NusaBERT-base-SmSA / added_tokens.json
w11wo's picture
Training in progress, epoch 1
5ad8060 verified
{
"##0e": 30913,
"##abab": 30658,
"##abaya": 30830,
"##abit": 31782,
"##abo": 32013,
"##abungkan": 30614,
"##acan": 31103,
"##adb": 30661,
"##ados": 30819,
"##aduhan": 31609,
"##agaan": 31822,
"##agalan": 30826,
"##agas": 31941,
"##ahag": 30808,
"##ahagian": 31516,
"##ahagikan": 31204,
"##ahar": 30757,
"##ahr": 31165,
"##ahw": 30759,
"##aid": 30981,
"##aik": 30784,
"##aire": 31819,
"##ajeng": 31456,
"##akake": 31722,
"##akamkan": 31025,
"##akeuh": 32010,
"##akeun": 30853,
"##akeup": 32025,
"##akia": 31857,
"##akl": 31098,
"##aklumkan": 30986,
"##akon": 30738,
"##akukeun": 31454,
"##aland": 31163,
"##aliti": 30703,
"##ally": 30786,
"##aluk": 30632,
"##amane": 30547,
"##amonyo": 30814,
"##ampiran": 31561,
"##ams": 30665,
"##ancara": 31756,
"##andh": 31001,
"##angge": 30939,
"##anggeus": 31164,
"##anggo": 31713,
"##angkaian": 31035,
"##angkeun": 31828,
"##aning": 31496,
"##anjaya": 31088,
"##antes": 31854,
"##antos": 30664,
"##antuak": 31564,
"##anyo": 31280,
"##apo": 31741,
"##aptar": 31352,
"##arag": 31205,
"##araha": 30750,
"##arahkan": 31478,
"##arane": 31537,
"##ares": 30878,
"##aritu": 31267,
"##arya": 31180,
"##asane": 31040,
"##asemen": 31716,
"##asifikasi": 31347,
"##astikan": 31935,
"##asup": 30692,
"##atangani": 30933,
"##ateng": 30638,
"##atet": 31078,
"##atip": 30571,
"##autan": 30977,
"##auty": 31678,
"##awis": 31967,
"##awot": 30696,
"##awu": 30535,
"##ayaran": 30767,
"##beauty": 31362,
"##bitkan": 31540,
"##cayaan": 31839,
"##ceae": 30822,
"##cidae": 30708,
"##deon": 31311,
"##ebabkan": 31094,
"##ebaskan": 31023,
"##ebel": 31543,
"##ebor": 31627,
"##echt": 31351,
"##ecio": 31788,
"##edd": 30736,
"##edding": 31208,
"##eden": 31402,
"##edh": 31562,
"##edhi": 31123,
"##edhiy": 31400,
"##edonia": 30834,
"##efinis": 31911,
"##egori": 30616,
"##egoro": 31975,
"##ehanana": 31479,
"##ehna": 30720,
"##ekake": 31558,
"##ekalkan": 30688,
"##ekeu": 30818,
"##ekl": 31404,
"##ektur": 30870,
"##ekut": 30996,
"##ekutuan": 31032,
"##elesaikan": 31885,
"##eleu": 31968,
"##elu": 31458,
"##eluar": 31053,
"##eluaran": 31573,
"##eluarkan": 31658,
"##embagaan": 31396,
"##empor": 31585,
"##ench": 30727,
"##endalikan": 31110,
"##enengan": 31398,
"##engen": 31052,
"##enggan": 31139,
"##engganu": 30776,
"##engi": 31576,
"##engkon": 31790,
"##enne": 31541,
"##ensina": 31709,
"##entah": 31253,
"##enten": 31523,
"##eop": 31005,
"##eor": 30594,
"##epe": 30645,
"##epeu": 31682,
"##epl": 31874,
"##erak": 30606,
"##eres": 31922,
"##erikan": 30653,
"##eris": 31924,
"##eritakan": 31403,
"##erj": 30629,
"##erja": 31089,
"##erjaan": 31913,
"##erjakan": 30879,
"##erl": 31886,
"##erland": 31081,
"##eron": 30576,
"##eroning": 31156,
"##ersi": 31468,
"##ersial": 31239,
"##ertai": 31119,
"##erti": 31132,
"##ertos": 31464,
"##esarkan": 31939,
"##esen": 30944,
"##esimal": 31305,
"##etasi": 31282,
"##etisi": 31444,
"##etoph": 30647,
"##etuj": 30546,
"##etujuan": 31666,
"##eud": 30662,
"##eue": 31829,
