இ": 20, "ர்": 21, "ரு": 22, "ந்த": 23, "ப்ப": 24, "து": 25, "ட்ட": 26, "▁ந": 27, "ில்": 28, "▁எ": 29, "ங்க": 30, "ைய": 31, "ாக": 32, "ிற": 33, "ின்": 34, "டு": 35, "▁உ": 36, "க்கு": 37, "ற்": 38, "ிர": 39, "ிக": 40, "று": 41, "ண்ட": 42, "ார": 43, "்ச": 44, "ள்ள": 45, "த்து": 46, "▁மு": 47, "ில": 48, "▁ஆ": 49, "ான": 50, "ற்ற": 51, "▁செ": 52, "டி": 53, "ர்க": 54, "ார்": 55, "லை": 56, "▁வி": 57, "▁ஒ": 58, "▁என்": 59, "ட்டு": 60, "ந்து": 61, "வி": 62, "ால்": 63, "ளை": 64, "ப்": 65, "ரி": 66, "தி": 67, "▁கு": 68, "ிரு": 69, "▁இரு": 70, "வு": 71, "▁அவ": 72, "▁கொ": 73, "▁போ": 74, "ல்ல": 75, "க்": 76, "▁செய": 77, "ச்ச": 78, "ின": 79, "▁கா": 80, "▁அத": 81, "த்": 82, "ான்": 83, "மை": 84, "▁பெ": 85, "▁மா": 86, "ளு": 87, "▁வே": 88, "றி": 89, "த்தில்": 90, "▁இந்த": 91, "▁ஒரு": 92, "க்கும்": 93, "னை": 94, "ப்பு": 95, "ையில்": 96, "ாய": 97, "ங்கள்": 98, "▁தொ": 99, "டை": 100, "ற்க": 101, "ர்கள்": 102, "ம்ப": 103, "ன்ற": 104, "▁ஏ": 105, "ரா": 106, "ுவ": 107, "ஸ்": 108, "ண்": 109, "ால": 110, "ிக்க": 111, "டிய": 112, "னர்": 113, "ண்டு": 114, "▁வெ": 115, "ாவ": 116, "ிறது": 117, "▁பு": 118, "ாத": 119, "கள்": 120, "மாக": 121, "ாள": 122, "▁கூ": 123, "மி": 124, "ச்": 125, "ன்ன": 126, "றை": 127, "வே": 128, "்கள்": 129, "▁உள்ள": 130, "கு": 131, "ப்பட்ட": 132, "ாம்": 133, "▁என": 134, "▁மற்ற": 135, "ற்ப": 136, "ங்கள": 137, "▁தெ": 138, "ழு": 139, "▁பிர": 140, "▁பொ": 141, "த்தை": 142, "ரிய": 143, "டுத்த": 144, "மான": 145, "▁பா": 146, "▁தே": 147, "▁நட": 148, "ரை": 149, "ளுக்கு": 150, "வும்": 151, "ையும்": 152, "▁இத": 153, "ரச": 154, "ட்ச": 155, "திய": 156, "்த்த": 157, "ின்ற": 158, "▁மற்றும்": 159, "ிட": 160, "ாம": 161, "கள": 162, "▁நீ": 163, "ரும்": 164, "வர்": 165, "▁மே": 166, "வை": 167, "▁வா": 168, "ற்று": 169, "▁நா": 170, "வத": 171, "▁வழ": 172, "மு": 173, "ண்டும்": 174, "டும்": 175, "▁ஜ": 176, "வில்": 177, "▁ர": 178, "டன்": 179, "▁செய்": 180, "ண்ண": 181, "▁சு": 182, "ன்று": 183, "▁தொட": 184, "ர்கள": 185, "▁வரு": 186, "▁அரச": 187, "னால்": 188, "்": 189, "▁▁": 190, "க": 191, "ு": 192, "த": 193, "ி": 194, "ப": 195, "ர": 196, "ம": 197, "ட": 198, "ா": 199, "வ": 200, "ல": 201, "ன": 202, "ை": 203, "ள": 204, "ய": 205, "ற": 206, "ச": 207, "ந": 208, "அ": 209, "ே": 210, "ண": 211, "இ": 212, "ெ": 213, "ோ": 214, "எ": 215, "ங": 216, "ொ": 217, "ழ": 218, "உ": 219, "ீ": 220, "ூ": 221, "ஆ": 222, "ஒ": 223, "ஸ": 224, "ஜ": 225, "ஏ": 226, "ஷ": 227, "ஞ": 228, "ஊ": 229, "ஹ": 230, "ஓ": 231, "ஐ": 232, "ஈ": 233, "ஃ": 234, "ௌ": 235, "ஶ": 236, "ஔ": 237, "ஂ": 238, "௧": 239, "௦": 240, "௨": 241, "௭": 242, "௫": 243, "௩": 244, "௮": 245, "௬": 246, "௪": 247, "௯": 248, "ௐ": 249, "ௗ": 250, "": 251, "": 252, "": 253, "": 254, "": 255, "▁": 256, "<pad>": 257}, "ne": {"<unk>": 0, "को": 1, "▁स": 2, "मा": 3, "का": 4, "▁प": 5, "र्": 6, "्र": 7, "न्": 8, "▁ग": 9, "▁र": 10, "ले": 11, "्य": 12, "ने": 13, "▁ब": 14, "ला": 15, "▁अ": 16, "▁भ": 17, "▁व": 18, "▁क": 19, "ार": 20, "▁ह": 21, "▁छ": 22, "▁न": 23, "▁त": 24, "▁म": 25, "▁प्र": 26, "▁ज": 27, "▁द": 28, "▁आ": 29, "स्": 30, "ाल": 31, "ना": 32, "क्": 33, "ता": 34, "▁उ": 35, "ति": 36, "एको": 37, "ान": 38, "▁गर": 39, "यो": 40, "▁वि": 41, "▁का": 42, "हर": 43, "▁गर्": 44, "नि": 45, "ेको": 46, "त्र": 47, "म्": 48, "लाई": 49, "नु": 50, "वा": 51, "▁य": 52, "ित": 53, "िक": 54, "▁ला": 55, "▁च": 56, "▁हु": 57, "था": 58, "री": 59, "▁मा": 60, "▁नि": 61, "्या": 62, "▁ल": 63, "▁ख": 64, "▁ए": 65, "▁रा": 66, "▁श": 67, "रा": 68, "क्ष": 69, "न्द": 70, "या": 71, "▁थ": 72, "▁सं": 73, "▁स्": 74, "त्": 75, "ल्": 76, "▁सा": 77, "▁ने": 78, "▁पनि": 79, "▁दि": 80, "बा": 81, "ेश": 82, "▁लाग": 83, "▁सम": 84, "पाल": 85, "ेर": 86, "हि": 87, "नी": 88, "ाउ": 89, "ष्": 90, "▁थि": 91, "ुर": 92, "ेका": 93, "▁१": 94, "एका": 95, "हरू": 96, "हरु": 97, "र्य": 98, "रि": 99, "▁फ": 100, "▁छन्": 101, "हा": 102, "बाट": 103, "दै": 104, "▁हो": 105, "पा": 106, "दा": 107, "▁भएको": 108, "क्र": 109, "▁को": 110, "कार": 111, "▁२": 112, "▁नेपाल": 113, "द्": 114, "▁लागि": 115, "स्त": 116, "▁त्य": 117, "न्त्र": 118, "▁रह": 119, "रो": 120, "भा": 121, "धि": 122, "न्छ": 123, "▁एक": 124, "▁पा": 125, "▁गर्न": 126, "▁गरि": 127, "▁यो": 128, "रण": 129, "▁घ": 130, "छि": 131, "ेख": 132, "▁के": 133, "▁निर्": 134, "ष्ट": 135, "▁गरेको": 136, "लो": 137, "वि": 138, "▁यस": 139, "▁कार्य": 140, "ही": 141, "▁सम्": 142, "ीय": 143, "▁पु": 144, "ेल": 145, "▁ध": 146, "▁ट": 147, "▁बता": 148, "सा": 149, "गा": 150, "र्ष": 151, "▁गर्ने": 152, "्न": 153, "ारी": 154, "▁भने": 155, "देश": 156, "स्था": 157, "्च": 158, "▁प्रति": 159, "▁बा": 160, "▁कु": 161, "▁सु": 162, "▁उन": 163, "न्त": 164, "▁व्य": 165, "कारी": 166, "▁ड": 167, "ध्य": 168, "▁थियो": 169, "ेखि": 170, "▁▁": 171, "ा": 172, "्": 173, "र": 174, "क": 175, "न": 176, "ि": 177, "े": 178, "स": 179, "म": 180, "ो": 181, "ल": 182, "त": 183, "प": 184, "य": 185, "ु": 186, "ग": 187, "ी": 188, "ह": 189, "व": 190, "द": 191, "ब": 192, "ज": 193, "भ": 194, "ए": 195, "छ": 196, "ट": 197, "ै": 198, "उ": 199, "अ": 200, "थ": 201, "श": 202, "ध": 203, "च": 204, "ष": 205, "ख": 206, "ड": 207, "आ": 208, "ं": 209, "ण": 210, "ँ": 211, "ू": 212, "ई": 213, "इ": 214, "फ": 215, "ठ": 216, "घ": 217, "१": 218, "ौ": 219, "२": 220, "ृ": 221, "०": 222, "ढ": 223, "ङ": 224, "५": 225, "झ": 226, "३": 227, "ञ": 228, "४": 229, "६": 230, "७": 231, "९": 232, "८": 233, "ओ": 234, "ः": 235, "औ": 236, "ऐ": 237, "ऋ": 238, "ऊ": 239, "़": 240, "ॉ": 241, "ऱ": 242, "ॐ": 243, "ॅ": 244, "ऽ": 245, "ऑ": 246, "॰": 247, "ॊ": 248, "ॠ": 249, "ऎ": 250, "ळ": 251, "ऒ": 252, "ॆ": 253, "ॽ": 254, "ऩ": 255, "▁": 256, "<pad>": 257}, "large_bn": {"<unk>": 0, "য়": 1, "ার": 2, "▁ক": 3, "▁স": 4, "▁ব": 5, "▁প": 6, "ের": 7, "্র": 8, "্য": 9, "▁আ": 10, "▁এ": 11, "ান": 12, "▁ম": 13, "▁ন": 14, "▁হ": 15, "▁দ": 16, "▁ত": 17, "▁কর": 18, "্ত": 19, "েন": 20, "য়ে": 21, "▁অ": 22, "▁জ": 23, "কে": 24, "িন": 25, "তে": 26, "ায়": 27, "▁প্র": 28, "াল": 29, "িক": 30, "▁য": 31, "▁র": 32, "▁শ": 33, "ছে": 34, "াম": 35, "ির": 36, "বে": 37, "লে": 38, "ড়": 39, "▁গ": 40, "▁চ": 41, "্ব": 42, "▁বি": 43, "টি": 44, "াদ": 45, "▁ভ": 46, "াস": 47, "িয়ে": 48, "র্": 49, "▁ও": 50, "াক": 51, "▁উ": 52, "াই": 53, "িত": 54, "্ট": 55, "▁পর": 56, "্ষ": 57, "িল": 58, "▁এক": 59, "ুর": 60, "▁করে": 61, "▁থ": 62, "াত": 63, "ুল": 64, "াজ": 65, "▁দে": 66, "▁সম": 67, "তি": 68, "▁বা": 69, "ন্": 70, "▁আম": 71, "লা": 72, "্থ": 73, "▁ফ": 74, "▁খ": 75, "▁ছ": 76, "নে": 77, "াব": 78, "িয়": 79, "▁ই": 80, "▁না": 81, "্যা": 82, "্প": 83, "রা": 84, "দের": 85, "েশ": 86, "ঙ্": 87, "ওয়": 88, "ছেন": 89, "োন": 90, "▁হয়ে": 91, "▁সে": 92, "ন্ত": 93, "ন্য": 94, "ক্ষ": 95, "বার": 96, "▁তা": 97, "িস": 98, "▁এই": 99, "▁তার": 100, "▁ল": 101, "েকে": 102, "টা": 103, "্ম": 104, "োগ": 105, "ঙ্গ": 106, "▁নি": 107, "াপ": 108, "চ্": 109, "েল": 110, "▁হয়": 111, "দ্": 112, "▁থেকে": 113, "াদের": 114, "ক্ত": 115, "কার": 116, "▁আর": 117, "াহ": 118, "▁পার": 119, "না": 120, "▁ধ": 121, "▁ঘ": 122, "নের": 123, "িনি": 124, "▁বল": 125, "▁ট": 126, "ীর": 127, "▁জান": 128, "ধ্য": 129, "▁এব": 130, "▁যে": 131, "াবে": 132, "▁এবং": 133, "▁করা": 134, "▁কি": 135, "▁সং": 136, "▁নে": 137, "▁ড": 138, "ুন": 139, "▁পা": 140, "▁পরি": 141, "ীয়": 142, "▁ব্য": 143, "বি": 144, "দ্ধ": 145, "▁উপ": 146, "স্থ": 147, "নি": 148, "রে": 149, "▁সা": 150, "▁তিনি": 151, "▁মা": 152, "▁জন্য": 153, "ষ্": 154, "িশ": 155, "ষ্ট": 156, "▁দু": 157, "▁মু": 158, "▁নিয়ে": 159, "তা": 160, "খন": 161, "▁নির": 162, "▁কার": 163, "ানে": 164, "্দ": 165, "▁দেখ": 166, "ছিল": 167, "▁হবে": 168, "জন": 169, "▁কোন": 170, "্ন": 171, "িতে": 172, "োর": 173, "▁বলে": 174, "▁কা": 175, "▁প্রতি": 176, "▁▁": 177, "া": 178, "ে": 179, "র": 180, "্": 181, "ি": 182, "ন": 183, "ক": 184, "য": 185, "ব": 186, "ত": 187, "স": 188, "ম": 189, "ল": 190, "়": 191, "প": 192, "দ": 193, "ু": 194, "হ": 195, "ো": 196, "জ": 197, "ট": 198, "শ": 199, "গ": 200, "ই": 201, "এ": 202, "ছ": 203, "আ": 204, "ী": 205, "চ": 206, "ও": 207, "ভ": 208, "থ": 209, "ড": 210, "ষ": 211, "ধ": 212, "খ": 213, "অ": 214, "ং": 215, "উ": 216, "ণ": 217, "ফ": 218, "ঠ": 219, "ৃ": 220, "ঁ": 221, "ূ": 222, "ঙ": 223, "ঘ": 224, "ঞ": 225, "ৈ": 226, "ৌ": 227, "ৎ": 228, "ঝ": 229, "ঢ": 230, "ঃ": 231, "ঐ": 232, "ঈ": 233, "ঋ": 234, "ঊ": 235, "ঔ": 236, "ৰ": 237, "ৗ": 238, "ৱ": 239, "": 240, "": 241, "": 242, "ঽ": 243, "": 244, "": 245, "ৄ": 246, "ৠ": 247, "": 248, "": 249, "৻": 250, "৺": 251, "": 252, "ঌ": 253, "৳": 254, "৴": 255, "▁": 256, "<pad>": 257}, "large_ml": {"<unk>": 0, "ന്": 1, "ക്": 2, "ത്": 3, "ന്ന": 4, "▁പ": 5, "ക്ക": 6, "തി": 7, "▁ക": 8, "്ട": 9, "ല്": 10, "▁സ": 11, "ും": 12, "▁വ": 13, "യി": 14, "▁മ": 15, "▁ന": 16, "ര്": 