"##euen": 30553,
"##eueng": 31701,
"##eug": 30921,
"##euh": 31266,
"##euk": 31093,
"##eul": 32027,
"##euna": 31316,
"##eung": 31210,
"##eunna": 30584,
"##eup": 30752,
"##euu": 31137,
"##eux": 32001,
"##eye": 31850,
"##eza": 30793,
"##faatkan": 32008,
"##fera": 31247,
"##fis": 30960,
"##flik": 30993,
"##ftar": 31144,
"##gaan": 30922,
"##gay": 30668,
"##geon": 31349,
"##geot": 31699,
"##gk": 31101,
"##gro": 31438,
"##gunakake": 30588,
"##hadiran": 31335,
"##hair": 31178,
"##hang": 30982,
"##hee": 31950,
"##hidm": 31060,
"##hidmat": 31310,
"##hidmatan": 31766,
"##hidupan": 31249,
"##hik": 31016,
"##hong": 31961,
"##iae": 30880,
"##iang": 30677,
"##ians": 31092,
"##iao": 31833,
"##iau": 30554,
"##ibut": 31340,
"##iel": 31876,
"##iet": 30542,
"##igan": 31601,
"##igi": 31545,
"##iidae": 30628,
"##ikeun": 31520,
"##ikt": 31591,
"##iktira": 30863,
"##iland": 30962,
"##ilidae": 31652,
"##ilion": 30585,
"##imbulkan": 31474,
"##impen": 30526,
"##impik": 30603,
"##indakake": 31642,
"##ingen": 30732,
"##ingkeun": 30604,
"##inidae": 31297,
"##inten": 31104,
"##inyo": 31925,
"##ions": 32026,
"##ipp": 31470,
"##iriman": 31511,
"##isok": 31462,
"##isyen": 30844,
"##itud": 31252,
"##itude": 31106,
"##itusi": 30876,
"##ivia": 31220,
"##iw": 30621,
"##jata": 31640,
"##kamer": 31451,
"##keun": 31050,
"##klist": 31142,
"##klusif": 30917,
"##kod": 32031,
"##kopan": 31161,
"##kritik": 31070,
"##kt48": 31447,
"##kuasa": 30997,
"##ld": 31390,
"##lec": 31613,
"##leu": 31830,
"##limen": 30899,
"##linawan": 31584,
"##lopedia": 31509,
"##makeup": 31467,
"##malaya": 31290,
"##manapun": 30802,
"##maniyah": 30539,
"##masi": 31549,
"##meub": 31879,
"##meubel": 31287,
"##miah": 31082,
"##namen": 30959,
"##neun": 31207,
"##nick": 31895,
"##nyane": 31831,
"##nyo": 31763,
"##ocera": 31033,
"##odidae": 30672,
"##oge": 31203,
"##ogikeun": 30924,
"##ogon": 30765,
"##ogra": 30940,
"##ogy": 31495,
"##ogyakarta": 31718,
"##ohanan": 31043,
"##oides": 31937,
"##oja": 31951,
"##okake": 31500,
"##okh": 30763,
"##oknyo": 30714,
"##okteran": 31964,
"##ols": 30831,
"##omat": 31754,
"##omatik": 30929,
"##ombor": 31690,
"##omena": 31482,
"##omyia": 31198,
"##omyiidae": 31326,
"##omyza": 31847,
"##oniidae": 31866,
"##onne": 30697,
"##ontalo": 32009,
"##onten": 30530,
"##onyo": 30544,
"##ophagus": 30918,
"##ophila": 31517,
"##ophyl": 30625,
"##ophyllum": 31710,
"##ople": 31375,
"##opogon": 31095,
"##orat": 31412,
"##orbit": 30912,
"##ordial": 30652,
"##orian": 31905,
"##orro": 30755,
"##orus": 31206,
"##oser": 31315,
"##oslav": 31250,
"##ospong": 31041,
"##otr": 30741,
"##otria": 31634,
"##oyeur": 31889,
"##pekeu": 31536,
"##peu": 31048,
"##poe": 31202,
"##raft": 31410,
"##rard": 31217,
"##rentahan": 31483,
"##rilus": 30643,
"##romos": 31071,
"##romosikan": 31177,
"##rys": 31990,
"##semb": 31051,
"##sic": 30975,
"##tau": 31933,
"##teu": 31087,
"##ther": 30775,
"##thi": 31036,
"##tig": 30735,
"##tiwa": 31899,
"##tob": 31461,
"##tos": 31631,
"##trol": 30642,
"##tun": 30579,
"##tung": 30538,
"##tunus": 31118,
"##tural": 30541,
"##uad": 31657,
"##uaikan": 31654,
"##uak": 31547,
"##uakan": 30812,
"##uam": 31603,
"##uatan": 31366,
"##ubarkan": 30891,
"##ube": 31074,
"##ubeul": 30937,
"##ubuhan": 31374,
"##ubuhkan": 31566,
"##uduh": 30649,
"##uduhake": 31019,
"##ugas": 30578,
"##ugi": 31668,
"##uhake": 31985,
"##uhun": 30923,
"##uik": 30932,
"##ukak": 31981,
"##ukeun": 31928,
"##ukeut": 30882,
"##uks": 31146,
"##uksesan": 30558,
"##ukuik": 31187,
"##ulitan": 31918,
"##ulo": 31769,
"##uluy": 31258,
"##umbuhan": 30711,
"##unakeun": 30733,
"##unani": 31359,
"##ungs": 31130,
"##ungsa": 31821,
"##unu": 31556,
"##unung": 31639,
"##unyo": 31837,
"##uo": 31745,
"##upe": 30744,
"##upeu": 31169,
"##upiter": 30783,
"##upo": 30756,
"##urit": 30837,
"##uruahan": 31724,
"##urunan": 30805,
"##uskupan": 30728,
"##usn": 31660,
"##uten": 31548,
"##utuhkan": 30867,
"##utup": 30685,
"##utur": 31873,
"##uv": 30974,
"##uwan": 31893,
"##uwe": 30679,
"##uweni": 31717,
"##uwun": 31952,
"##uwur": 31608,
"##watan": 31428,
"##wegen": 31000,
"##wor": 30854,
"##yane": 31691,
"##ych": 31735,
"##yeo": 31684,
"##yeon": 31459,
"##yeong": 31271,
"##yle": 31560,
"##yli": 30810,
"##yogikeun": 31806,
"##yphi": 31694,
"##yt": 30824,
"##ytih": 31715,
"##yuar": 31345,
"##yuarat": 31832,
"##zidae": 31296,
"##°": 31212,
"##²": 30895,
"##ı": 30988,
"##ł": 30564,
"##α": 31381,
"##ε": 31887,
"##ι": 30781,
"##ο": 30989,
"##а": 31494,
"##е": 30671,
"##и": 31991,
"##н": 31263,
"##о": 31075,
"##р": 31481,
"##с": 31330,
"##ا": 30872,
"##ر": 31047,
"##ل": 31730,
"##م": 30678,
"##ن": 31992,
"##و": 31288,
"##ي": 31122,
"##ᄋ": 31189,
"##ᅡ": 30723,
"##ᅵ": 31793,
"##ᆫ": 31058,
"191": 30587,
"1913": 31641,
"1915": 31662,
"1916": 31890,
"1931": 31068,
"2021": 30712,
"2022": 30675,
"2023": 31411,
"2024": 31006,
"3d": 31712,
"978": 31407,
"ado": 31292,
"adol": 31188,
"adolah": 31936,
"advent": 31687,
"afr": 31878,
"agrilus": 31460,
"agromy": 31259,
"agromyzidae": 30799,
"aia": 31770,
"aircraft": 31096,
"akeh": 31862,
"akhbar": 31059,
"aktip": 30862,
"aktiviti": 31931,
"aleks": 31443,
"align": 30873,
"alit": 30925,
"amarga": 31170,
"amaz": 31302,
"anggo": 30884,
"anjeun": 31743,
"anjeunna": 31471,
"antarab": 30806,
"antarabangsa": 30883,
"antarane": 31661,
"antuk": 31629,
"apal": 31764,
"apost": 31507,
"apostolik": 31140,
"arane": 31883,
"araneae": 31329,
"araneidae": 31544,
"aranj": 31384,
"aranjeunna": 31196,
"aras": 31946,
"arep": 31308,
"argent": 31869,
"armenia": 31725,
"arsit": 31325,
"arth": 32016,
"artic": 31373,
"asilidae": 31853,
"asring": 31945,
"aster": 31435,
"astrag": 31091,
"astragalus": 31649,
"astro": 31864,
"astronomical": 31762,
"atan": 31720,
"atanapi": 30552,
"atawa": 31693,
"ayeuna": 30976,
"azerb": 30754,
"azerbai": 31765,
"azerbaijan": 31295,
"babagan": 31622,
"babar": 31681,
"babarapo": 31587,
"badag": 30930,
"bade": 31863,
"bagean": 31486,
"baharu": 30600,
"baillar": 31619,
"bain": 31807,
"banc": 31797,
"bancian": 31714,
"bandaraya": 31814,
"banglad": 31856,
"banjur": 30871,
"barubah": 30761,
"beau": 30695,
"bebentukan": 31289,