17, "▁അ": 18, "്പ": 19, "ച്": 20, "്ര": 21, "ുന്ന": 22, "ങ്": 23, "ത്തി": 24, "രി": 25, "മാ": 26, "ണ്": 27, "ള്": 28, "ട്ട": 29, "ത്ത": 30, "്യ": 31, "പ്പ": 32, "റ്": 33, "സ്": 34, "ിയ": 35, "ച്ച": 36, "▁ത": 37, "ങ്ങ": 38, "▁എ": 39, "ണ്ട": 40, "▁ഇ": 41, "▁ച": 42, "ുക": 43, "ടെ": 44, "▁ആ": 45, "ില": 46, "ാണ്": 47, "രു": 48, "ിക്ക": 49, "▁പ്ര": 50, "ില്": 51, "റ്റ": 52, "▁വി": 53, "ാന": 54, "റെ": 55, "ഞ്": 56, "ിച്ച": 57, "ായി": 58, "▁ര": 59, "ള്ള": 60, "▁ബ": 61, "ുന്നു": 62, "ിക": 63, "െയ": 64, "ക്ക്": 65, "ന്ന്": 66, "ന്റെ": 67, "▁ഉ": 68, "ടു": 69, "▁ജ": 70, "▁നി": 71, "ായ": 72, "ുടെ": 73, "വി": 74, "▁ഒ": 75, "ാര": 76, "▁സ്": 77, "ക്ഷ": 78, "ങ്ങള": 79, "െന്ന": 80, "ുള്ള": 81, "റി": 82, "ത്ര": 83, "ല്ല": 84, "ദ്": 85, "▁ശ": 86, "ഞ്ഞ": 87, "▁എന്ന": 88, "ാര്": 89, "ിന": 90, "ാന്": 91, "▁സം": 92, "രിക്ക": 93, "ുമ": 94, "ാല": 95, "മായി": 96, "▁ല": 97, "യും": 98, "രുന്നു": 99, "പ്പെ": 100, "യാ": 101, "▁കു": 102, "ടി": 103, "▁മു": 104, "വാ": 105, "ദേ": 106, "്മ": 107, "ണ്ട്": 108, "▁നട": 109, "ങ്ക": 110, "ില്ല": 111, "▁മാ": 112, "▁ചെയ": 113, "യില": 114, "സി": 115, "▁ഭ": 116, "▁പി": 117, "ുന്നത്": 118, "ാവ": 119, "▁കോ": 120, "െന്ന്": 121, "▁ഗ": 122, "ണം": 123, "ന്ത്": 124, "േഷ": 125, "നി": 126, "▁ഒരു": 127, "യില്": 128, "▁പറ": 129, "തു": 130, "▁പോ": 131, "മ്മ": 132, "ോഗ": 133, "ങ്ങള്": 134, "▁ദ": 135, "ിവ": 136, "രാ": 137, "▁പു": 138, "മായ": 139, "ച്ച്": 140, "▁കേ": 141, "ത്ത്": 142, "▁കൊ": 143, "▁അവ": 144, "ാക്ക": 145, "ിൽ": 146, "ുവ": 147, "ത്തില്": 148, "ത്തില": 149, "ംഗ": 150, "ത്തെ": 151, "▁ഹ": 152, "സ്ഥ": 153, "▁ഫ": 154, "▁രാ": 155, "▁തു": 156, "▁യ": 157, "ന്ദ": 158, "രെ": 159, "റ്റ്": 160, "ട്": 161, "മ്പ": 162, "ദ്യ": 163, "▁നേ": 164, "വും": 165, "ാം": 166, "െന്നും": 167, "യ്": 168, "ുകള": 169, "പ്പോ": 170, "▁ഡ": 171, "ന്ത": 172, "തിന": 173, "യുടെ": 174, "▁കാ": 175, "മാണ്": 176, "്": 177, "▁▁": 178, "ി": 179, "ന": 180, "ക": 181, "ത": 182, "ു": 183, "ാ": 184, "ര": 185, "യ": 186, "ട": 187, "പ": 188, "ല": 189, "മ": 190, "െ": 191, "വ": 192, "ം": 193, "സ": 194, "റ": 195, "ച": 196, "ണ": 197, "ള": 198, "ോ": 199, "ങ": 200, "േ": 201, "ദ": 202, "അ": 203, "ീ": 204, "ഷ": 205, "ശ": 206, "എ": 207, "ഗ": 208, "ജ": 209, "ൂ": 210, "ധ": 211, "ഞ": 212, "ബ": 213, "ർ": 214, "ൽ": 215, "ഇ": 216, "ഹ": 217, "ആ": 218, "ൊ": 219, "ഭ": 220, "ഡ": 221, "ഴ": 222, "ൻ": 223, "ഉ": 224, "ഥ": 225, "ൾ": 226, "ഒ": 227, "ൈ": 228, "ഫ": 229, "ഖ": 230, "ൃ": 231, "ഘ": 232, "ഏ": 233, "ഈ": 234, "ഓ": 235, "ൗ": 236, "ഐ": 237, "ൺ": 238, "ഠ": 239, "ഛ": 240, "ഊ": 241, "ഔ": 242, "ഢ": 243, "ഃ": 244, "ൌ": 245, "ഋ": 246, "ഌ": 247, "ഝ": 248, "ൡ": 249, "ൿ": 250, "഼": 251, "ൎ": 252, "ൟ": 253, "ഽ": 254, "ഺ": 255, "▁": 256, "<pad>": 257}, "large_hi": {"<unk>": 0, "▁क": 1, "▁स": 2, "▁ह": 3, "▁म": 4, "▁प": 5, "ार": 6, "ने": 7, "ें": 8, "▁ब": 9, "▁के": 10, "्र": 11, "▁है": 12, "▁ज": 13, "या": 14, "▁द": 15, "▁र": 16, "▁व": 17, "▁में": 18, "▁ल": 19, "▁अ": 20, "ों": 21, "▁की": 22, "▁न": 23, "▁को": 24, "▁ग": 25, "ान": 26, "▁आ": 27, "र्": 28, "ता": 29, "▁कि": 30, "▁से": 31, "▁इ": 32, "▁भ": 33, "▁उ": 34, "▁का": 35, "▁कर": 36, "▁त": 37, "ना": 38, "्य": 39, "▁ने": 40, "▁पर": 41, "िक": 42, "ला": 43, "▁श": 44, "▁औ": 45, "▁च": 46, "▁और": 47, "▁प्र": 48, "▁इस": 49, "ही": 50, "स्": 51, "▁ए": 52, "ाल": 53, "क्": 54, "हा": 55, "▁हो": 56, "ड़": 57, "▁हैं": 58, "▁जा": 59, "▁य": 60, "ित": 61, "▁थ": 62, "वा": 63, "▁भी": 64, "िया": 65, "ाम": 66, "िल": 67, "िए": 68, "ते": 69, "▁ख": 70, "के": 71, "िय": 72, "▁बा": 73, "ंग": 74, "▁फ": 75, "▁वि": 76, "हीं": 77, "त्र": 78, "▁स्": 79, "ेश": 80, "न्": 81, "कर": 82, "ती": 83, "▁सा": 84, "री": 85, "ले": 86, "से": 87, "▁रा": 88, "▁एक": 89, "▁लिए": 90, "रा": 91, "▁नहीं": 92, "ारी": 93, "▁सं": 94, "नी": 95, "गा": 96, "िस": 97, "्या": 98, "ति": 99, "▁ले": 100, "सी": 101, "▁सम": 102, "▁ट": 103, "ोग": 104, "ुर": 105, "▁अप": 106, "▁दे": 107, "िन": 108, "▁रह": 109, "▁ही": 110, "▁हु": 111, "का": 112, "▁ड": 113, "▁किया": 114, "क्ष": 115, "ंद": 116, "▁मु": 117, "वार": 118, "त्": 119, "ाय": 120, "ुल": 121, "▁नि": 122, "▁कार": 123, "ली": 124, "▁गया": 125, "ां": 126, "ियों": 127, "▁पह": 128, "की": 129, "्ट": 130, "▁कहा": 131, "न्ह": 132, "िला": 133, "▁घ": 134, "▁था": 135, "▁तो": 136, "▁करने": 137, "▁साथ": 138, "कार": 139, "ास": 140, "मा": 141, "▁सि": 142, "▁उन्ह": 143, "▁यह": 144, "▁कु": 145, "▁रहे": 146, "्म": 147, "ंच": 148, "▁उन": 149, "▁बाद": 150, "रो": 151, "▁पू": 152, "▁लोग": 153, "ाह": 154, "▁अध": 155, "ंड": 156, "गी": 157, "▁सु": 158, "भा": 159, "▁दो": 160, "▁छ": 161, "▁राज": 162, "रे": 163, "▁आप": 164, "कि": 165, "▁उस": 166, "▁दिया": 167, "ढ़": 168, "भी": 169, "▁अन": 170, "िर": 171, "▁▁": 172, "ा": 173, "क": 174, "र": 175, "े": 176, "न": 177, "्": 178, "ी": 179, "स": 180, "ि": 181, "ं": 182, "ह": 183, "म": 184, "त": 185, "ल": 186, "ो": 187, "प": 188, "य": 189, "व": 190, "द": 191, "ज": 192, "ब": 193, "ग": 194, "ै": 195, "ु": 196, "ट": 197, "श": 198, "ए": 199, "च": 200, "अ": 201, "ड": 202, "भ": 203, "ू": 204, "आ": 205, "इ": 206, "थ": 207, "ख": 208, "ध": 209, "उ": 210, "फ": 211, "़": 212, "ई": 213, "ष": 214, "औ": 215, "ण": 216, "ौ": 217, "छ": 218, "घ": 219, "ॉ": 220, "ठ": 221, "ओ": 222, "ढ": 223, "ृ": 224, "झ": 225, "ऐ": 226, "ऑ": 227, "ँ": 228, "ञ": 229, "ऊ": 230, "ः": 231, "ऋ": 232, "ॅ": 233, "ऩ": 234, "ऱ": 235, "ङ": 236, "ऎ": 237, "ळ": 238, "ॐ": 239, "॰": 240, "ऍ": 241, "ऽ": 242, "ॢ": 243, "ॆ": 244, "ॊ": 245, "ॠ": 246, "॒": 247, "ॄ": 248, "॔": 249, "ऄ": 250, "ऒ": 251, "ॽ": 252, "॑": 253, "॓": 254, "ऴ": 255, "▁": 256, "<pad>": 257}, "large_doi": {"<unk>": 0, "▁क": 1, "▁द": 2, "▁स": 3, "▁ब": 4, "▁ज": 5, "▁प": 6, "▁म": 7, "ने": 8, "▁ह": 9, "ह्": 10, "▁त": 11, "▁ग": 12, "ां": 13, "ार": 14, "▁च": 15, "▁न": 16, "ें": 17, "▁अ": 18, "▁ल": 19, "▁आ": 20, "्र": 21, "▁दे": 22, "▁र": 23, "▁इ": 24, "िय": 25, "▁उ": 26, "▁कर": 27, "दा": 28, "ना": 29, "क्": 30, "▁ते": 31, "दे": 32, "▁ऐ": 33, "▁दी": 34, "न्": 35, "▁हो": 36, "्त": 37, "ान": 38, "्य": 39, "ड़": 40, "▁दा": 41, "▁पर": 42, "▁गी": 43, "▁भ": 44, "न्न": 45, "ता": 46, "▁ख": 47, "दी": 48, "री": 49, "र्": 50, "▁ने": 51, "▁श": 52, "▁व": 53, "▁बी": 54, "क्ख": 55, "न्नै": 56, "▁ऎ": 57, "▁ए": 58, "▁जे": 59, "▁जा": 60, "▁प्र": 61, "▁कन्नै": 62, "ाल": 63, "िक": 64, "ित": 65, "▁फ": 66, "ास": 67, "्ल": 68, "▁नेई": 69, "▁ओ": 70, "▁अप": 71, "▁इस": 72, "नी": 73, "ेआ": 74, "रा": 75, "ेई": 76, "▁थ": 77, "▁जि": 78, "्ह": 79, "▁की": 80, "▁को": 81, "▁गै": 82, "ह्ल": 83, "ियां": 84, "गी": 85, "्थ": 86, "ती": 87, "▁दि": 88, "▁ड": 89, "▁एह्": 90, "्ट": 91, "▁कु": 92, "▁सम": 93, "ेँ": 94, "ारी": 95, "्म": 96, "ला": 97, "▁उस": 98, "▁उप": 99, "▁ओह्": 100, "ाह": 101, "ल्ल": 102, "▁कि": 103, "ंग": 104, "स्त": 105, "▁घ": 106, "ियै": 107, "्प": 108, "▁नि": 109, "ंदा": 110, "▁इक": 111, "ाई": 112, "ंद": 113, "नें": 114, "ाम": 115, "▁नेईं": 116, "▁सु": 117, "ाज": 118, "▁लेई": 119, "ब्": 120, "▁मु": 121, "रे": 122, "▁के": 123, "ाह्": 124, "च्": 125, "▁सं": 126, "ैं": 127, "▁सक": 128, "▁य": 129, "िया": 130, "ोग": 131, "▁ध": 132, "▁करने": 133, "ोज": 134, "▁आह्ल": 135, "▁छ": 136, "वा": 137, "ंदे": 138, "ात": 139, "▁से": 140, "▁मि": 141, "▁जिस": 142, "वि": 143, "एं": 144, "ली": 145, "क्क": 146, "त्त": 147, "▁होई": 148, "▁में": 149, "द्": 150, "यां": 151, "्स": 152, "ति": 153, "ड़ी": 154, "ियें": 155, "मां": 156, "▁औ": 157, "▁अपने": 158, "▁कोई": 159, "▁वि": 160, "ते": 161, "क्ष": 162, "कर": 163, "▁सर": 164, "ज्": 165, "▁लो": 166, "ंदी": 167, "▁पै": 168, "ले": 169, "▁मे": 170, "यै": 171, "या": 172, "्क": 173, "▁सू": 174, "ट्ट": 175, "ानी": 176, "▁आस्त": 177, "रू": 178, "म्म": 179, "▁थमां": 180, "्या": 181, "मा": 182, "▁आस्तै": 183, "▁▁": 184, "ा": 185, "े": 186, "्": 187, "र": 188, "न": 189, "ी": 190, "क": 191, "द": 192, "ं": 193, "स": 194, "त": 195, "ि": 196, "ह": 197, "ल": 198, "म": 199, "ज": 200, "प": 201, "ै": 202, "ग": 203, "ब": 204, "ो": 205, "य": 206, "च": 207, "ु": 208, "आ": 209, "ड": 210, "ई": 211, "व": 212, "श": 213, "ख": 214, "ू": 215, "इ": 216, "अ": 217, "ट": 218, "उ": 219, "ऐ": 220, "भ": 221, "ध": 222, "ए": 223, "़": 224, "ँ": 225, "थ": 226, "'": 227, "फ": 228, "ौ": 229, "ओ": 230, "ऎ": 231, "छ": 232, "घ": 233, "ढ": 234, "ठ": 235, "ण": 236, "ष": 237, "झ": 238, "ऽ": 239, "औ": 240, "ृ": 241, "ञ": 242, "ऊ": 243, "ऱ": 244, "ङ": 245, "ॉ": 246, "ः": 247, "ऋ": 248, "ऑ": 249, "॰": 250, "ऩ": 251, "ळ": 252, "ऻ": 253, "ॅ": 254, "ॎ": 255, "▁": 256, "<pad>": 257}, "large_ur": {"<unk>": 0, "▁ک": 1, "▁ا": 2, "▁م": 3, "▁ہ": 4, "یں": 5, "▁ب": 6, "▁س": 7, "▁ن": 8, "▁ت": 9, "ور": 10, "▁کی": 11, "▁پ": 12, "▁کے": 13, "▁ج": 14, "ان": 15, "▁د": 16, "ار": 17, "▁و": 