"berbeza": 31927,
"berhad": 30719,
"berhampiran": 30684,
"berhar": 31473,
"berikutan": 31618,
"berkahwin": 31265,
"berket": 31860,
"berketurunan": 31121,
"berkhidmat": 30581,
"berkomp": 30524,
"bersa": 30591,
"bersemp": 31567,
"bersempadan": 31361,
"bersi": 30743,
"berta": 30961,
"bertanggungjawab": 31638,
"berter": 31175,
"bertur": 31803,
"beubeul": 30586,
"beubeulahan": 30597,
"beur": 31273,
"bhar": 31061,
"bhd": 31501,
"biasana": 30928,
"biasane": 31394,
"biaso": 31786,
"biasonyo": 32004,
"bibli": 30570,
"bilion": 30852,
"biography": 31233,
"ble": 31757,
"blo": 31835,
"boga": 31559,
"bohemia": 31066,
"bois": 31758,
"bombyli": 31965,
"bombyliidae": 31838,
"born": 30865,
"boten": 31901,
"broyeur": 30942,
"bulb": 30902,
"bulbophyllum": 31881,
"bulgaria": 31973,
"bungo": 31750,
"bup": 31015,
"cai": 31527,
"calif": 30577,
"californ": 32011,
"carex": 30829,
"carian": 30650,
"carita": 31371,
"cath": 30648,
"cathetan": 30627,
"catholic": 31213,
"cawangan": 30654,
"cecid": 31593,
"cecidomyiidae": 30724,
"centr": 31143,
"ceramb": 31606,
"cerambyc": 31423,
"cerat": 30817,
"ceratopogon": 31490,
"ceratopogonidae": 31904,
"ceuk": 30995,
"chann": 30702,
"chec": 31497,
"chir": 31744,
"chrys": 30710,
"cla": 31773,
"clas": 30908,
"cocog": 30905,
"coleop": 32018,
"collec": 31232,
"cols": 30701,
"colspan": 31960,
"concass": 31069,
"concasseur": 31341,
"const": 31602,
"conv": 31111,
"cov": 31932,
"covid": 30869,
"cuk": 31128,
"cukuik": 31680,
"culic": 31431,
"czech": 31172,
"dados": 31018,
"dakek": 31590,
"dalan": 30694,
"dapek": 31236,
"daptar": 31987,
"darip": 30674,
"darjah": 31317,
"dato": 30839,
"dav": 31632,
"delengen": 31538,
"demokratik": 31849,
"demospong": 31235,
"demospongiae": 30617,
"dendrob": 31811,
"dendrobium": 30823,
"dene": 31115,
"dening": 31031,
"deparet": 30713,
"deparetema": 31953,
"deu": 30657,
"deui": 31272,
"deukeut": 30855,
"deut": 30794,
"dhe": 31184,
"dhew": 31747,
"dhewe": 31283,
"dheweke": 31986,
"dhuwur": 31360,
"dianggo": 31268,
"dianugerah": 31616,
"diarani": 30718,
"dibahagikan": 30999,
"digawe": 31944,
"digunakake": 31328,
"dijad": 30795,
"diji": 30562,
"dikl": 30868,
"dikon": 31109,
"dilancarkan": 30777,
"dima": 31892,
"dimasuk": 30954,
"dinten": 31653,
"dinyat": 31107,
"dipun": 30556,
"diraja": 31772,
"disab": 31650,
"disabuik": 30820,
"disember": 31884,
"diskografi": 31484,
"ditabang": 31337,
"ditabik": 31906,
"ditam": 31298,
"ditamui": 31293,
"ditamukan": 31737,
"ditand": 30596,
"ditem": 31378,
"ditub": 31871,
"ditubuhkan": 31334,
"ditug": 30660,
"diturun": 31583,
"dolich": 31633,
"dolichop": 32017,
"dolichopodidae": 30825,
"domest": 31651,
"donya": 31877,
"doub": 30666,
"dros": 30801,
"drosophila": 31365,
"dunya": 30707,
"durung": 31211,
"dut": 31393,
"duwe": 30935,
"dytis": 31465,
"dytiscidae": 31238,
"eksekut": 31571,
"eksentr": 30994,
"eksped": 31672,
"eksper": 31186,
"elec": 31445,
"eli": 31966,
"elitra": 31085,
"empayar": 30881,
"encyc": 31129,
"encyclopedia": 31554,
"ener": 31336,
"entuk": 30860,
"episod": 30951,
"eropah": 31176,
"eta": 31116,