18, "▁میں": 19, "▁ہے": 20, "یا": 21, "▁اور": 22, "وں": 23, "▁کر": 24, "▁ر": 25, "▁ل": 26, "▁اس": 27, "ال": 28, "▁سے": 29, "▁کا": 30, "▁کو": 31, "▁گ": 32, "ات": 33, "▁کہ": 34, "ائ": 35, "▁ہو": 36, "▁آ": 37, "▁ع": 38, "ام": 39, "یک": 40, "▁ان": 41, "▁ح": 42, "ھی": 43, "نے": 44, "▁خ": 45, "▁نے": 46, "ری": 47, "▁ش": 48, "▁پر": 49, "یہ": 50, "ین": 51, "▁چ": 52, "▁ہیں": 53, "▁ف": 54, "▁نہ": 55, "▁ق": 56, "یر": 57, "اہ": 58, "لی": 59, "ئے": 60, "لا": 61, "▁یہ": 62, "تا": 63, "نا": 64, "▁بھی": 65, "▁تھ": 66, "تے": 67, "▁ال": 68, "اد": 69, "▁ص": 70, "ست": 71, "ئی": 72, "اب": 73, "▁ایک": 74, "▁ط": 75, "▁تو": 76, "▁نہیں": 77, "تی": 78, "▁وہ": 79, "ند": 80, "▁رہ": 81, "نی": 82, "▁اپ": 83, "لہ": 84, "سی": 85, "▁ز": 86, "اک": 87, "▁کیا": 88, "می": 89, "▁جو": 90, "ون": 91, "ید": 92, "ول": 93, "▁ای": 94, "▁،": 95, "ائی": 96, "ود": 97, "▁ہم": 98, "▁تھا": 99, "از": 100, "▁لی": 101, "اری": 102, "گر": 103, "ائے": 104, "ٹی": 105, "وم": 106, "کھ": 107, "▁دی": 108, "▁ڈ": 109, "لم": 110, "انی": 111, "ھر": 112, "▁وال": 113, "▁مع": 114, "اں": 115, "▁ہی": 116, "▁دو": 117, "▁بی": 118, "▁▁": 119, "ا": 120, "ی": 121, "ک": 122, "ر": 123, "و": 124, "ہ": 125, "ن": 126, "ے": 127, "م": 128, "ت": 129, "ل": 130, "س": 131, "ب": 132, "د": 133, "ں": 134, "ھ": 135, "ج": 136, "پ": 137, "ع": 138, "گ": 139, "ئ": 140, "ق": 141, "ف": 142, "ح": 143, "ش": 144, "ز": 145, "خ": 146, "ٹ": 147, "چ": 148, "ص": 149, "،": 150, "آ": 151, "ط": 152, "ڈ": 153, "ض": 154, "ڑ": 155, "ظ": 156, "غ": 157, "ذ": 158, "ث": 159, "ِ": 160, "ُ": 161, "ي": 162, "ؤ": 163, "ٰ": 164, "َ": 165, "ء": 166, "؟": 167, "ك": 168, "ّ": 169, "ه": 170, "ً": 171, "ۃ": 172, "ـ": 173, "ْ": 174, "ى": 175, "ۂ": 176, "ؓ": 177, "ؒ": 178, "؛": 179, "أ": 180, "ژ": 181, "ؐ": 182, "ؔ": 183, "ة": 184, "ۓ": 185, "ؑ": 186, "٭": 187, "ٴ": 188, "إ": 189, "ٗ": 190, "ٔ": 191, "ٖ": 192, "ٍ": 193, "ٌ": 194, "؎": 195, "ٓ": 196, "ۆ": 197, "ێ": 198, "؍": 199, "٬": 200, "٫": 201, "ٲ": 202, "ٕ": 203, "ۍ": 204, "ۀ": 205, "٘": 206, "ې": 207, "ٙ": 208, "ە": 209, "ٱ": 210, "ڪ": 211, "ڻ": 212, "ٛ": 213, "ړ": 214, "ٮ": 215, "ښ": 216, "؞": 217, "ۅ": 218, "ۏ": 219, "ٚ": 220, "ڄ": 221, "؏": 222, "ٻ": 223, "څ": 224, "ڊ": 225, "ڙ": 226, "ٽ": 227, "ڳ": 228, "ؕ": 229, "ځ": 230, "ږ": 231, "ڃ": 232, "ڷ": 233, "ٟ": 234, "ډ": 235, "ڽ": 236, "ۇ": 237, "ٞ": 238, "ڏ": 239, "ڼ": 240, "ڌ": 241, "ڎ": 242, "ڥ": 243, "ڦ": 244, "ګ": 245, "ټ": 246, "ٿ": 247, "ڀ": 248, "ڋ": 249, "ڍ": 250, "ڞ": 251, "ۉ": 252, "ۑ": 253, "ؠ": 254, "ٝ": 255, "▁": 256, "<pad>": 257}, "large_mr": {"<unk>": 0, "या": 1, "्या": 2, "▁क": 3, "▁आ": 4, "▁स": 5, "▁प": 6, "▁म": 7, "्र": 8, "ार": 9, "▁त": 10, "▁अ": 11, "ला": 12, "▁व": 13, "ना": 14, "▁ह": 15, "ात": 16, "▁द": 17, "र्": 18, "हे": 19, "▁या": 20, "ले": 21, "्य": 22, "▁आहे": 23, "ां": 24, "च्या": 25, "▁न": 26, "▁ज": 27, "ही": 28, "ली": 29, "रा": 30, "▁ब": 31, "ती": 32, "ून": 33, "चा": 34, "ल्या": 35, "ने": 36, "▁अस": 37, "िक": 38, "▁त्या": 39, "▁श": 40, "वा": 41, "ता": 42, "ची": 43, "▁प्र": 44, "ण्या": 45, "चे": 46, "▁ग": 47, "क्": 48, "▁कर": 49, "नी": 50, "्ह": 51, "▁हो": 52, "▁का": 53, "वर": 54, "▁के": 55, "स्": 56, "सा": 57, "▁भ": 58, "ंत": 59, "▁आण": 60, "▁घ": 61, "▁उ": 62, "▁ना": 63, "▁आणि": 64, "ित": 65, "ेत": 66, "▁वि": 67, "▁रा": 68, "▁र": 69, "मा": 70, "▁यां": 71, "▁ए": 72, "▁मा": 73, "▁य": 74, "ते": 75, "▁पा": 76, "ंद": 77, "ील": 78, "▁दि": 79, "त्": 80, "▁ल": 81, "का": 82, "▁च": 83, "ठी": 84, "णा": 85, "▁झ": 86, "क्ष": 87, "▁वा": 88, "ध्य": 89, "▁नि": 90, "▁ख": 91, "री": 92, "▁सं": 93, "्ट": 94, "▁झा": 95, "▁फ": 96, "साठी": 97, "ळे": 98, "▁मु": 99, "▁सु": 100, "▁स्": 101, "कार": 102, "मु": 103, "ास": 104, "▁दे": 105, "णार": 106, "हि": 107, "▁त्यां": 108, "वे": 109, "▁नाही": 110, "ध्ये": 111, "णी": 112, "▁म्ह": 113, "रो": 114, "्यां": 115, "▁ला": 116, "▁को": 117, "णे": 118, "मध्ये": 119, "वी": 120, "शी": 121, "ंग": 122, "▁सा": 123, "▁जा": 124, "कर": 125, "▁ट": 126, "ण्यात": 127, "ान": 128, "वि": 129, "लं": 130, "▁हे": 131, "्री": 132, "द्": 133, "मुळे": 134, "ष्ट": 135, "▁ठ": 136, "▁एक": 137, "्हा": 138, "▁आहेत": 139, "▁आप": 140, "डे": 141, "▁इ": 142, "▁पर": 143, "से": 144, "▁पु": 145, "▁ते": 146, "हा": 147, "▁यांनी": 148, "ल्": 149, "▁भा": 150, "ळी": 151, "▁राज": 152, "▁तर": 153, "बा": 154, "▁मो": 155, "ळा": 156, "▁कार": 157, "दी": 158, "तील": 159, "ारी": 160, "▁ये": 161, "की": 162, "डी": 163, "▁मि": 164, "मी": 165, "पा": 166, "▁बा": 167, "ोल": 168, "दा": 169, "▁▁": 170, "ा": 171, "्": 172, "र": 173, "े": 174, "त": 175, "य": 176, "ी": 177, "क": 178, "ल": 179, "न": 180, "स": 181, "व": 182, "ि": 183, "ं": 184, "ह": 185, "म": 186, "च": 187, "प": 188, "ण": 189, "ो": 190, "द": 191, "आ": 192, "ु": 193, "ग": 194, "ज": 195, "श": 196, "अ": 197, "ट": 198, "ब": 199, "ू": 200, "ड": 201, "ध": 202, "ळ": 203, "ष": 204, "भ": 205, "ख": 206, "ठ": 207, "घ": 208, "थ": 209, "उ": 210, "फ": 211, "ए": 212, "झ": 213, "ई": 214, "ढ": 215, "ॉ": 216, "इ": 217, "ृ": 218, "ऊ": 219, "ै": 220, "ॅ": 221, "ऱ": 222, "ौ": 223, "ओ": 224, "ँ": 225, "छ": 226, "ऑ": 227, "ञ": 228, "ः": 229, "ऐ": 230, "़": 231, "औ": 232, "ऋ": 233, "ऍ": 234, "ॲ": 235, "ङ": 236, "ऽ": 237, "ॐ": 238, "ॆ": 239, "ॊ": 240, "ॄ": 241, "ऴ": 242, "ऩ": 243, "ऎ": 244, "ॕ": 245, "ॠ": 246, "॑": 247, "ऒ": 248, "॓": 249, "॔": 250, "॰": 251, "ॽ": 252, "ऌ": 253, "॒": 254, "ऺ": 255, "▁": 256, "<pad>": 257}, "large_gu": {"<unk>": 0, "▁ક": 1, "મા": 2, "▁પ": 3, "▁સ": 4, "વા": 5, "ને": 6, "▁ત": 7, "્ય": 8, "ના": 9, "▁છ": 10, "▁આ": 11, "▁જ": 12, "▁અ": 13, "્ર": 14, "માં": 15, "ાર": 16, "▁છે": 17, "▁હ": 18, "ની": 19, "▁મ": 20, "▁ર": 21, "▁વ": 22, "ું": 23, "▁બ": 24, "▁કર": 25, "તા": 26, "▁તે": 27, "▁દ": 28, "ર્": 29, "▁ન": 30, "▁લ": 31, "▁એ": 32, "▁શ": 33, "▁મા": 34, "▁અને": 35, "થી": 36, "▁કે": 37, "▁ગ": 38, "લા": 39, "રા": 40, "્ટ": 41, "્યા": 42, "રી": 43, "નો": 44, "▁પ્ર": 45, "▁આવ": 46, "▁સા": 47, "િક": 48, "ટે": 49, "યા": 50, "▁પર": 51, "▁ભ": 52, "▁હત": 53, "▁થ": 54, "▁ચ": 55, "▁ખ": 56, "હે": 57, "સ્": 58, "▁ફ": 59, "▁વિ": 60, "▁ઉ": 61, "ક્": 62, "ાવ": 63, "ન્": 64, "લી": 65, "ાય": 66, "મે": 67, "▁પણ": 68, "▁કો": 69, "ંગ": 70, "▁માટે": 71, "▁જે": 72, "કો": 73, "▁રા": 74, "ંત": 75, "▁એક": 76, "િત": 77, "નું": 78, "શે": 79, "વામાં": 80, "▁કરી": 81, "વી": 82, "▁જો": 83, "▁હો": 84, "▁પા": 85, "▁સ્": 86, "રો": 87, "્યું": 88, "રે": 89, "હી": 90, "્યો": 91, "લ્": 92, "કે": 93, "યો": 94, "▁પો": 95, "▁વા": 96, "ણી": 97, "▁તેમ": 98, "▁આપ": 99, "િયા": 100, "ડી": 101, "થે": 102, "ારે": 103, "તી": 104, "ામ": 105, "▁ઘ": 106, "▁ટ": 107, "ત્": 108, "▁સં": 109, "લે": 110, "ાન": 111, "▁સાથે": 112, "▁મો": 113, "▁બા": 114, "▁કાર": 115, "▁ધ": 116, "ેશ": 117, "કાર": 118, "તિ": 119, "▁ના": 120, "▁ડ": 121, "કા": 122, "ણે": 123, "▁લો": 124, "▁સમ": 125, "્રી": 126, "▁હતી": 127, "▁સુ": 128, "વે": 129, "ડા": 130, "જી": 131, "તે": 132, "▁તો": 133, "ાગ": 134, "▁વધ": 135, "ક્ષ": 136, "ાલ": 137, "ંધ": 138, "▁મુ": 139, "▁બે": 140, "▁રહ": 141, "▁કરવા": 142, "ંદ": 143, "ટી": 144, "▁જા": 145, "ત્ર": 146, "ારી": 147, "▁નિ": 148, "ાસ": 149, "▁મળ": 150, "ાઈ": 151, "▁નથી": 152, "સે": 153, "▁ઓ": 154, "રૂ": 155, "▁ઉપ": 156, "▁તમા": 157, "કી": 158, "િવ": 159, "્યારે": 160, "▁આવે": 161, "▁હતા": 162, "▁મહ": 163, "તો": 164, "દી": 165, "સ્ટ": 166, "સા": 167, "્રે": 168, "▁હતો": 169, "▁મે": 170, "સી": 171, "▁આવી": 172, "ણા": 173, "▁સર": 174, "ન્ટ": 175, "▁લોકો": 176, "▁રહે": 177, "▁રાજ": 178, "્વા": 179, "િલ્": 180, "લો": 181, "▁▁": 182, "ા": 183, "ે": 184, "ર": 185, "ન": 186, "્": 187, "ી": 188, "ક": 189, "મ": 190, "ત": 191, "વ": 192, "ો": 193, "ં": 194, "સ": 195, "પ": 196, "ય": 197, "િ": 198, "લ": 199, "જ": 200, "ુ": 201, "હ": 202, "ટ": 203, "દ": 204, "ગ": 205, "છ": 206, "શ": 207, "બ": 208, "થ": 209, "આ": 210, "અ": 211, "ણ": 212, "ડ": 213, "એ": 214, "ધ": 215, "ચ": 216, "ખ": 217, "ભ": 218, "ૂ": 219, "ળ": 220, "ફ": 221, "ઈ": 222, "ઓ": 223, "ષ": 224, "ઇ": 225, "ઉ": 226, "ઘ": 227, "ઝ": 228, "ઠ": 229, "ૃ": 230, "ૈ": 231, "ૌ": 232, "ઢ": 233, "ૉ": 234, "ઃ": 235, "ઊ": 236, "ઞ": 237, "ૅ": 238, "ઑ": 239, "ઔ": 240, "ઋ": 241, "ઐ": 242, "ઍ": 243, "ઁ": 244, "ઙ": 245, "઼": 246, "ૐ": 247, "ૠ": 248, "ૢ": 249, "": 250, "ઽ": 251, "ૄ": 252, "": 253, "૱": 254, "": 255, "▁": 256, "<pad>": 257}, "large_kn": {"<unk>": 0, "▁ಮ": 1, "▁ಸ": 2, "ತ್": 3, "ಲ್": 4, "▁ಕ": 5, "ಿದ": 6, "ಾರ": 7, "ನ್": 8, "ಲ್ಲ": 9, "▁ನ": 10, "ಂದ": 11, "▁ಅ": 12, "ರು": 13, "ಾಗ": 14, "▁ಪ": 15, "▁ಹ": 16, "್ರ": 17, "ತ್ತ": 18, "▁ಬ": 19, "ನ್ನ": 20, "ಿಸ": 21, "ಗಳ": 22, "್ಯ": 23, "ಕ್": 24, "ರ್": 25, "▁ವ": 26, "ಗೆ": 27, "ಲ್ಲಿ": 28, "್ದ": 29, "ನ್ನು": 30, "ರಿ": 31, "▁ಆ": 32, "▁ತ": 33, "ೆಯ": 34, "▁ಎ": 35, "▁ಇ": 36, "ಿದ್ದ": 37, "ಸ್": 38, "ಿಯ": 39, "ಿಕ": 40, "ುವ": 41, "▁ಮಾ": 42, "್ಟ": 43, "ುತ್ತ": 44, "▁ರ": 45, "▁ಪ್ರ": 46, "ದು": 47, "▁ಜ": 48, "ಾಗಿ": 49, "ಂತ": 50, "ಿದೆ": 51, "ಕ್ಕ": 52, "▁ದ": 53, "ಂದು": 54, "ಿನ": 55, "▁ಗ": 56, "ರೆ": 57, "ಂಡ": 58, "ವು": 59, "▁ಶ": 60, "ಾನ": 61, "▁ವಿ": 62, "ತ್ತು": 63, "ಾಯ": 64, "ತಿ": 65, "ಾದ": 66, "▁ಮಾಡ": 67, "▁ನಿ": 68, "ದಲ್ಲಿ": 69, "▁ಈ": 70, "▁ಅವ": 71, "ಿಗೆ": 72, "ಲು": 73, "ಟ್ಟ": 74, "ಗಳು": 75, "ಾರೆ": 76, "▁ಚ": 77, "ಕ್ಷ": 78, "್ಮ": 79, "▁ಉ": 80, "▁ಸಂ": 81, "▁ನೀ": 82, "ಿಂದ": 83, "ಾಲ": 84, "ಿತ": 85, "▁ಭ": 86, "▁ಒ": 87, "ಾಮ": 88, "ದೆ": 89, "▁ಮತ್ತು": 90, "▁ಯ": 91, "ತ್ರ": 92, "ಕ್ಕೆ": 93, "▁ಮು": 94, "ನೆ": 95, "ಾವ": 96, "ಡಿ": 97, "ಿದ್ದಾರೆ": 98, "▁ಸ್": 99, "ಂಗ": 100, "▁ಎಂದು": 101, "ಂಬ": 102, "ರುವ": 103, "ಡೆ": 104, "ೇಕ": 105, "ಿಲ್ಲ": 106, "ಳ್": 107, "ಮ್ಮ": 108, "ೇಶ": 109, "ಗಳನ್ನು": 110, "ಾಜ": 111, "ಳ್ಳ": 112, "ಚ್": 113, "ಷ್ಟ": 114, "ಪ್": 115, "ಿವ": 116, "ಟ್": 117, "ಾರ್": 118, "ವಾಗಿ": 119, "ುದ": 120, "ವನ್ನು": 121, "ರಿಸ": 122, "ಾಗಿದೆ": 123, "ಾರಿ": 124, "ೊಂಡ": 125, "ೇಳ": 126, "▁ಕಾರ": 127, "ಾಸ": 128, "ುದು": 129, "ನಾ": 130, "▁ಹೆ": 131, "ಚ್ಚ": 132, "▁ಹೊ": 133, "▁ಕೆ": 134, "▁ಬೆ": 135, "ಲೆ": 136, "ಬೇಕ": 137, "ತೆ": 138, "ಡ್": 139, "ಿದರು": 140, "ಾಣ": 141, "▁ಸಮ": 142, "್ಯಾ": 143, "▁ಇದ": 144, "ಿಸಿ": 145, "▁ಆದ": 146, "ೋಗ": 147, "▁ನೀಡ": 148, "▁ಲ": 149, "ಧ್ಯ": 150, "ೊಳ್ಳ": 151, "▁ಬಿ": 152, "ವಿ": 153, "▁ಕು": 154, "ಬ್": 155, "ರಿಗೆ": 156, "ತ್ಯ": 157, "▁ಮೂ": 158, "▁ಹಾಗ": 159, "ುತ್ತದೆ": 160, "ವೆ": 161, "▁ಸಾ": 162, "ಂತೆ": 163, "ರಣ": 164, "▁ಕೊ": 165, "ಕಾರ": 166, "ನು": 167, "ಪ್ಪ": 168, "ಗ್": 169, "ೆಯಲ್ಲಿ": 170, "ವಾ": 171, "▁ಸಿ": 172, "▁ರಾಜ": 173, "ಿಸುವ": 174, "್ಣ": 175, "▁ತಿ": 176, "ಡು": 177, "ೆಗೆ": 178, "ಲಿ": 179, "▁ಹೇಳ": 180, "್ಧ": 181, "ಗಳಲ್ಲಿ": 182, "▁▁": 183, "್": 184, "ಿ": 185, "ರ": 186, "ು": 187, "ಾ": 188, "ದ": 189, "ನ": 190, "ೆ": 191, "ತ": 192, "ಕ": 193, "ಲ": 194, "ಗ": 195, "ವ": 196, "ಸ": 197, "ಯ": 198, "ಮ": 199, "ಂ": 200, "ಳ": 201, "ಪ": 202, "ಡ": 203, "ಬ": 204, "ಹ": 205, "ೇ": 206, "ಟ": 207, "ಅ": 208, "ೂ": 209, "ಜ": 210, "ೊ": 211, "ೀ": 212, "ಚ": 213, "ಶ": 214, "ಣ": 215, "ೋ": 216, "ಷ": 217, "ಎ": 218, "ಧ": 219, "ಆ": 220, "ಇ": 221, "ಭ": 222, "ಥ": 223, "ೈ": 224, "ಖ": 225, "ಈ": 226, "ಉ": 227, "ಒ": 228, "ೃ": 229, "ಫ": 230, "ೌ": 231, "ಘ": 232, "ಠ": 233, "ಏ": 234, "ಐ": 235, "ಞ": 236, "ಓ": 237, "ಛ": 238, "ಊ": 239, "ೕ": 240, "ಢ": 241, "ಃ": 242, "ಔ": 243, "ಝ": 244, "ಋ": 245, "಼": 246, "ಙ": 247, "ೖ": 248, "ಱ": 249, "ಽ": 250, "ೞ": 251, "ಌ": 252, "": 253, "ೄ": 254, "ೠ": 255, "▁": 256, "<pad>": 257}, "large_mni": {"<unk>": 0, "▁ꯑ": 1, "▁ꯃ": 2, "ꯁꯤ": 3, "ꯒꯤ": 4, "ꯅꯤ": 5, "ꯁꯤꯡ": 6, "▁ꯂ": 7, "▁ꯑꯃ": 8, "▁ꯀ": 9, "▁ꯆ": 10, "▁ꯑꯁꯤ": 11, "ꯨꯡ": 12, "ꯅꯥ": 13, "ꯔꯤ": 14, "▁ꯄ": 15, "ꯌꯥ": 16, "▁ꯁ": 17, "ꯗꯨ": 18, "▁ꯍ": 19, "ꯥꯢ": 20, "▁ꯃꯁꯤꯡ": 21, "ꯥꯛ": 22, "▁ꯏ": 23, "ꯂꯤ": 24, "▁ꯃꯇ": 25, "ꯅꯨꯡ": 26, "▁ꯊ": 27, "▁ꯑꯃꯅꯤ": 28, "ꯗꯤ": 29, "ꯕꯥ": 30, "▁ꯂꯩ": 31, "▁ꯑꯗꯨ": 32, "▁ꯑꯣ": 33, "▁ꯅ": 34, "▁ꯃꯅꯨꯡ": 35, "▁ꯃꯤ": 36, "ꯋꯥ": 37, "ꯀꯤ": 38, "▁ꯇ": 39, "ꯗꯥ": 40, "ꯦꯝ": 41, "ꯈꯤ": 42, "ꯌꯦ": 43, "▁ꯈ": 44, "▁ꯆꯩ": 45, "▁ꯐ": 46, "ꯣꯟ": 47, "ꯥꯡ": 48, "▁ꯃꯇꯝ": 49, "ꯌꯥꯝ": 50, "ꯧꯕ": 51, "ꯨꯝ": 52, "▁ꯆꯩꯁꯤꯡ": 53, "ꯔꯤꯕ": 54, "▁ꯑꯦ": 55, "▁ꯃꯍ": 56, "ꯥꯟ": 57, "▁ꯗ": 58, "▁ꯂꯥꯢ": 59, "ꯣꯛ": 60, "ꯕꯤ": 61, "ꯜꯂꯤ": 62, "ꯁꯤꯡꯒꯤ": 63, "▁ꯃꯁꯤ": 64, "ꯂꯣꯟ": 65, "ꯥꯏ": 66, "ꯇꯩ": 67, "▁ꯑꯣꯏ": 68, "ꯄꯥꯛ": 69, "▁ꯃꯍꯥꯛ": 70, "▁ꯋꯥ": 71, "▁ꯑꯃꯒꯤ": 72, "▁ꯄꯨ": 73, "ꯃꯤ": 74, "▁ꯀꯧꯕ": 75, "▁ꯆꯜꯂꯤ": 76, "▁ꯃꯤꯇꯩ": 77, "ꯅꯤꯡ": 78, "ꯟꯅ": 79, "ꯑꯣ": 80, "▁ꯌꯦ": 81, "▁ꯃꯇꯝꯅꯤ": 82, "▁ꯃꯅꯨꯡꯗ": 83, "ꯡꯂ": 84, "▁ꯌꯥꯝ": 85, "▁ꯑꯗꯨꯒ": 86, "▁ꯃꯥ": 87, "▁ꯑꯣꯢ": 88, "꯭ꯔ": 89, "▁ꯌꯦꯡꯂ": 90, "ꯨꯞ": 91, "ꯛꯇ": 92, "ꯥꯎ": 93, "▁ꯑꯃꯁ": 94, "ꯂꯦꯝ": 95, "ꯤꯡ": 96, "ꯄꯥ": 97, "▁ꯎ": 98, "▁ꯁꯦꯝ": 99, "▁ꯑꯃꯁꯨꯡ": 100, "ꯦꯟ": 101, "▁ꯗꯅ": 102, "ꯌꯦꯛ": 103, "▁ꯃꯥꯂꯦꯝ": 104, "▁ꯑꯃꯗꯤ": 105, "ꯖꯤ": 106, "▁ꯁꯤ": 107, "ꯣꯡ": 108, "ꯣꯌ": 109, "▁ꯏꯌꯦꯛ": 110, "▁ꯂꯩꯄꯥꯛ": 111, "▁ꯄꯨꯋꯥ": 112, "▁ꯁꯦꯝꯄ": 113, "▁ꯏꯌꯦꯛꯅ": 114, "▁ꯃꯤꯇꯩꯀꯤ": 115, "▁ꯂꯤ": 116, "▁ꯑꯣꯏꯅ": 117, "ꯣꯔ": 118, "▁ꯒꯤ": 119, "ꯇꯥ": 120, "▁ꯉ": 121, "▁ꯌꯦꯡꯂꯗꯤ": 122, "▁ꯀꯥꯡ": 123, "ꯕꯨ": 124, "▁ꯃꯔ": 125, "▁ꯃꯈ": 126, "ꯁꯨ": 127, "▁ꯁꯥ": 128, "ꯄꯤ": 129, "ꯍꯤ": 130, "ꯣꯢ": 131, "ꯂꯣꯟꯒꯤ": 132, "ꯂꯝ": 133, "ꯔꯕ": 134, "ꯦꯛ": 135, "▁ꯌꯥ": 136, "▁ꯃꯇꯨꯡ": 137, "▁ꯊꯣꯛ": 138, "▁ꯋꯥꯔꯤ": 139, "▁ꯈꯨ": 140, "▁ꯅꯨ": 141, "▁ꯃꯤꯑꯣ": 142, "ꯨꯔ": 143, "▁ꯍꯥ": 144, "ꯪꯂ": 145, "▁ꯆꯍꯤ": 146, "ꯗꯒꯤ": 147, "ꯂꯨꯞ": 148, "▁ꯀꯥꯡꯂꯨꯞ": 149, "ꯋꯥꯢ": 150, "▁ꯄꯨꯋꯥꯂꯤ": 151, "ꯅꯦ": 152, "ꯥꯟꯕ": 153, "꯭ꯂ": 154, "ꯆꯥ": 155, "ꯅꯕꯥ": 156, "ꯈꯤꯕ": 157, "ꯐꯝ": 158, "ꯗꯝ": 159, "▁ꯏꯁ": 160, "ꯃꯛ": 161, "ꯃꯦ": 162, "▁ꯍꯧ": 163, "ꯤꯟ": 164, "ꯤꯁ": 165, "ꯠꯇ": 166, "ꯩꯅ": 167, "▁ꯆꯥꯎ": 168, "▁ꯂꯝ": 169, "▁ꯍꯥꯏ": 170, "▁ꯌ": 171, "▁ꯑꯣꯢꯅ": 172, "▁ꯀꯪꯂ": 173, "▁ꯔ": 174, "ꯒꯥ": 175, "▁ꯏꯁꯩ": 176, "▁ꯃꯍꯥꯛꯀꯤ": 177, "▁ꯁꯦꯝꯄꯅꯤ": 178, "ꯦꯜ": 179, "ꯥꯁ": 180, "▁ꯍꯥꯢ": 181, "ꯊꯧ": 182, "ꯅꯕ": 183, "▁ꯑꯁꯤꯒꯤ": 184, "▁ꯂꯧ": 185, "ꯕꯁꯤ": 186, "▁ꯅꯤꯡ": 187, "▁ꯀꯪꯂꯩ": 188, "▁ꯀꯤꯡ": 189, "▁ꯑꯩ": 190, "▁ꯃꯅꯨꯡꯗꯒꯤ": 191, "ꯦꯡ": 192, "ꯣꯏ": 193, "▁ꯀꯤꯡꯗꯝ": 194, "▁ꯅꯩꯅ": 195, "▁ꯄꯥꯟꯕ": 196, "ꯂꯤꯌꯥ": 197, "▁ꯍꯥꯌ": 198, "▁ꯂꯤꯔꯕ": 199, "▁ꯀ꯭ꯂ": 200, "▁ꯎꯆ": 201, "ꯝꯕ": 202, "▁ꯀꯣꯔ": 203, "▁ꯊꯋꯥꯢ": 204, "ꯏꯟꯅ": 205, "▁ꯃꯇꯨꯡꯏꯟꯅ": 206, "ꯚꯤꯁ": 207, "▁ꯂꯩꯔꯤꯕ": 208, "▁▁": 209, "ꯤ": 210, "ꯥ": 211, "ꯃ": 212, "ꯅ": 213, "ꯁ": 214, "ꯑ": 215, "ꯡ": 216, "ꯂ": 217, "ꯨ": 218, "ꯕ": 219, "ꯗ": 220, "ꯒ": 221, "ꯣ": 222, "ꯔ": 223, "ꯦ": 224, "ꯝ": 225, "ꯀ": 226, "ꯇ": 227, "ꯛ": 228, "ꯄ": 229, "ꯩ": 230, "ꯌ": 231, "ꯟ": 232, "ꯆ": 233, "ꯏ": 234, "ꯍ": 235, "ꯢ": 236, "ꯈ": 237, "ꯊ": 238, "ꯧ": 239, "ꯜ": 240, "꯭": 241, "ꯠ": 242, "ꯋ": 243, "ꯐ": 244, "ꯎ": 245, "ꯪ": 246, "ꯖ": 247, "ꯉ": 248, "ꯞ": 249, "ꯚ": 250, "ꯓ": 251, "ꯙ": 252, "ꯘ": 253, "꯬": 254, "꫱": 255, "▁": 256, "<pad>": 257}, "large_sd": {"<unk>": 0, "▁म": 1, "▁ज": 2, "▁ह": 3, "▁क": 4, "▁स": 5, "▁व": 6, "▁प": 7, "नि": 8, "हि": 9, "▁ख": 10, "▁आ": 11, "▁त": 12, "ां": 13, "▁ब": 14, "ार": 15, "ें": 16, "▁अ": 17, "यो": 18, "▁ल": 19, "▁जे": 20, "▁हि": 21, "ूं": 22, "हे": 23, "्र": 24, "▁में": 25, "▁र": 26, "▁कर": 27, "▁हु": 28, "▁श": 29, "ंद": 30, "▁आहे": 31, "ड़": 32, "ाइ": 33, "▁ग": 34, "▁खे": 35, "▁न": 36, "हिं": 37, "▁जो": 38, "्त": 39, "▁जी": 40, "▁हिक": 41, "▁थ": 42, "▁मु": 43, "या": 44, "री": 45, "क़": 46, "ान": 47, "▁द": 48, "▁हुन": 49, "हिंज": 50, "वा": 51, "िल": 52, "▁हिकु": 53, "ज़": 54, "ाल": 55, "▁च": 56, "िय": 57, "र्": 58, "▁ऐ": 59, "▁छ": 60, "▁ते": 61, "▁ड": 62, "▁ऐं": 63, "ंग": 64, "फ़": 65, "▁श्र": 66, "▁लाइ": 67, "▁सां": 68, "खे": 69, "्ह": 70, "▁इ": 71, "ाम": 72, "णु": 73, "ाए": 74, "▁करे": 75, "ेल": 76, "ंहिंज": 77, "▁बि": 78, "ुनि": 79, "▁खां": 80, "▁मूं": 81, "ाण": 82, "▁घ": 83, "लु": 84, "्य": 85, "ाई": 86, "्म": 87, "▁आहि": 88, "ियो": 89, "▁ई": 90, "िन": 91, "▁छा": 92, "ीं": 93, "▁भ": 94, "ाय": 95, "ु॒": 96, "▁हू": 97, "▁थी": 98, "▁लग": 99, "▁करु": 100, "दा": 101, "▁उ": 102, "▁सभ": 103, "▁ट": 104, "▁सु": 105, "▁पो": 106, "ेरी": 107, "ानी": 108, "रु": 109, "▁वार": 110, "▁मूंखे": 111, "ली": 112, "ृंग": 113, "▁हिन": 114, "ृंगेरी": 115, "▁श्रृंगेरी": 116, "िस": 117, "्ट": 118, "▁कयो": 119, "एं": 120, "े॒": 121, "हिर": 122, "हिड़": 123, "दी": 124, "जी": 125, "▁अल": 126, "िर": 127, "▁पर": 128, "▁श्री": 129, "वास": 130, "जे": 131, "दि": 132, "ा॒": 133, "▁ठ": 134, "निवास": 135, "▁श्रीनिवास": 136, "▁गो": 137, "ास": 138, "ीअ": 139, "▁फ": 140, "ंदो": 141, "▁मां": 142, "▁कहिड़": 143, "ाब": 144, "▁कु": 145, "▁ज़": 146, "▁सघ": 147, "िक": 148, "▁पोइ": 149, "▁आहिनि": 150, "▁मुंहिंज": 151, "दो": 152, "▁रा": 153, "▁हो": 154, "क़्त": 155, "बानी": 156, "▁पंहिंज": 157, "स्त": 158, "▁पहिंज": 159, "▁वक़्त": 160, "हु": 161, "ीक": 162, "▁अज": 163, "▁अलार": 164, "▁को": 165, "▁ख़": 166, "▁थो": 167, "▁बै": 168, "▁अलारम": 169, "ारी": 170, "हा": 171, "ात": 172, "ि॒": 173, "▁क़": 174, "▁चयो": 175, "स्": 176, "▁हे": 177, "▁महिर": 178, "▁महिरबानी": 179, "क्": 180, "ाव": 181, "ारु": 182, "▁बैदि": 183, "दु": 184, "मेल": 185, "▁वध": 186, "▁▁": 187, "ा": 188, "े": 189, "ि": 190, "र": 191, "ं": 192, "ह": 193, "ु": 194, "क": 195, "ी": 196, "म": 197, "ज": 198, "न": 199, "ो": 200, "्": 201, "ल": 202, "स": 203, "य": 204, "त": 205, "व": 206, "द": 207, "़": 208, "प": 209, "ब": 210, "ख": 211, "ू": 212, "ग": 213, "ड": 214, "आ": 215, "ण": 216, "अ": 217, "ट": 218, "श": 219, "इ": 220, "॒": 221, "ई": 222, "थ": 223, "च": 224, "ए": 225, "फ": 226, "भ": 227, "ठ": 228, "उ": 229, "ध": 230, "घ": 231, "छ": 232, "ै": 233, "ऐ": 234, "ौ": 235, "झ": 236, "ॾ": 237, "ृ": 238, "ढ": 239, "ॉ": 240, "ञ": 241, "ष": 242, "ॻ": 243, "ॿ": 244, "ओ": 245, "ॼ": 246, "ऑ": 247, "ऱ": 248, "औ": 249, "ङ": 250, "ँ": 251, "ऊ": 252, "ॅ": 253, "ऍ": 254, "ऩ": 255, "▁": 256, "<pad>": 257}, "large_or": {"<unk>": 0, "▁କ": 1, "▁ସ": 2, "▁ପ": 3, "ାର": 4, "▁ବ": 5, "୍ର": 6, "ନ୍": 7, "ରେ": 8, "▁ମ": 9, "୍ୟ": 