"eu": 30926,
"eul": 30599,
"eup": 31751,
"f1": 31086,
"fakult": 31949,
"filem": 31569,
"filmografi": 31425,
"fiz": 31453,
"fn": 31324,
"france": 31406,
"gadhah": 31251,
"gaduh": 31891,
"gampong": 30626,
"gancang": 31231,
"gawe": 30739,
"gedena": 31014,
"gedhe": 30866,
"geor": 31331,
"german": 30963,
"geu": 30898,
"geud": 31277,
"geuda": 30893,
"geudae": 31659,
"geun": 31278,
"geur": 30595,
"geure": 31805,
"geus": 31167,
"gov": 30624,
"gra": 31174,
"gubern": 30529,
"guinea": 31222,
"gunong": 31147,
"habitatnyo": 30919,
"hade": 31801,
"hae": 31989,
"haiwan": 30740,
"handap": 30602,
"happ": 30680,
"hass": 30758,
"haut": 31343,
"haute": 31448,
"hayang": 32014,
"hea": 31774,
"hek": 31759,
"helik": 31900,
"henteu": 31387,
"hiduik": 31449,
"hiji": 31630,
"hirup": 31369,
"histeridae": 31727,
"htm": 30749,
"hungaria": 31600,
"hungary": 30910,
"huru": 31020,
"iaitu": 30731,
"ideas": 30792,
"ieu": 31577,
"iha": 31433,
"ija": 31938,
"ikea": 31182,
"iko": 31667,
"iku": 31728,
"imah": 31565,
"imej": 31491,
"indak": 31152,
"indun": 31956,
"indunisia": 30785,
"infan": 30780,
"ingg": 31480,
"inggeris": 30583,
"inggih": 31348,
"ingkang": 31669,
"insee": 31055,
"instit": 31979,
"inyo": 32030,
"ireland": 31391,
"isih": 31221,
"iss": 30936,
"iyan": 31921,
"iyanaritu": 31908,
"jaba": 31413,
"jalma": 31843,
"janten": 31131,
"jawatan": 31332,
"jawatankuasa": 31380,
"jawi": 31304,
"jema": 30548,
"jenayah": 31469,
"jeneng": 30790,
"jepun": 30835,
"jero": 30663,
"jeu": 30991,
"jeun": 31225,
"jeung": 31007,
"jeux": 31815,
"jewel": 30965,
"jih": 32002,
"jinis": 31224,
"johann": 30885,
"jpl": 30734,
"julai": 31930,
"juo": 30676,
"kaasup": 31388,
"kaayaan": 30687,
"kabanyakan": 30630,
"kabeh": 31422,
"kabentuk": 30651,
"kabis": 31787,
"kabiskopan": 30644,
"kabup": 31134,
"kacamatan": 31057,
"kacatet": 31595,
"kada": 31113,
"kados": 31923,
"kaedah": 30590,
"kajadian": 32015,
"kakit": 30877,
"kakitangan": 31489,
"kalas": 31943,
"kalawan": 31370,
"kalayan": 31160,
"kalebu": 31599,
"kaler": 30782,
"kalih": 31553,
"kaliyan": 31522,
"kaluar": 31934,
"kalurahan": 30858,
"kamb": 31488,
"kanak": 30833,
"kangge": 31201,
"kanggo": 30716,
"kanthi": 31190,
"kapalo": 30534,
"kaping": 30540,
"karak": 31820,
"kardinal": 31320,
"kareh": 31312,
"kareta": 30641,
"karusakan": 31947,
"kary": 31084,
"kasal": 31257,
"kasaluruahan": 31909,
"kasebut": 31193,
"katon": 31685,
"kaul": 31903,
"kaulinan": 31285,
"kaun": 31851,
"kaunti": 31179,
"kawa": 31721,
"kawalan": 31199,
"kawas": 30953,
"kayata": 31097,
"kebi": 32003,
"kedah": 31321,
"kedi": 30686,
"kejohanan": 30725,
"kelab": 31607,
"kelantan": 31322,
"kelu": 31733,
"kemend": 31644,
"kemp": 30598,
"kemudiannya": 31719,
"kemunc": 31656,
"kender": 31240,
"kenderaan": 30768,
"kene": 31073,
"keneh": 31533,
"keng": 31539,
"kerjaya": 31151,
"kerusi": 30949,
"kesihatan": 31524,
"ketuj": 31318,
"keu": 31825,
"keur": 31389,
"kewangan": 31485,
"khalif": 31044,
"kitu": 30864,
"kiw": 30525,
"km2": 30859,
"km²": 31417,
"kolej": 31003,
"komand": 31610,
"komuniti": 31150,
"kontrov": 30914,