10, "ଙ୍": 11, "ିବ": 12, "▁ଏ": 13, "ତି": 14, "▁ନ": 15, "▁କର": 16, "ଙ୍କ": 17, "▁ଅ": 18, "▁ଦ": 19, "ାଇ": 20, "ର୍": 21, "▁ହ": 22, "▁ଆ": 23, "ିଲ": 24, "ାନ": 25, "ହି": 26, "▁ର": 27, "କୁ": 28, "ିବା": 29, "ଛି": 30, "ିକ": 31, "▁ପ୍ର": 32, "▁ଜ": 33, "ତା": 34, "▁ଭ": 35, "ସ୍": 36, "▁ବି": 37, "କ୍": 38, "▁ଯ": 39, "▁ଗ": 40, "ଥିଲ": 41, "ନ୍ତି": 42, "▁କରି": 43, "ନ୍ତ": 44, "▁ସେ": 45, "ମ୍": 46, "ହା": 47, "▁ଶ": 48, "ବା": 49, "▁ଚ": 50, "ନା": 51, "▁ଓ": 52, "▁ଲ": 53, "ିତ": 54, "ଛନ୍ତି": 55, "▁ଉ": 56, "ଷ୍": 57, "ଡ଼": 58, "ଲି": 59, "▁ଦେ": 60, "▁ନି": 61, "ଟି": 62, "ରୁ": 63, "▁ତ": 64, "ବେ": 65, "ୋଇ": 66, "ାରେ": 67, "ମାନ": 68, "୍ୱ": 69, "ଣ୍": 70, "▁ହେ": 71, "ଥିବା": 72, "ରି": 73, "ଙ୍କୁ": 74, "ଥିଲେ": 75, "ାମ": 76, "▁ହୋଇ": 77, "ତ୍": 78, "ନ୍ଦ": 79, "▁ପାଇ": 80, "ଧ୍ୟ": 81, "କ୍ଷ": 82, "▁ତା": 83, "▁ରା": 84, "▁ଏହି": 85, "ସି": 86, "ଥା": 87, "୍ୟା": 88, "▁ସମ": 89, "ାର୍": 90, "▁ଖ": 91, "ୋଗ": 92, "▁କି": 93, "▁ବା": 94, "ାଯ": 95, "ଡି": 96, "୍ରୀ": 97, "▁ପାଇଁ": 98, "▁ସ୍": 99, "େଇ": 100, "ଲା": 101, "୍ଚ": 102, "ଥିଲା": 103, "▁ମଧ୍ୟ": 104, "ାଗ": 105, "▁ଘ": 106, "ାତ": 107, "ୁର": 108, "▁ଫ": 109, "କାର": 110, "ଳି": 111, "ଭି": 112, "ଙ୍ଗ": 113, "ସ୍ତ": 114, "ଦ୍": 115, "େଶ": 116, "ରା": 117, "ଷ୍ଟ": 118, "ୋଲି": 119, "▁କେ": 120, "▁ମୁ": 121, "ଣା": 122, "▁ଟ": 123, "▁ଅନ": 124, "ାବ": 125, "ଲେ": 126, "▁ଏକ": 127, "▁କରାଯ": 128, "ୋକ": 129, "▁ପା": 130, "ିନ": 131, "ାୟ": 132, "▁କରିବା": 133, "ଡ଼ି": 134, "▁ଏହା": 135, "▁ଉପ": 136, "ଯ୍ୟ": 137, "▁ସହ": 138, "▁ସଂ": 139, "▁ରାଜ": 140, "ାରୁ": 141, "▁ମି": 142, "▁ସା": 143, "▁ଯେ": 144, "ଥି": 145, "ଣ୍ଡ": 146, "▁ମା": 147, "ିଲ୍": 148, "▁ପର": 149, "ମା": 150, "▁ଏବ": 151, "▁ସୁ": 152, "▁ଏବଂ": 153, "କା": 154, "▁ସମ୍": 155, "▁ଧ": 156, "▁ନା": 157, "ମାନେ": 158, "ଣି": 159, "ଳେ": 160, "ଞ୍ଚ": 161, "ୀୟ": 162, "▁ନେଇ": 163, "▁ପରେ": 164, "▁ଚା": 165, "ହାର": 166, "▁କହି": 167, "▁ବ୍ୟ": 168, "▁ବୋଲି": 169, "କ୍ର": 170, "ନ୍ୟ": 171, "ଳା": 172, "ହୁ": 173, "ଜି": 174, "ାଉ": 175, "▁ଦେଇ": 176, "▁▁": 177, "ା": 178, "୍": 179, "ି": 180, "ର": 181, "କ": 182, "େ": 183, "ନ": 184, "ବ": 185, "ତ": 186, "ସ": 187, "ୁ": 188, "ପ": 189, "ମ": 190, "ହ": 191, "ଲ": 192, "ଦ": 193, "ୟ": 194, "ୋ": 195, "ଇ": 196, "ଥ": 197, "ଜ": 198, "ଗ": 199, "ୀ": 200, "ଟ": 201, "ଣ": 202, "ଏ": 203, "ଶ": 204, "ଆ": 205, "ଙ": 206, "ଭ": 207, "ଯ": 208, "ଛ": 209, "ଳ": 210, "ଡ": 211, "ଅ": 212, "ଷ": 213, "ଚ": 214, "ଧ": 215, "ଉ": 216, "ଖ": 217, "ଁ": 218, "ଂ": 219, "ଓ": 220, "଼": 221, "ୂ": 222, "ଠ": 223, "ୱ": 224, "ଫ": 225, "ୃ": 226, "ଘ": 227, "ଞ": 228, "'": 229, "ଢ": 230, "ୌ": 231, "ୈ": 232, "ଝ": 233, "ଵ": 234, "ଃ": 235, "ଋ": 236, "ଔ": 237, "": 238, "ଈ": 239, "ଐ": 240, "ଊ": 241, "ୢ": 242, "ୖ": 243, "ୠ": 244, "ୄ": 245, "ୗ": 246, "": 247, "୰": 248, "ଽ": 249, "୲": 250, "ଌ": 251, "": 252, "୳": 253, "": 254, "": 255, "▁": 256, "<pad>": 257}, "large_mai": {"<unk>": 0, "▁क": 1, "▁स": 2, "▁म": 3, "▁प": 4, "▁अ": 5, "▁ज": 6, "▁ब": 7, "्र": 8, "ार": 9, "▁द": 10, "▁आ": 11, "▁न": 12, "▁छ": 13, "▁र": 14, "▁ह": 15, "▁भ": 16, "ेल": 17, "▁ल": 18, "▁व": 19, "हि": 20, "्य": 21, "▁ग": 22, "▁त": 23, "▁ए": 24, "ान": 25, "▁के": 26, "छि": 27, "▁अछि": 28, "िक": 29, "र्": 30, "ाक": 31, "मे": 32, "न्": 33, "▁मे": 34, "ित": 35, "ाल": 36, "▁प्र": 37, "िल": 38, "ना": 39, "▁च": 40, "्त": 41, "ैत": 42, "ाम": 43, "▁कर": 44, "▁श": 45, "ास": 46, "▁एक": 47, "▁जे": 48, "िय": 49, "▁ओ": 50, "▁वि": 51, "▁सं": 52, "रा": 53, "्व": 54, "▁पर": 55, "▁उ": 56, "▁रह": 57, "▁सम": 58, "ाज": 59, "ड़": 60, "▁जा": 61, "ति": 62, "ला": 63, "नि": 64, "ीक": 65, "▁से": 66, "ने": 67, "्ष": 68, "▁सँ": 69, "▁दे": 70, "ात": 71, "ुर": 72, "▁अप": 73, "▁गेल": 74, "नक": 75, "▁छी": 76, "▁मु": 77, "▁ख": 78, "▁हम": 79, "स्": 80, "थिल": 81, "ाँ": 82, "▁सु": 83, "ता": 84, "▁छल": 85, "▁हो": 86, "▁छै": 87, "▁ध": 88, "▁ई": 89, "ाद": 90, "▁लेल": 91, "त्र": 92, "▁फ": 93, "टा": 94, "▁य": 95, "न्द": 96, "ाय": 97, "ोक": 98, "थि": 99, "सँ": 100, "▁को": 101, "ाह": 102, "ंग": 103, "हो": 104, "▁कि": 105, "▁कह": 106, "▁रहल": 107, "िन": 108, "हु": 109, "▁नहि": 110, "ाव": 111, "के": 112, "ष्": 113, "▁अपन": 114, "ाग": 115, "▁सभ": 116, "▁भेल": 117, "▁ने": 118, "रि": 119, "▁एहि": 120, "्म": 121, "▁नि": 122, "दा": 123, "▁इ": 124, "▁मै": 125, "▁घ": 126, "▁सेहो": 127, "▁सब": 128, "कार": 129, "्च": 130, "▁मि": 131, "इत": 132, "ाप": 133, "▁बे": 134, "बाक": 135, "री": 136, "▁मैथिल": 137, "▁राज": 138, "िया": 139, "▁लोक": 140, "नो": 141, "पाल": 142, "्प": 143, "▁कए": 144, "ेक": 145, "▁छथि": 146, "ेश": 147, "▁केर": 148, "्यक": 149, "नी": 150, "हार": 151, "द्": 152, "▁संग": 153, "▁बि": 154, "ाब": 155, "▁देख": 156, "ती": 157, "▁कार": 158, "सभ": 159, "▁स्": 160, "▁सा": 161, "▁झ": 162, "मा": 163, "कर": 164, "ढ़": 165, "▁दु": 166, "▁▁": 167, "ा": 168, "क": 169, "र": 170, "ि": 171, "्": 172, "े": 173, "न": 174, "ल": 175, "स": 176, "त": 177, "म": 178, "ह": 179, "प": 180, "ी": 181, "द": 182, "ब": 183, "य": 184, "ज": 185, "व": 186, "ु": 187, "ो": 188, "ग": 189, "छ": 190, "अ": 191, "ै": 192, "ं": 193, "भ": 194, "ए": 195, "ँ": 196, "आ": 197, "च": 198, "श": 199, "ट": 200, "थ": 201, "ख": 202, "ू": 203, "ध": 204, "ड": 205, "ष": 206, "ण": 207, "इ": 208, "ओ": 209, "़": 210, "उ": 211, "ौ": 212, "ई": 213, "फ": 214, "ठ": 215, "घ": 216, "ऽ": 217, "ृ": 218, "झ": 219, "ॅ": 220, "ढ": 221, "ञ": 222, "ङ": 223, "ऐ": 224, "ॉ": 225, "ः": 226, "औ": 227, "ऊ": 228, "ऋ": 229, "ॆ": 230, "ऑ": 231, "ॊ": 232, "ळ": 233, "॰": 234, "ऒ": 235, "ॐ": 236, "ॾ": 237, "ॄ": 238, "ऱ": 239, "ॠ": 240, "ॻ": 241, "॒": 242, "ॼ": 243, "ऩ": 244, "॓": 245, "ॱ": 246, "ऎ": 247, "ॿ": 248, "ऍ": 249, "॑": 250, "ॴ": 251, "॔": 252, "ॲ": 253, "ऴ": 254, "ॕ": 255, "▁": 256, "<pad>": 257}, "large_kok": {"<unk>": 0, "्य": 1, "्या": 2, "▁क": 3, "▁त": 4, "▁आ": 5, "▁म": 6, "▁प": 7, "▁स": 8, "ला": 9, "▁ह": 10, "▁अ": 11, "ार": 12, "▁व": 13, "▁न": 14, "ां": 15, "्र": 16, "ात": 17, "ले": 18, "▁द": 19, "▁ज": 20, "▁ब": 21, "ही": 22, "ाच": 23, "र्": 24, "ून": 25, "ाय": 26, "्ह": 27, "▁ग": 28, "▁त्या": 29, "ाव": 30, "ली": 31, "▁य": 32, "▁अस": 33, "ान": 34, "ल्या": 35, "च्या": 36, "▁हो": 37, "हे": 38, "ती": 39, "▁र": 40, "ाही": 41, "▁श": 42, "ता": 43, "▁आहे": 44, "▁कर": 45, "▁च": 46, "क्": 47, "▁उ": 48, "स्": 49, "▁ए": 50, "▁भ": 51, "▁प्र": 52, "▁घ": 53, "▁आण": 54, "ते": 55, "चे": 56, "ची": 57, "▁ख": 58, "नी": 59, "▁आणि": 60, "ना": 61, "▁म्ह": 62, "▁का": 63, "िक": 64, "▁एक": 65, "री": 66, "चा": 67, "▁ल": 68, "▁वा": 69, "वा": 70, "▁फ": 71, "ने": 72, "ाण": 73, "▁वि": 74, "▁नाही": 75, "सा": 76, "ंत": 77, "वर": 78, "ित": 79, "▁ते": 80, "▁म्हण": 81, "▁मा": 82, "▁हे": 83, "▁के": 84, "ेत": 85, "▁दि": 86, "▁झ": 87, "▁ला": 88, "▁स्": 89, "ाज": 90, "त्": 91, "▁इ": 92, "ाक": 93, "ाल": 94, "ाला": 95, "ंद": 96, "क्ष": 97, "शी": 98, "ल्": 99, "ंग": 100, "ण्या": 101, "▁तर": 102, "▁आप": 103, "ुर": 104, "ांत": 105, "ेव": 106, "▁पण": 107, "तो": 108, "ास": 109, "ाह": 110, "्ट": 111, "ुन": 112, "डे": 113, "▁नि": 114, "द्": 115, "ळे": 116, "णार": 117, "▁तु": 118, "▁या": 119, "कार": 120, "▁ट": 121, "स्त": 122, "▁मु": 123, "▁सं": 124, "▁को": 125, "▁असे": 126, "▁ध": 127, "ाम": 128, "▁काही": 129, "▁तो": 130, "लं": 131, "ठी": 132, "▁मी": 133, "तात": 134, "ें": 135, "ोक": 136, "▁त्यां": 137, "ांग": 138, "णी": 139, "▁पर": 140, "लो": 141, "▁कि": 142, "▁लाग": 143, "रे": 144, "ाग": 145, "व्ह": 146, "▁ति": 147, "▁काय": 148, "डी": 149, "▁झा": 150, "▁मि": 151, "णे": 152, "ाच्या": 153, "ाची": 154, "▁वे": 155, "ळी": 156, "्यां": 157, "▁दे": 158, "▁आम": 159, "▁सम": 160, "रा": 161, "का": 162, "से": 163, "▁ठ": 164, "▁ड": 165, "न्": 166, "▁सु": 167, "्ये": 168, "धी": 169, "▁वाट": 170, "▁▁": 171, "ा": 172, "्": 173, "त": 174, "र": 175, "े": 176, "ी": 177, "य": 178, "क": 179, "ल": 180, "न": 181, "स": 182, "व": 183, "ह": 184, "ं": 185, "च": 186, "म": 187, "ि": 188, "प": 189, "ो": 190, "ण": 191, "द": 192, "आ": 193, "ग": 194, "ु": 195, "ज": 196, "ब": 197, "ू": 198, "अ": 199, "श": 200, "ट": 201, "ड": 202, "ळ": 203, "ध": 204, "ख": 205, "भ": 206, "ष": 207, "घ": 208, "थ": 209, "ठ": 210, "उ": 211, "ए": 212, "झ": 213, "फ": 214, "इ": 215, "ढ": 216, "ई": 217, "ै": 218, "ॉ": 219, "ऊ": 220, "ॅ": 221, "ृ": 222, "छ": 223, "ओ": 224, "ौ": 225, "ऱ": 226, "ः": 227, "ँ": 228, "ऐ": 229, "ऑ": 230, "ञ": 231, "़": 232, "औ": 233, "ऋ": 234, "॑": 235, "ॆ": 236, "ऽ": 237, "ऍ": 238, "ॊ": 239, "ॄ": 240, "ङ": 241, "ऴ": 242, "ॲ": 243, "ऎ": 244, "ॐ": 245, "ऩ": 246, "ऒ": 247, "ॕ": 248, "ॠ": 249, "॒": 250, "॰": 251, "॓": 252, "॔": 253, "ॢ": 254, "ऌ": 255, "▁": 256, "<pad>": 257}, "large_brx": {"<unk>": 0, "ाय": 1, "▁ब": 2, "नि": 3, "▁स": 4, "ान": 5, "▁म": 6, "ाव": 7, "ार": 8, "▁ह": 9, "▁ग": 10, "ोन": 11, "▁ज": 12, "ों": 13, "्र": 14, "▁क": 15, "ां": 16, "▁द": 17, "▁आ": 18, "ोर": 