"kowe": 31145,
"kristian": 31702,
"kula": 31792,
"kulawar": 31983,
"kulawarga": 30764,
"kumaha": 31915,
"kunj": 31197,
"kura": 31319,
"kuring": 31300,
"kutha": 31242,
"kuwe": 30700,
"kuwi": 30816,
"labiah": 30770,
"laborat": 31706,
"lair": 30946,
"lajeng": 31916,
"lalek": 31477,
"laluan": 31840,
"lambok": 30704,
"lamela": 30746,
"lamun": 30956,
"lanang": 31997,
"langau": 31655,
"langk": 31112,
"langkung": 31784,
"lapan": 31215,
"larv": 31125,
"larvanyo": 30698,
"lawah": 31429,
"laweh": 31813,
"left": 31344,
"lengkep": 31748,
"ler": 32007,
"leres": 31275,
"leu": 31674,
"leung": 31988,
"leutik": 31008,
"leuwih": 30766,
"lian": 31230,
"limoniidae": 30640,
"linyphi": 31379,
"linyphiidae": 31090,
"liwat": 31550,
"liya": 31042,
"liyane": 31704,
"loba": 31977,
"loro": 31260,
"lua": 30592,
"lumb": 31824,
"luwih": 30927,
"maca": 30567,
"madras": 31476,
"magnit": 31382,
"maharaja": 30573,
"mahisok": 30791,
"majoriti": 30888,
"makeupmakeup": 30634,
"makh": 30957,
"maklumat": 31917,
"malalui": 31795,
"malaya": 31817,
"malih": 31046,
"mamakan": 31248,
"mamb": 30673,
"mamiliki": 30574,
"mampunyo": 30760,
"mampunyoi": 32024,
"manawa": 31368,
"maneh": 31802,
"manehna": 31426,
"manggerek": 31605,
"mangr": 31157,
"mangrup": 31354,
"mangrupa": 31836,
"mangrupikeun": 30637,
"manj": 31356,
"manjadi": 31114,
"mano": 31083,
"manungsa": 31149,
"manusa": 31636,
"manyebabkan": 31270,
"maran": 31826,
"maranehanana": 30549,
"marang": 30947,
"marcapada": 30916,
"marie": 30909,
"marin": 31705,
"marit": 31307,
"marupo": 31896,
"marupokan": 31487,
"masar": 31776,
"masarakat": 31223,
"maso": 31314,
"matemat": 31872,
"mato": 31392,
"matoari": 30774,
"mats": 30689,
"mawa": 31138,
"mbukak": 31783,
"medal": 30797,
"meks": 30721,
"melaka": 30601,
"melint": 31697,
"melu": 31284,
"memberit": 30560,
"mempel": 30875,
"memulakan": 30836,
"menand": 30639,
"menehi": 30635,
"menerusi": 31209,
"mengandungi": 31612,
"mengekalkan": 31816,
"mengkl": 31753,
"mengut": 30771,
"menika": 30618,
"menyang": 30593,
"menyokong": 31998,
"mere": 30990,
"mesyuarat": 31574,
"meu": 32022,
"meub": 31912,
"meubel": 31395,
"meubels": 31781,
"meubl": 31907,
"meuble": 31457,
"meubles": 31355,
"meul": 31580,
"meulage": 30889,
"meun": 31030,
"meunang": 31980,
"mib": 30715,
"mich": 30633,
"militar": 31108,
"military": 31778,
"mimiti": 31880,
"minangk": 31643,
"minangka": 30966,
"minangkab": 31542,
"minit": 31377,
"misuwur": 31463,
"miturut": 30955,
"miw": 31971,
"miwah": 31531,
"moal": 31551,
"moden": 31200,
"mohamad": 30769,
"mohd": 31589,
"mp3": 30745,
"mpo": 31823,
"mudo": 31227,
"mukim": 31519,
"mungg": 30843,
"munisip": 31077,
"munisipalitas": 31518,
"muscidae": 30730,
"mutlakna": 30938,
"mutlaknyo": 31568,
"muzik": 31427,
"myc": 31740,
"mycetoph": 30964,
"mycetophilidae": 30619,
"nae": 31647,
"nagara": 31775,
"naha": 31183,
"naib": 31530,
"najib": 30842,
"nakeuh": 31929,
"nalika": 31746,
"namo": 31062,
"namp": 31581,
"nangg": 31262,
"nanging": 31663,
"naon": 30536,
"ndh": 30827,
"nduweni": 31976,
"nektar": 30838,
"nemb": 30550,
"nenten": 30726,