19, "▁बि": 20, "ला": 21, "नाय": 22, "खौ": 23, "नो": 24, "▁फ": 25, "▁थ": 26, "▁र": 27, "▁न": 28, "▁ख": 29, "थि": 30, "▁ल": 31, "ाद": 32, "▁बे": 33, "फोर": 34, "▁प": 35, "ुं": 36, "ानै": 37, "ाम": 38, "ारि": 39, "िर": 40, "से": 41, "ाब": 42, "न्": 43, "दों": 44, "ना": 45, "▁गो": 46, "लि": 47, "▁अ": 48, "सि": 49, "▁आर": 50, "▁होन": 51, "बो": 52, "ाग": 53, "ानाय": 54, "ाह": 55, "ाख": 56, "ाज": 57, "▁मोन": 58, "▁आरो": 59, "नानै": 60, "▁ए": 61, "या": 62, "ाइ": 63, "ुब": 64, "िरि": 65, "ानि": 66, "▁के": 67, "थाय": 68, "गिरि": 69, "ोल": 70, "जों": 71, "आव": 72, "्ला": 73, "ें": 74, "ोम": 75, "▁उ": 76, "▁भ": 77, "▁सि": 78, "ोग": 79, "लाम": 80, "सा": 81, "दि": 82, "ेर": 83, "ास": 84, "▁जि": 85, "▁दि": 86, "▁बिथ": 87, "▁खा": 88, "▁सम": 89, "मोन": 90, "्रि": 91, "ाल": 92, "ायो": 93, "▁बर": 94, "ुर": 95, "▁थाख": 96, "फोरा": 97, "ुन": 98, "▁इ": 99, "यो": 100, "ायाव": 101, "▁है": 102, "्रा": 103, "▁खालाम": 104, "ान्": 105, "पि": 106, "ेल": 107, "▁ला": 108, "टि": 109, "ोब": 110, "▁लोग": 111, "र्": 112, "▁थाखाय": 113, "फ्र": 114, "▁नि": 115, "ादों": 116, "▁माव": 117, "्ल": 118, "बि": 119, "▁लोगो": 120, "ुम": 121, "ेन": 122, "ांग": 123, "ाथ": 124, "राय": 125, "▁दै": 126, "▁व": 127, "▁सुब": 128, "▁फोर": 129, "याव": 130, "ुलि": 131, "खा": 132, "▁राज": 133, "स्": 134, "▁हो": 135, "▁प्र": 136, "▁सोर": 137, "▁बिथां": 138, "▁कर": 139, "नायनि": 140, "क्": 141, "जो": 142, "▁में": 143, "ानो": 144, "▁जा": 145, "ाङ": 146, "ानानै": 147, "फोरखौ": 148, "▁आस": 149, "ारी": 150, "ाया": 151, "▁बुं": 152, "ेज": 153, "▁च": 154, "फ्राय": 155, "▁सुबुं": 156, "ने": 157, "ोलो": 158, "▁ने": 159, "▁मि": 160, "▁बिज": 161, "▁औ": 162, "खार": 163, "▁गुब": 164, "▁थानाय": 165, "ब्ला": 166, "▁से": 167, "▁दोलो": 168, "▁खौ": 169, "▁आसाम": 170, "▁लोगोसे": 171, "बाय": 172, "▁को": 173, "्य": 174, "▁आफ": 175, "हा": 176, "▁त": 177, "▁और": 178, "▁जादों": 179, "न्द": 180, "▁▁": 181, "ा": 182, "न": 183, "ि": 184, "ो": 185, "र": 186, "ब": 187, "स": 188, "य": 189, "म": 190, "ं": 191, "े": 192, "्": 193, "ग": 194, "ल": 195, "द": 196, "ज": 197, "ख": 198, "ह": 199, "व": 200, "ु": 201, "थ": 202, "फ": 203, "क": 204, "ै": 205, "आ": 206, "ौ": 207, "प": 208, "त": 209, "ी": 210, "इ": 211, "ट": 212, "'": 213, "ए": 214, "उ": 215, "अ": 216, "भ": 217, "ङ": 218, "ड": 219, "श": 220, "च": 221, "ध": 222, "ष": 223, "ू": 224, "औ": 225, "ओ": 226, "ण": 227, "ई": 228, "़": 229, "झ": 230, "घ": 231, "छ": 232, "ृ": 233, "ठ": 234, "ढ": 235, "ॉ": 236, "ँ": 237, "ऐ": 238, "ः": 239, "ऑ": 240, "ऊ": 241, "ञ": 242, "ऱ": 243, "ऋ": 244, "ऩ": 245, "ॺ": 246, "ॅ": 247, "ॽ": 248, "ळ": 249, "ॆ": 250, "ॐ": 251, "॔": 252, "ऴ": 253, "ऽ": 254, "॰": 255, "▁": 256, "<pad>": 257}, "large_sa": {"<unk>": 0, "्य": 1, "त्": 2, "्र": 3, "▁स": 4, "र्": 5, "ति": 6, "▁प": 7, "न्": 8, "▁व": 9, "▁त": 10, "▁क": 11, "▁न": 12, "्या": 13, "वा": 14, "स्": 15, "मा": 16, "म्": 17, "क्": 18, "▁अ": 19, "ना": 20, "▁प्र": 21, "द्": 22, "ता": 23, "▁य": 24, "त्र": 25, "▁च": 26, "▁म": 27, "ते": 28, "वि": 29, "स्य": 30, "▁द": 31, "ष्": 32, "▁श": 33, "▁भ": 34, "त्य": 35, "ार": 36, "▁वि": 37, "▁इ": 38, "या": 39, "क्ष": 40, "त्व": 41, "नि": 42, "रा": 43, "दि": 44, "्च": 45, "मि": 46, "▁स्": 47, "प्र": 48, "ेन": 49, "था": 50, "▁ज": 51, "दा": 52, "पि": 53, "तु": 54, "▁ग": 55, "▁ह": 56, "▁ए": 57, "त्वा": 58, "र्व": 59, "का": 60, "▁ब": 61, "ङ्": 62, "णा": 63, "न्त": 64, "र्थ": 65, "ेव": 66, "रि": 67, "ष्ट": 68, "ाव": 69, "नु": 70, "्ञ": 71, "यो": 72, "तः": 73, "पा": 74, "द्ध": 75, "▁नि": 76, "▁आ": 77, "▁इति": 78, "ेष": 79, "श्च": 80, "▁वा": 81, "तो": 82, "ान": 83, "भि": 84, "रु": 85, "न्द": 86, "्व": 87, "तं": 88, "ती": 89, "▁उ": 90, "सा": 91, "मु": 92, "ज्ञ": 93, "धि": 94, "त्या": 95, "▁पु": 96, "न्य": 97, "कार": 98, "ङ्ग": 99, "प्": 100, "त्त": 101, "द्य": 102, "▁ध": 103, "रू": 104, "▁सा": 105, "वे": 106, "्छ": 107, "▁ल": 108, "ने": 109, "हा": 110, "र्म": 111, "नं": 112, "▁सर्व": 113, "रो": 114, "हि": 115, "भा": 116, "ये": 117, "च्छ": 118, "दे": 119, "्रा": 120, "सि": 121, "व्य": 122, "▁स्व": 123, "ला": 124, "▁एव": 125, "ह्": 126, "रे": 127, "▁ना": 128, "स्त": 129, "▁सु": 130, "मे": 131, "▁प्रा": 132, "▁श्र": 133, "स्या": 134, "ैव": 135, "नां": 136, "कृ": 137, "यं": 138, "ग्": 139, "▁सं": 140, "▁मा": 141, "धा": 142, "ब्": 143, "क्त": 144, "न्ति": 145, "ण्": 146, "ञ्च": 147, "▁तु": 148, "जा": 149, "रूप": 150, "ल्": 151, "र्य": 152, "ोऽ": 153, "ित": 154, "ष्ठ": 155, "न्न": 156, "रण": 157, "श्व": 158, "शा": 159, "सं": 160, "▁कृ": 161, "▁रा": 162, "▁र": 163, "नी": 164, "णि": 165, "त्रा": 166, "भाव": 167, "▁भव": 168, "मः": 169, "▁इत्य": 170, "▁कि": 171, "्": 172, "▁▁": 173, "ा": 174, "त": 175, "र": 176, "ि": 177, "य": 178, "व": 179, "न": 180, "म": 181, "स": 182, "प": 183, "े": 184, "द": 185, "क": 186, "ु": 187, "ं": 188, "ो": 189, "श": 190, "ः": 191, "ष": 192, "च": 193, "भ": 194, "ह": 195, "ण": 196, "ध": 197, "ग": 198, "ी": 199, "ज": 200, "ल": 201, "थ": 202, "॒": 203, "ृ": 204, "ू": 205, "अ": 206, "ब": 207, "॑": 208, "ै": 209, "इ": 210, "ट": 211, "ञ": 212, "ऽ": 213, "ए": 214, "ङ": 215, "ौ": 216, "ख": 217, "आ": 218, "उ": 219, "छ": 220, "ड": 221, "ठ": 222, "घ": 223, "फ": 224, "ॐ": 225, "ऋ": 226, "ढ": 227, "ई": 228, "ओ": 229, "ऊ": 230, "ँ": 231, "ऐ": 232, "ळ": 233, "झ": 234, "औ": 235, "़": 236, "ॄ": 237, "ॢ": 238, "ॉ": 239, "॰": 240, "ॆ": 241, "ऎ": 242, "ॊ": 243, "ऱ": 244, "ऑ": 245, "ॅ": 246, "ऌ": 247, "ऴ": 248, "ॣ": 249, "ॠ": 250, "ऍ": 251, "ॡ": 252, "ऩ": 253, "ऒ": 254, "ॖ": 255, "▁": 256, "<pad>": 257}, "large_sat": {"<unk>": 0, "▁ᱠ": 1, "ᱱᱟ": 2, "▁ᱟ": 3, "▁ᱨ": 4, "▁ᱥ": 5, "▁ᱨᱮ": 6, "▁ᱫ": 7, "ᱟᱹ": 8, "▁ᱢ": 9, "▁ᱵ": 10, "▁ᱦ": 11, "▁ᱛ": 12, "▁ᱫᱚ": 13, "ᱚᱱ": 14, "▁ᱯ": 15, "ᱟᱨ": 16, "▁ᱠᱚ": 17, "▁ᱜ": 18, "▁ᱡ": 19, "ᱟᱜ": 20, "ᱟᱱ": 21, "ᱱᱟᱜ": 22, "▁ᱞ": 23, "ᱟᱱᱟ": 24, "▁ᱱ": 25, "▁ᱮ": 26, "▁ᱟᱨ": 27, "ᱚᱨ": 28, "ᱚᱛ": 29, "ᱟᱦ": 30, "ᱤᱫ": 31, "ᱟᱭ": 32, "ᱤᱭ": 33, "▁ᱢᱮ": 34, "▁ᱠᱟᱱᱟ": 35, "▁ᱚ": 36, "▁ᱱᱚ": 37, "ᱚᱢ": 38, "ᱠᱟ": 39, "ᱮᱫ": 40, "▁ᱪ": 41, "▁ᱨᱮᱱᱟᱜ": 42, "ᱤᱱ": 43, "ᱩᱨ": 44, "▁ᱠᱷ": 45, "▁ᱥᱟ": 46, "▁ᱩ": 47, "ᱛᱮ": 48, "▁ᱵᱟ": 49, "ᱣᱟ": 50, "▁ᱦᱚ": 51, "ᱷᱟ": 52, "ᱤᱥ": 53, "ᱼᱟ": 54, "▁ᱛᱮ": 55, "▁ᱞᱮ": 56, "ᱞᱟ": 57, "▁ᱥᱮ": 58, "ᱚᱜ": 59, "ᱚᱱᱚᱛ": 60, "ᱤᱨ": 61, "▁ᱟᱹ": 62, "ᱭᱟᱜ": 63, "▁ᱢᱮᱱᱟᱜ": 64, "ᱟᱢ": 65, "▁ᱧ": 66, "▁ᱜᱮ": 67, "▁ᱢᱤᱫ": 68, "ᱟᱦᱮ": 69, "▁ᱛᱟᱦᱮ": 70, "ᱰᱤ": 71, "▁ᱠᱟ": 72, "ᱤᱡ": 73, "ᱟᱝ": 74, "ᱟᱹᱨ": 75, "ᱟᱲ": 76, "▁ᱴ": 77, "ᱭᱟ": 78, "▁ᱨᱮᱭᱟᱜ": 79, "ᱟᱣ": 80, "▁ᱠᱷᱚᱱ": 81, "▁ᱥᱤ": 82, "ᱩᱭ": 83, "ᱛᱩ": 84, "ᱡᱽ": 85, "ᱟᱞ": 86, "ᱟᱸ": 87, "ᱚᱸ": 88, "ᱤᱞ": 89, "▁ᱛᱟᱦᱮᱸ": 90, "▁ᱟᱠ": 91, "ᱮᱥ": 92, "ᱠᱷ": 93, "ᱶᱟ": 94, "▁ᱦᱚᱱᱚᱛ": 95, "▁ᱱᱚᱣᱟ": 96, "ᱟᱹᱜ": 97, "ᱩᱜ": 98, "ᱚᱦ": 99, "ᱢᱟ": 100, "ᱨᱤ": 101, "▁ᱩᱱ": 102, "ᱥᱤ": 103, "ᱚᱞ": 104, "▁ᱵᱮ": 105, "▁ᱱᱚᱶᱟ": 106, "ᱨᱮ": 107, "▁ᱵᱷ": 108, "▁ᱱᱟ": 109, "▁ᱢᱮᱱᱟᱜᱼᱟ": 110, "ᱮᱞ": 111, "▁ᱦᱚᱸ": 112, "ᱮᱱ": 113, "ᱤᱭᱟ": 114, "▁ᱚᱱᱟ": 115, "▁ᱟᱡ": 116, "▁ᱥᱟᱶ": 117, "ᱤᱭᱟᱹ": 118, "▁ᱨᱟ": 119, "ᱠᱚ": 120, "ᱤᱛ": 121, "ᱚᱲ": 122, "ᱚᱫ": 123, "ᱚᱵ": 124, "▁ᱞᱮᱠᱟ": 125, "▁ᱦᱩᱭ": 126, "▁ᱦᱚᱲ": 127, "ᱤᱠ": 128, "ᱮᱛ": 129, "▁ᱰ": 130, "ᱟᱥ": 131, "▁ᱢᱩ": 132, "ᱛᱤ": 133, "ᱚᱴ": 134, "▁ᱯᱷ": 135, "▁ᱧᱩ": 136, "ᱨᱟ": 137, "ᱚᱠ": 138, "ᱩᱞ": 139, "▁ᱞᱟᱹᱜ": 140, "ᱷᱟᱨ": 141, "▁ᱠᱟᱹ": 142, "▁ᱞᱟᱹᱜᱤᱫ": 143, "ᱯᱩᱨ": 144, "▁ᱟᱹᱰᱤ": 145, "▁ᱠᱟᱛᱮ": 146, "▁ᱟᱭ": 147, "▁ᱥᱤᱧ": 148, "▁ᱵᱟᱝ": 149, "▁ᱡᱟᱦ": 150, "ᱛᱩᱢ": 151, "ᱫᱽ": 152, "ᱩᱱ": 153, "▁ᱟᱠᱟᱱᱟ": 154, "▁ᱧᱩᱛᱩᱢ": 155, "ᱢᱤ": 156, "▁ᱛᱟᱭ": 157, "▁ᱩᱱᱤ": 158, "▁ᱥᱤᱧᱚᱛ": 159, "ᱫᱚ": 160, "ᱷᱤ": 161, "▁ᱯᱟ": 162, "ᱜᱟ": 163, "ᱴᱤ": 164, "▁ᱫᱤᱥ": 165, "ᱚᱥ": 166, "ᱚᱝ": 167, "▁ᱢᱟᱨ": 168, "▁ᱮᱢ": 169, "▁ᱤ": 170, "ᱮᱡ": 171, "▁ᱢᱮᱱ": 172, "▁ᱯᱚᱱᱚᱛ": 173, "ᱵᱟ": 174, "▁ᱡᱟᱦᱟᱸ": 175, "ᱚᱭ": 176, "▁ᱯᱨ": 177, "▁ᱞᱮᱠᱟᱛᱮ": 178, "▁ᱠᱩ": 179, "▁ᱯᱟᱹᱨ": 180, "ᱛᱟ": 181, "ᱵᱽ": 182, "▁ᱨᱤᱱ": 183, "ᱫᱟ": 184, "▁ᱜᱟ": 185, "ᱰᱟ": 186, "ᱲᱟ": 187, "ᱮᱨ": 188, "▁ᱟᱠᱟ": 189, "ᱚᱡ": 190, "ᱠᱩ": 191, "ᱟᱹᱭ": 192, "▁ᱠᱟᱱ": 193, "▁ᱯᱟᱹᱨᱥᱤ": 194, "▁ᱫᱷ": 195, "ᱰᱮ": 196, "▁ᱞᱮᱫ": 197, "ᱮᱴ": 198, "▁ᱦᱩᱭᱩᱜ": 199, "▁ᱟᱹᱛᱩ": 200, "▁ᱦᱟ": 201, "ᱮᱜ": 202, "ᱟᱹᱱ": 203, "ᱣᱟᱜ": 204, "ᱞᱤ": 205, "▁ᱫᱤᱥᱚᱢ": 206, "▁ᱞᱟ": 207, "▁ᱵᱤᱨ": 208, "▁ᱢᱟ": 209, "ᱟᱹᱲ": 210, "ᱩᱨᱩ": 211, "▁ᱥᱚᱨ": 212, "▁ᱠᱮᱫ": 213, "ᱯᱷ": 214, "ᱵᱷ": 215, "▁ᱛᱟᱭᱚᱢ": 216, "▁ᱮᱱᱟ": 217, "▁ᱨᱮᱱ": 218, "▁▁": 219, "ᱟ": 220, "ᱚ": 221, "ᱮ": 222, "ᱨ": 223, "ᱱ": 224, "ᱤ": 225, "ᱠ": 226, "ᱜ": 227, "ᱫ": 228, "ᱛ": 229, "ᱢ": 230, "ᱥ": 231, "ᱩ": 232, "ᱭ": 233, "ᱞ": 234, "ᱦ": 235, "ᱵ": 236, "ᱷ": 237, "ᱡ": 238, "ᱹ": 239, "ᱯ": 240, "ᱴ": 241, "ᱣ": 242, "ᱸ": 243, "ᱰ": 244, "ᱲ": 245, "ᱪ": 246, "ᱝ": 247, "ᱽ": 248, "ᱧ": 249, "ᱼ": 250, "ᱶ": 251, "ᱳ": 252, "ᱬ": 253, "ᱺ": 254, "ᱻ": 255, "▁": 256, "<pad>": 257}, "large_as": {"<unk>": 0, "▁ক": 1, "য়": 2, "▁প": 3, "▁ব": 4, "াৰ": 5, "▁স": 6, "্ৰ": 