"neol": 31353,
"nepi": 31578,
"ngad": 30706,
"ngag": 30659,
"ngagaduhan": 30543,
"ngagunakeun": 30615,
"ngah": 31063,
"ngal": 31808,
"ngali": 30646,
"ngam": 30622,
"ngand": 31009,
"nganggo": 31346,
"nganj": 31450,
"nganjrek": 31475,
"nganti": 31810,
"ngar": 31424,
"ngaran": 31646,
"ngarep": 30729,
"ngatur": 30911,
"ngen": 31323,
"ngeun": 30809,
"ngeunaan": 31615,
"nggawe": 31957,
"nggunakake": 30840,
"ngirim": 31437,
"ngiring": 30887,
"ngis": 31281,
"ngisor": 31673,
"ngo": 30709,
"ngom": 30821,
"ngon": 31013,
"ngora": 32000,
"ngr": 31017,
"ngu": 32029,
"nib": 31127,
"ningali": 31861,
"ningkat": 31357,
"njaba": 30572,
"njupuk": 30903,
"nombor": 31711,
"nord": 31692,
"norway": 30848,
"nps": 30847,
"npsn": 31439,
"nuduhake": 30985,
"nurwegen": 30958,
"nyaeta": 31779,
"nyan": 31279,
"nyang": 31333,
"nye": 30705,
"nyieun": 31910,
"nyo": 31309,
"nyoe": 31800,
"oge": 30972,
"ogos": 31409,
"oksi": 30561,
"olahr": 31269,
"olimpik": 31099,
"omah": 30667,
"ono": 31034,
"onth": 31158,
"onthophagus": 31214,
"ortod": 31286,
"ouv": 31780,
"owl": 31024,
"pacahan": 31535,
"padha": 31926,
"pado": 31430,
"pahang": 31022,
"pahl": 31234,
"pama": 31635,
"pamaen": 31645,
"pamake": 31440,
"pamar": 31397,
"pamarentah": 31628,
"pamb": 30575,
"pambantu": 30568,
"pambantuakan": 31563,
"pamrentahan": 31408,
"pandemi": 31446,
"panganan": 30971,
"panggerek": 31029,
"pangguna": 30832,
"pangl": 31383,
"panjangnyo": 30742,
"panjenengan": 31011,
"panon": 31623,
"panonpoe": 31752,
"pany": 31870,
"parai": 31512,
"paraiaran": 30807,
"parairan": 31141,
"parantos": 31555,
"parl": 31504,
"parlimen": 30907,
"pautan": 31166,
"pelab": 31848,
"pelakon": 30608,
"pelanc": 31614,
"pembahagian": 31648,
"pemberont": 31162,
"pembun": 31229,
"pengamb": 30636,
"pengangk": 31897,
"pengarah": 31120,
"pengerusi": 32023,
"penghar": 30943,
"penil": 31809,
"pentadb": 30565,
"pentadbiran": 30748,
"penubuhan": 30607,
"perad": 31846,
"perangan": 30527,
"peratus": 31416,
"perband": 31421,
"perbandaran": 31105,
"perger": 31841,
"peribadi": 31942,
"pering": 31195,
"perkahw": 30979,
"perkahwinan": 30945,
"perkhidmatan": 30537,
"perlembagaan": 30813,
"perlis": 30569,
"perma": 31159,
"perni": 30845,
"perniagaan": 30811,
"persa": 31261,
"persek": 31670,
"pertamo": 30656,
"pertub": 30856,
"pertubuhan": 31844,
"perub": 31299,
"perubatan": 31683,
"petempatan": 31254,
"peu": 31102,
"peugeot": 30533,
"peun": 30751,
"peus": 31192,
"philipp": 30531,
"phor": 31842,
"phoridae": 30747,
"pierre": 31056,
"pikeun": 30753,
"pingat": 31620,
"pirang": 31510,
"pisan": 31799,
"pisanan": 31514,
"piy": 31845,
"piyamb": 31244,
"piyambak": 31579,
"piyambakipun": 31552,
"pkr": 31503,
"planetesimal": 30992,
"planetis": 31898,
"platnick": 31789,
"plek": 31827,
"poe": 31818,
"poh": 30737,
"poland": 31671,
"polen": 30987,
"pont": 30788,
"popul": 30849,
"porifera": 30920,
"poskod": 31700,
"pour": 30779,
"praj": 31372,
"pratelan": 31027,
"prefiks": 31264,
"presid": 31154,
"prix": 31611,
"produs": 31996,
"projek": 31664,
"prote": 31100,
"protel": 30948,