7, "▁আ": 8, "্য": 9, "ৰি": 10, "ৰা": 11, "▁ম": 12, "্ত": 13, "▁অ": 14, "▁হ": 15, "▁ন": 16, "▁দ": 17, "ান": 18, "▁এ": 19, "▁বি": 20, "তি": 21, "তে": 22, "▁ল": 23, "▁চ": 24, "▁প্ৰ": 25, "▁গ": 26, "্ব": 27, "▁জ": 28, "াল": 29, "িল": 30, "ৰু": 31, "▁কৰি": 32, "িত": 33, "াই": 34, "িক": 35, "▁য": 36, "ীয়": 37, "ছে": 38, "▁উ": 39, "ন্": 40, "্ষ": 41, "▁শ": 42, "াত": 43, "ৰে": 44, "োৱ": 45, "▁ভ": 46, "ৰ্": 47, "াব": 48, "ষ্": 49, "▁সম": 50, "ন্ত": 51, "▁আৰু": 52, "াক": 53, "িয়": 54, "▁ত": 55, "াম": 56, "্থ": 57, "্র": 58, "ায়": 59, "▁ৰা": 60, "ক্ষ": 61, "লৈ": 62, "▁হৈ": 63, "▁নি": 64, "▁এই": 65, "ুল": 66, "ীৰ": 67, "াহ": 68, "লে": 69, "▁তে": 70, "িব": 71, "ষ্ট": 72, "াগ": 73, "ছিল": 74, "াস": 75, "নৰ": 76, "নে": 77, "▁পৰি": 78, "▁ই": 79, "াপ": 80, "▁কৰা": 81, "াদ": 82, "েই": 83, "▁ৰ": 84, "োক": 85, "▁সং": 86, "কাৰ": 87, "ন্দ": 88, "োৱা": 89, "কা": 90, "▁খ": 91, "ওঁ": 92, "িৰ": 93, "▁থ": 94, "োগ": 95, "্প": 96, "▁পৰা": 97, "কল": 98, "টো": 99, "সম": 100, "ুৰ": 101, "াজ": 102, "না": 103, "▁ধ": 104, "্ধ": 105, "▁তেওঁ": 106, "স্থ": 107, "েশ": 108, "জন": 109, "ক্ত": 110, "ুৱ": 111, "াবে": 112, "িন": 113, "▁অন": 114, "▁কৰিব": 115, "▁কৰে": 116, "্চ": 117, "▁ঘ": 118, "ুলি": 119, "▁লগ": 120, "▁বাবে": 121, "েল": 122, "াৰে": 123, "ভি": 124, "াৱ": 125, "দ্ধ": 126, "▁ব্য": 127, "োৰ": 128, "▁ড": 129, "▁ছ": 130, "▁ফ": 131, "টা": 132, "▁হয়": 133, "▁কি": 134, "▁অসম": 135, "োন": 136, "খন": 137, "ীয়া": 138, "ীয়ে": 139, "ণ্": 140, "্ৰী": 141, "াধ": 142, "▁কৰ": 143, "▁আৰ": 144, "নি": 145, "▁হৈছে": 146, "▁মু": 147, "▁বুলি": 148, "▁এক": 149, "মান": 150, "▁উপ": 151, "▁প্ৰতি": 152, "েত": 153, "▁প্র": 154, "▁যে": 155, "▁দু": 156, "থা": 157, "▁কে": 158, "য়া": 159, "▁ৰাজ": 160, "▁আহ": 161, "ষ্ঠ": 162, "াট": 163, "▁কাৰ": 164, "ৰ্ম": 165, "▁অনু": 166, "কৰ": 167, "দি": 168, "ৰাক": 169, "োৱাৰ": 170, "▁বিশ": 171, "▁মহ": 172, "াঁ": 173, "ৃত": 174, "▁জন": 175, "▁দে": 176, "খ্য": 177, "্ম": 178, "ৰত": 179, "ঞ্চ": 180, "▁বা": 181, "▁দি": 182, "বি": 183, "▁▁": 184, "া": 185, "ৰ": 186, "্": 187, "ি": 188, "ক": 189, "ত": 190, "ে": 191, "ন": 192, "ব": 193, "ল": 194, "য": 195, "প": 196, "ম": 197, "স": 198, "ু": 199, "হ": 200, "দ": 201, "়": 202, "ো": 203, "ী": 204, "গ": 205, "জ": 206, "ই": 207, "আ": 208, "চ": 209, "ৱ": 210, "ট": 211, "ছ": 212, "শ": 213, "ষ": 214, "ভ": 215, "ৈ": 216, "অ": 217, "ধ": 218, "থ": 219, "ণ": 220, "এ": 221, "খ": 222, "ং": 223, "উ": 224, "ও": 225, "'": 226, "র": 227, "ঁ": 228, "ড": 229, "ূ": 230, "ৃ": 231, "ঠ": 232, "ফ": 233, "ঘ": 234, "ঞ": 235, "ৎ": 236, "ঙ": 237, "ৌ": 238, "ঢ": 239, "ঃ": 240, "ঝ": 241, "ঐ": 242, "ঔ": 243, "ঋ": 244, "ঈ": 245, "৲": 246, "ঊ": 247, "৹": 248, "ৗ": 249, "ৄ": 250, "৻": 251, "৺": 252, "৸": 253, "ৠ": 254, "ঌ": 255, "▁": 256, "<pad>": 257}, "large_ks": {"<unk>": 0, "▁ا": 1, "▁چ": 2, "▁ک": 3, "▁چھ": 4, "َن": 5, "▁م": 6, "ان": 7, "▁اَ": 8, "▁ی": 9, "ہٕ": 10, "▁ت": 11, "▁چھِ": 12, "ہِ": 13, "َر": 14, "ٛز": 15, "▁س": 16, "کھ": 17, "▁مَن": 18, "ار": 19, "▁پ": 20, "▁مَنٛز": 21, "▁اَکھ": 22, "▁ب": 23, "یٖ": 24, "▁چھُ": 25, "▁و": 26, "ست": 27, "ِل": 28, "اک": 29, "ند": 30, "▁کَر": 31, "▁ف": 32, "تھ": 33, "نؠ": 34, "▁تہٕ": 35, "▁آ": 36, "▁ن": 37, "مَن": 38, "َس": 39, "▁کٲ": 40, "ۄس": 41, "▁گ": 42, "▁ہ": 43, "ٲنؠ": 44, "▁د": 45, "▁یۄس": 46, "نٛ": 47, "ستٲنؠ": 48, "▁کَران": 49, "▁ر": 50, "▁ہِ": 51, "▁کٲم": 52, "وٗ": 53, "▁اَد": 54, "ام": 55, "ارہ": 56, "▁ش": 57, "▁فِل": 58, "▁ج": 59, "▁اَداک": 60, "▁اَداکارہ": 61, "▁فِلمَن": 62, "ری": 63, "ندو": 64, "او": 65, "▁ہِندو": 66, "ال": 67, "▁ز": 68, "یا": 69, "نٛد": 70, "▁یِ": 71, "ین": 72, "▁ہِندوستٲنؠ": 73, "▁ع": 74, "یٖر": 75, "نہٕ": 76, "▁کٔ": 77, "▁ل": 78, "▁خ": 79, "ُک": 80, "▁اِ": 81, "ٹھ": 82, "ور": 83, "َل": 84, "َم": 85, "وان": 86, "ِس": 87, "▁ح": 88, "َتھ": 89, "▁یہِ": 90, "اد": 91, "▁کٔش": 92, "▁ہُ": 93, "رِ": 94, "نی": 95, "▁کٔشیٖر": 96, "▁مَ": 97, "▁مُ": 98, "لی": 99, "▁ہُنٛد": 100, "وس": 101, "یو": 102, "یر": 103, "▁یِوان": 104, "ُن": 105, "▁آس": 106, "▁پاک": 107, "َب": 108, "اق": 109, "ؠٹھ": 110, "ِم": 111, "▁پاکِ": 112, "رٛ": 113, "▁ای": 114, "▁ص": 115, "▁ق": 116, "تؠ": 117, "می": 118, "نٛز": 119, "▁یا": 120, "▁پؠٹھ": 121, "را": 122, "▁ض": 123, "▁کھ": 124, "ستان": 125, "تی": 126, "▁اوس": 127, "ژھ": 128, "▁پاکِستٲنؠ": 129, "▁تہ": 130, "▁جۆ": 131, "ول": 132, "اب": 133, "▁ٹ": 134, "یٖن": 135, "ِک": 136, "اہ": 137, "رٕ": 138, "▁تَ": 139, "یاہ": 140, "▁ط": 141, "ای": 142, "ون": 143, "ُس": 144, "َت": 145, "▁أ": 146, "▁جۆم": 147, "▁آر": 148, "▁سی": 149, "▁چھے": 150, "ات": 151, "▁وار": 152, "▁یِم": 153, "ُل": 154, "سی": 155, "▁ضِل": 156, "رن": 157, "▁ڈ": 158, "▁یُس": 159, "▁بی": 160, "▁بَ": 161, "چھ": 162, "▁سِ": 163, "▁گام": 164, "▁ہٕ": 165, "▁▁": 166, "ا": 167, "ن": 168, "َ": 169, "ی": 170, "ِ": 171, "ر": 172, "م": 173, "ک": 174, "ہ": 175, "ھ": 176, "س": 177, "و": 178, "ت": 179, "چ": 180, "ل": 181, "د": 182, "ٕ": 183, "ُ": 184, "ٛ": 185, "ز": 186, "ٲ": 187, "ب": 188, "ؠ": 189, "پ": 190, "ش": 191, "گ": 192, "ٹ": 193, "ف": 194, "ٖ": 195, "ۄ": 196, "ج": 197, "ٔ": 198, "ع": 199, "ق": 200, "آ": 201, "ڈ": 202, "،": 203, "ٗ": 204, "ص": 205, "ح": 206, "خ": 207, "ے": 208, "ٚ": 209, "ژ": 210, "ط": 211, "ۆ": 212, "أ": 213, "ض": 214, "ظ": 215, "غ": 216, "ٟ": 217, "ڑ": 218, "ؤ": 219, "ث": 220, "ذ": 221, "ك": 222, "ي": 223, "ێ": 224, "ۍ": 225, "ئ": 226, "ۅ": 227, "ٮ": 228, "ۂ": 229, "ٰ": 230, "ْ": 231, "ں": 232, "ه": 233, "إ": 234, "؛": 235, "ّ": 236, "ى": 237, "۪": 238, "؟": 239, "ې": 240, "ؙ": 241, "ـ": 242, "ٍ": 243, "ً": 244, "ۭ": 245, "؍": 246, "ء": 247, "ۓ": 248, "ؐ": 249, "ٝ": 250, "ٓ": 251, "ؒ": 252, "ة": 253, "ٳ": 254, "ٱ": 255, "▁": 256, "<pad>": 257}, "large_te": {"<unk>": 0, "▁ప": 1, "ని": 2, "ార": 3, "్ర": 4, "▁క": 5, "న్": 6, "▁వ": 7, "స్": 8, "▁అ": 9, "ర్": 10, "▁మ": 11, "ంద": 12, "లు": 13, "▁స": 14, "▁చ": 15, "లో": 16, "కు": 17, "▁త": 18, "్య": 19, "న్న": 20, "గా": 21, "ంచ": 22, "ల్": 23, "ారు": 24, "క్": 25, "ట్": 26, "▁ర": 27, "ను": 28, "ంది": 29, "తు": 30, "▁ప్ర": 31, "▁ఆ": 32, "ాల": 33, "రి": 34, "డు": 35, "▁ఉ": 36, "టి": 37, "▁చే": 38, "▁ఇ": 39, "▁న": 40, "▁ద": 41, "డి": 42, "▁బ": 43, "కి": 44, "ంత": 45, "యి": 46, "▁వి": 47, "ప్": 48, "రు": 49, "త్": 50, "లి": 51, "▁ఎ": 52, "ంట": 53, "▁జ": 54, "▁గ": 55, "ిన": 56, "తి": 57, "మా": 58, "లా": 59, "ించ": 60, "ంలో": 61, "ార్": 62, "ంగా": 63, "డా": 64, "ప్ప": 65, "▁ఈ": 66, "సు": 67, "టు": 68, "▁ని": 69, "స్తు": 70, "డ్": 71, "ద్": 72, "తో": 73, "చ్": 74, "యా": 75, "▁రా": 76, "నే": 77, "లే": 78, "ంగ": 79, "▁కా": 80, "వా": 81, "ష్": 82, "ది": 83, "్యా": 84, "సి": 85, "చ్చ": 86, "న్ని": 87, "న్నారు": 88, "▁స్": 89, "టీ": 90, "దు": 91, "నా": 92, "▁హ": 93, "▁భ": 94, "▁తె": 95, "న్నా": 96, "స్త": 97, "ందు": 98, "గు": 99, "ండ": 100, "▁శ": 101, "వు": 102, "త్ర": 103, "▁చె": 104, "ిక": 105, "▁సి": 106, "రో": 107, "పు": 108, "రా": 109, "నికి": 110, "ళ్": 111, "మ్": 112, "వి": 113, "▁మా": 114, "▁ఏ": 115, "ేశ": 116, "క్ష": 117, "▁కొ": 118, "ంచి": 119, "▁ఒ": 120, "▁కూ": 121, "ారి": 122, "▁పా": 123, "క్క": 124, "▁ఫ": 125, "▁పె": 126, "▁ము": 127, "పై": 128, "్రా": 129, "కా": 130, "▁వె": 131, "▁కో": 132, "ంతో": 133, "పో": 134, "▁సం": 135, "ల్లో": 136, "కో": 137, "మి": 138, "యం": 139, "▁తీ": 140, "▁కే": 141, "▁లే": 142, "▁కూడా": 143, "▁పో": 144, "ైన": 145, "లీ": 146, "ారం": 147, "మె": 148, "లను": 149, "లకు": 150, "ష్ట": 151, "డం": 152, "్రి": 153, "్వ": 154, "▁ను": 155, "ప్పు": 156, "యు": 157, "ద్ద": 158, "▁మీ": 159, "ాలు": 160, "▁చి": 161, "నీ": 162, "పీ": 163, "▁వా": 164, "▁ఒక": 165, "గి": 166, "ము": 167, "ట్ట": 168, "▁సా": 169, "తే": 170, "▁ట": 171, "పా": 172, "ంగ్": 173, "▁లో": 174, "▁గు": 175, "త్త": 176, "ంటి": 177, "పి": 178, "▁కు": 179, "▁నా": 180, "బ్": 181, "▁సిని": 182, "▁▁": 183, "్": 184, "ి": 185, "ా": 186, "ు": 187, "ర": 188, "న": 189, "ం": 190, "ల": 191, "క": 192, "త": 193, "ప": 194, "స": 195, "వ": 196, "ద": 197, "మ": 198, "ట": 199, "ో": 200, "ే": 201, "య": 202, "చ": 203, "డ": 204, "గ": 205, "ీ": 206, "ె": 207, "అ": 208, "జ": 209, "బ": 210, "ూ": 211, "శ": 212, "ై": 213, "ష": 214, "ఆ": 215, "ధ": 216, "హ": 217, "భ": 218, "ొ": 219, "ఉ": 220, "ఇ": 221, "ఎ": 222, "ణ": 223, "ళ": 224, "ఈ": 225, "థ": 226, "ఫ": 227, "ఖ": 228, "ఏ": 229, "ఒ": 230, "ృ": 231, "ౌ": 232, "ఓ": 233, "ఘ": 234, "ఐ": 235, "ఠ": 236, "ఛ": 237, "ఢ": 238, "ఊ": 239, "ఞ": 240, "ఔ": 241, "ః": 242, "ఝ": 243, "ఋ": 244, "ఱ": 245, "ఁ": 246, "ఙ": 247, "ౄ": 248, "ౖ": 249, "ఽ": 250, "౹": 251, "ౠ": 252, "ౙ": 253, "ఌ": 254, "ౘ": 255, "▁": 256, "<pad>": 257}, "large_pa": {"<unk>": 0, "▁ਕ": 1, "▁ਦ": 2, "▁ਸ": 3, "▁ਹ": 4, "▁ਨ": 5, "▁ਵ": 6, "ਾਂ": 7, "▁ਪ": 8, "▁ਜ": 9, "▁ਮ": 10, "ਾਰ": 11, "▁ਅ": 12, "▁ਤ": 13, "▁ਇ": 14, "▁ਦੇ": 15, "▁ਬ": 16, "▁ਲ": 17, "▁ਹੈ": 18, "▁ਵਿ": 19, "ਾਲ": 20, "ਿਆ": 21, "ੂੰ": 22, "ਤੇ": 23, "▁ਰ": 24, "▁ਦੀ": 25, "ਸ਼": 26, "▁ਕਿ": 27, "▁ਗ": 28, "▁ਨੂੰ": 29, "▁ਉ": 30, "▁ਕਰ": 31, "ਿੰ": 32, "ਾਨ": 33, "▁ਆ": 34, "ੋਂ": 35, "੍ਰ": 36, "ਆਂ": 37, "▁ਅਤੇ": 38, "▁ਹੋ": 39, "▁ਚ": 40, "▁'": 41, "ਤੀ": 42, "ਦਾ": 43, "ਰੀ": 44, "▁ਦਾ": 45, "ਤਾ": 46, "ੱਚ": 47, "▁ਨੇ": 48, "▁ਇਸ": 49, "੍ਹ": 50, "ਿੱ": 51, "ਹੀ": 52, "ਜ਼": 53, "ਦੇ": 54, "▁ਖ": 55, "▁ਕੀ": 56, "▁ਲਈ": 57, "▁ਨਾਲ": 58, "ਲਾ": 59, "ਹਿ": 60, "▁ਪ੍ਰ": 61, "▁ਵਿੱਚ": 62, "▁ਸ਼": 63, "ੱਕ": 64, "ਹਾ": 65, "▁ਹਨ": 66, "▁ਭ": 67, "ਦੀ": 68, "▁ਤੋਂ": 69, "▁ਜਾ": 70, "▁ਫ": 71, "ਰਾ": 72, "ਵਾ": 73, "▁ਸਿੰ": 74, "▁ਤੇ": 75, "▁ਵੀ": 76, "▁ਵਿਚ": 77, "▁ਸਿੰਘ": 78, "ਣਾ": 79, "੍ਹਾਂ": 80, "ੀਆਂ": 81, "ੱਖ": 82, "ਨਾ": 83, "ਕਾਰ": 84, "ੱਲ": 85, "ੁਰ": 86, "ਵੇ": 87, "▁ਇਹ": 88, "▁ਮੁ": 89, "▁ਸਕ": 90, "ਨ੍ਹਾਂ": 91, "ਟੀ": 92, "▁ਕੇ": 93, "▁ਸੀ": 94, "ਸੀ": 95, "ਿਸ": 96, "▁ਸਮ": 97, "ਦਰ": 98, "▁ਡ": 99, "▁ਕਰਨ": 100, "ਾਈ": 101, "ਿਆਂ": 102, "▁ਇੱਕ": 103, "ਹੀਂ": 104, "ਲੀ": 105, "▁ਆਪ": 106, "ਨੀ": 107, "ਲੇ": 108, "▁ਕੋ": 109, "▁ਸੰ": 110, "▁ਨਹੀਂ": 111, "ੁੰ": 112, "▁ਜਾਂ": 113, "ੈਂ": 114, "ਾਬ": 115, "ਕੇ": 116, "ਾਇ": 117, "▁ਦਿੱ": 118, "▁ਪਰ": 119, "▁ਉਨ੍ਹਾਂ": 120, "ਾਮ": 121, "ਣੇ": 122, "▁ਸਰ": 123, "▁ਉਹ": 124, "ਿਕ": 125, "ਿਲ": 126, "ਰੇ": 127, "ਗਾ": 128, "▁ਜ਼": 129, "▁ਹੀ": 130, "ਿਰ": 131, "ਾਹ": 132, "▁ਘ": 133, "▁ਟ": 134, "ਤਰ": 135, "▁ਕੀਤਾ": 136, "▁ਲੋ": 137, "▁ਉਸ": 138, "ੌਰ": 139, "▁ਕੁ": 140, "▁ਮੰ": 141, "ਣੀ": 142, "▁ਇਕ": 143, "▁ਗਿਆ": 144, "ਡੀ": 145, "▁ਤੁ": 146, "▁ਕਿਸ": 147, "▁ਕਿਹਾ": 148, "▁ਐ": 149, "▁ਵਾਲ": 150, "▁ਪੰ": 151, "▁ਜੋ": 152, "ਕਾ": 153, "ੱਸ": 154, "▁ਸੁ": 155, "▁ਕਾਰ": 156, "ਉਣ": 157, "▁ਬਾ": 158, "▁ਰਾ": 159, "ਹੇ": 160, "ਟਰ": 161, "▁ਕੀਤੀ": 162, "▁ਯ": 163, "▁ਪਾ": 164, "ਨਾਂ": 165, "▁ਧ": 166, "ਗੀ": 167, "▁ਤਾਂ": 168, "ਾਰੇ": 169, "▁ਪੁ": 170, "▁ਸਾ": 171, "ਜੀ": 172, "ਮੀ": 173, "ਫ਼": 174, "ਾਰੀ": 175, "▁ਰਿ": 176, "ੂਰ": 177, "ਸ਼ਨ": 178, "▁ਪੰਜ": 179, "▁ਲੋਕ": 180, "ਗੇ": 181, "▁ਨਾ": 182, "▁ਦਿ": 183, "▁ਕੰ": 184, "▁ਮੌ": 185, "ਹੁ": 186, "▁▁": 187, "ਾ": 188, "ਰ": 189, "ੀ": 190, "ਸ": 191, "ੇ": 192, "ਿ": 193, "ਕ": 194, "ਨ": 195, "ਦ": 196, "ਹ": 197, "ਤ": 198, "ਲ": 199, "ਂ": 200, "ਵ": 201, "ਮ": 202, "ੰ": 203, "ਜ": 204, "ੋ": 205, "ੱ": 206, "ਪ": 207, "ਆ": 208, "ਗ": 209, "ੁ": 210, "਼": 211, "ਬ": 212, "ੈ": 213, "ੂ": 214, "ਚ": 215, "ਅ": 216, "ਇ": 217, "ਣ": 218, "ਟ": 219, "ਖ": 220, "ਈ": 221, "ਉ": 222, "੍": 223, "ਡ": 224, "ਧ": 225, "ਫ": 226, "ਭ": 227, "'": 228, "ਘ": 229, "ੜ": 230, "ੌ": 231, "ਥ": 232, "ਏ": 233, "ਯ": 234, "ਐ": 235, "ਛ": 236, "ਝ": 237, "ਠ": 238, "ਓ": 239, "ਢ": 240, "ਊ": 241, "ਔ": 242, "ੳ": 243, "ੲ": 244, "ਞ": 245, "ਙ": 246, "ੴ": 247, "ੑ": 248, "ੵ": 249, "ਃ": 250, "ਁ": 251, "": 252, "": 253, "": 254, "": 255, "▁": 256, "<pad>": 257}, "large_ta": {"<unk>": 0, "்க": 1, "்த": 2, "ம்": 3, "ன்": 4, "▁ப": 5, "ல்": 6, "க்க": 7, "▁க": 8, "்ட": 9, "▁வ": 10, "த்த": 11, "▁ம": 12, "்ப": 13, "▁அ": 14, "ும்": 15, "▁த": 16, "▁ச": 17, "ிய": 18, "ள்": 19, "ர்": 20, "▁இ": 21, "ரு": 22, "ந்த": 23, "ப்ப": 24, "து": 25, "ட்ட": 26, "▁ந": 27, "ில்": 28, "▁எ": 29, "ங்க": 30, "ைய": 31, "ாக": 32, "ிற": 33, "ின்": 34, "டு": 35, "▁உ": 36, "க்கு": 37, "ிர": 38, "று": 39, "்ச": 40, "ிக": 41, "ார": 42, "ண்ட": 43, "ற்": 44, "த்து": 45, "ள்ள": 46, "ில": 47, "ான": 48, "▁ஆ": 49, "▁மு": 50, "ற்ற": 51, "▁செ": 52, "டி": 53, "▁என்": 54, "ார்": 55, "ர்க": 56, "லை": 57, "▁வி": 58, "▁ஒ": 59, "ட்டு": 60, "வி": 61, "ப்": 62, "ந்து": 63, "ரி": 64, "ளை": 65, "ால்": 66, "தி": 67, "▁கு": 68, "ிரு": 69, "வு": 70, "▁இரு": 71, "ல்ல": 72, "▁அவ": 73, "▁போ": 74, "க்": 75, "▁கொ": 76, "ச்ச": 77, "▁செய": 78, "ின": 79, "ான்": 80, "த்": 81, "▁கா": 82, "▁அத": 83, "▁மா": 84, "▁பெ": 85, "றி": 86, "மை": 87, "▁வே": 88, "ளு": 89, "▁ஒரு": 90, "னை": 91, "த்தில்": 92, "▁இந்த": 93, "க்கும்": 94, "ப்பு": 95, "ாய": 96, "ையில்": 97, "ங்கள்": 98, "▁தொ": 99, "டை": 100, "ற்க": 101, "ம்ப": 102, "ரா": 103, "ர்கள்": 104, "ண்": 105, "ன்ற": 106, "ுவ": 107, "ால": 108, "ஸ்": 109, "ிக்க": 110, "ாவ": 111, "டிய": 112, "▁ஏ": 113, "▁பு": 114, "▁என": 115, "▁வெ": 116, "ண்டு": 117, "ாத": 118, "ன்ன": 119, "▁கூ": 120, "ிறது": 121, "மி": 122, "ாள": 123, "மாக": 124, "ச்": 125, "கள்": 126, "னர்": 127, "ாம்": 128, "றை": 129, "கு": 130, "வே": 131, "ழு": 132, "்கள்": 133, "▁பிர": 134, "▁உள்ள": 135, "▁மற்ற": 136, "ப்பட்ட": 137, "ங்கள": 138, "▁பொ": 139, "▁தெ": 140, "த்தை": 141, "ரிய": 142, "ற்ப": 143, "▁பா": 144, "டுத்த": 145, "▁நட": 146, "ரை": 147, "மான": 148, "▁தே": 149, "ளுக்கு": 150, "ரச": 151, "ட்ச": 152, "ையும்": 153, "்த்த": 154, "திய": 155, "ிட": 156, "▁நீ": 157, "வும்": 158, "ாம": 159, "வர்": 160, "▁என்று": 161, "▁மற்றும்": 162, "▁இத": 163, "▁வா": 164, "ரும்": 165, "ின்ற": 166, "வை": 167, "கள": 168, "▁மே": 169, "ற்று": 170, "▁நா": 171, "மு": 172, "▁ர": 173, "▁என்ற": 174, "ண்டும்": 175, "வத": 176, "▁வழ": 177, "ண்ண": 178, "டும்": 179, "▁பே": 180, "டன்": 181, "▁செய்": 182, "வில்": 183, "னு": 184, "▁சு": 185, "ன்று": 186, "▁அரச": 187, "ர்கள": 188, "▁சொ": 189, "▁செய்த": 190, "ளி": 191, "▁தொட": 192, "▁ஜ": 193, "மா": 194, "▁கோ": 195, "▁வரு": 196, "ிகள்": 197, "டுக": 198, "ழ்": 199, "ிட்ட": 200, "்": 201, "▁▁": 202, "க": 203, "ு": 204, "த": 205, "ி": 206, "ப": 207, "ர": 208, "ம": 209, "ட": 210, "ா": 211, "வ": 212, "ன": 213, "ல": 214, "ை": 215, "ய": 216, "ள": 217, "ற": 218, "ச": 219, "ந": 220, "அ": 221, "ே": 222, "ண": 223, "இ": 224, "ெ": 225, "ோ": 226, "எ": 227, "ங": 228, "ொ": 229, "ழ": 230, "ீ": 231, "உ": 232, "ூ": 233, "ஆ": 234, "ஒ": 235, "ஸ": 236, "ஜ": 237, "ஏ": 238, "ஷ": 239, "ஞ": 240, "ஹ": 241, "ஊ": 242, "ஓ": 243, "ஐ": 244, "ஈ": 245, "ஃ": 246, "ௌ": 247, "ஶ": 248, "ஂ": 249, "ஔ": 250, "ௐ": 251, "ௗ": 252, "": 253, "": 254, "": 255, "▁": 256, "<pad>": 257}, "large_ne": {"<unk>": 0, "▁स": 1, "को": 2, "▁प": 3, "र्": 4, "का": 5, "मा": 6, "्र": 7, "न्": 8, "▁ग": 9, "ले": 10, "ने": 11, "▁र": 12, "्य": 13, "ला": 14, "▁ब": 15, "▁भ": 16, "▁अ": 17, "▁क": 18, "▁व": 19, "▁ह": 20, "▁छ": 21, "▁न": 22, "ार": 23, "▁त": 24, "▁म": 25, "▁द": 26, "▁आ": 27, "▁प्र": 28, "स्": 29, "▁ज": 30, "ता": 31, "क्": 32, "▁उ": 33, "ना": 34, "ति": 35, "ाल": 36, "ान": 37, "यो": 38, "हर": 39, "▁गर्": 40, "एको": 41, "▁गर": 42, "नि": 43, "▁वि": 44, "▁का": 45, "लाई": 46, "त्र": 47, "नु": 48, "ेको": 49, "म्": 50, "वा": 51, "▁य": 52, "िक": 53, "▁हु": 54, "▁च": 55, "था": 56, "ित": 57, "▁नि": 58, "▁ए": 59, "▁ल": 60, "▁मा": 61, "री": 62, "्या": 63, "▁रा": 64, "▁ख": 65, "रा": 66, "▁ला": 67, "▁श": 68, "क्ष": 69, "त्": 70, "▁पनि": 71, "न्द": 72, "▁स्": 73, "या": 74, "▁सं": 75, "▁सा": 76, "ल्": 77, "▁ने": 78, "ेर": 79, "▁थ": 80, "हरू": 81, "▁सम": 82, "▁लाग": 83, "नी": 84, "ाउ": 85, "▁दि": 86, "बा": 87, "ेश": 88, "हि": 89, "ष्": 90, "पाल": 91, "हरु": 92, "न्छ": 93, "दै": 94, "ेका": 95, "हा": 96, "▁हो": 97, "▁फ": 98, "ुर": 99, "पा": 100, "कार": 101, "एका": 102, "दा": 103, "र्य": 104, "रि": 105, "▁थि": 106, "▁छन्": 107, "स्त": 108, "▁भने": 109, "▁त्य": 110, "▁गर्न": 111, "द्": 112, "▁को": 113, "बाट": 114, "▁एक": 115, "▁लागि": 116, "न्त्र": 117, "▁यो": 118, "▁नेपाल": 119, "▁के": 120, "▁पा": 121, "ाम": 122, "क्र": 123, "धि": 124, "▁भएको": 125, "भा": 126, "रण": 127, "्न": 128, "▁ध": 129, "छि": 130, "ष्ट": 131, "वि": 132, "▁उन": 133, "▁गरि": 134, "▁यस": 135, "ही": 136, "▁निर्": 137, "▁रह": 138, "▁घ": 139, "▁सम्": 140, "लो": 141, "ेख": 142, "▁कु": 143, "▁ट": 144, "▁गर्ने": 145, "सा": 146, "▁कार्य": 147, "▁आफ": 148, "▁बता": 149, "ेल": 150, "▁सु": 151, "्च": 152, "स्था": 153, "ारी": 154, "▁पु": 155, "ीय": 156, "▁गरेको": 157, "▁व्य": 158, "▁सर": 159, "न्त": 160, "▁बा": 161, "ँग": 162, "ली": 163, "धान": 164, "गा": 165, "रो": 166, "पर्": 167, "▁ड": 168, "देश": 169, "कारी": 170, "िन": 171, "पछि": 172, "▁क्": 173, "ध्य": 174, "योग": 175, "रह": 176, "भि": 177, "▁तथा": 178, "▁उप": 179, "▁▁": 180, "ा": 181, "्": 182, "र": 183, "न": 184, "क": 185, "ि": 186, "े": 187, "स": 188, "म": 189, "ल": 190, "ो": 191, "त": 192, "प": 193, "य": 194, "ु": 195, "ह": 196, "ी": 197, "ग": 198, "व": 199, "द": 200, "ब": 201, "भ": 202, "ज": 203, "छ": 204, "ए": 205, "ट": 206, "ै": 207, "उ": 208, "अ": 209, "थ": 210, "ध": 211, "च": 212, "श": 213, "ष": 214, "ख": 215, "आ": 216, "ड": 217, "ू": 218, "ँ": 219, "ं": 220, "ण": 221, "ई": 222, "फ": 223, "इ": 224, "ठ": 225, "घ": 226, "ौ": 227, "ृ": 228, "ढ": 229, "ङ": 230, "झ": 231, "ञ": 232, "ओ": 233, "ः": 234, "औ": 235, "ऐ": 236, "ऊ": 237, "ऋ": 238, "ॉ": 239, "़": 240, "ऱ": 241, "ॐ": 242, "ॅ": 243, "ऽ": 244, "ऑ": 245, "॰": 246, "ॠ": 247, "ळ": 248, "ॊ": 249, "ऎ": 250, "ॆ": 251, "ॽ": 252, "ऒ": 253, "ऩ": 254, "ऍ": 255, "▁": 256, "<pad>": 257}} |