"protelean": 31665,
"psychodidae": 31418,
"psychotria": 31902,
"publishing": 31749,
"pungkasan": 31026,
"punika": 31338,
"puniki": 31597,
"punyo": 31148,
"purata": 31515,
"pusingan": 31738,
"railway": 31729,
"rakan": 31621,
"rasmi": 30846,
"rawatan": 31376,
"razak": 31054,
"rd1": 31959,
"reference": 31970,
"referensina": 31804,
"reka": 31493,
"rekod": 31972,
"remp": 30690,
"rese": 31958,
"ringkasnya": 31962,
"rings": 31686,
"ringtones": 31405,
"riw": 31505,
"robah": 31676,
"romania": 31798,
"rows": 32005,
"rowspan": 30973,
"rujuakan": 31582,
"rump": 31734,
"runt": 31181,
"s1": 31010,
"sabab": 30931,
"sababaraha": 30978,
"sabagai": 30669,
"sabah": 31350,
"saben": 31313,
"sabo": 30952,
"saboh": 30545,
"sabuah": 31993,
"sabuak": 31012,
"sacara": 31791,
"sacaro": 30950,
"sada": 30623,
"sadaya": 31731,
"sadur": 31506,
"sadurunge": 31812,
"sae": 31859,
"sagadang": 30566,
"sagala": 31696,
"saged": 31529,
"saha": 30851,
"sahiji": 31767,
"saik": 31135,
"saiki": 31079,
"saikua": 31126,
"sajarah": 31755,
"sajeroning": 30967,
"sakab": 30620,
"sakabeh": 31768,
"sakola": 30523,
"sakum": 31982,
"sakumna": 31452,
"salain": 31955,
"salaku": 31472,
"salle": 31124,
"saltic": 30934,
"salticidae": 31339,
"samant": 30970,
"samantaro": 31256,
"samem": 31049,
"sami": 30998,
"sampun": 31420,
"sanajan": 31796,
"sane": 31528,
"sanes": 31419,
"sanggeus": 31072,
"sangkan": 31133,
"saperti": 30894,
"sapertos": 31243,
"sarawak": 30532,
"sarekat": 31598,
"sareng": 31994,
"saroman": 30557,
"sarta": 30699,
"sarua": 31173,
"sarupo": 30796,
"sasuatu": 30778,
"satungg": 31760,
"sawet": 31219,
"sawetara": 31021,
"sawij": 30563,
"sawijining": 31625,
"sawise": 31466,
"sayoknyo": 31723,
"scarab": 31191,
"scarabae": 30522,
"scarabaeidae": 31080,
"scope": 31028,
"sebag": 31171,
"sebal": 30789,
"sebarang": 30717,
"sedeng": 31508,
"sedengkeun": 31301,
"seek": 31914,
"sejen": 31679,
"seksyen": 30610,
"selanjut": 31064,
"sempadan": 31688,
"senarai": 31888,
"senecio": 31291,
"sepanyol": 31414,
"sepur": 31434,
"seramai": 31919,
"serb": 31984,
"sese": 31732,
"seset": 31882,
"sesetengah": 31246,
"setiausaha": 31739,
"setidak": 30580,
"seue": 31327,
"seueur": 31617,
"seul": 31575,
"seuwa": 31855,
"sij": 31978,
"siji": 31546,
"singh": 30815,
"sira": 30691,
"sisih": 30762,
"sken": 31185,
"slov": 31592,
"slovakia": 31364,
"societ": 30693,
"socorro": 31761,
"soest": 31168,
"sokongan": 30681,
"sora": 31974,
"sorangan": 30670,
"sous": 31624,
"sov": 31940,
"squar": 31039,
"staphy": 30874,
"staphylin": 31703,
"staphylinidae": 31502,
"stasion": 30612,
"stesen": 31604,
"sukan": 31532,
"sumat": 30559,
"swara": 31194,
"syarikat": 31386,
"taban": 31695,
"tabanidae": 30722,
"tabantuak": 31834,
"tacatat": 31596,
"tach": 31736,
"tachinidae": 31038,
"tagolong": 31498,
"talatak": 31002,
"talian": 31858,
"tamil": 31513,
"tampek": 32012,
"tanduak": 31742,
"tarikh": 31995,
"tegese": 31216,
"teka": 31436,
"telef": 31771,
"telefon": 31136,
"telev": 31999,
"television": 30904,
"televisyen": 30800,
"tembung": 30969,
"tempatan": 30803,
"tempoh": 31237,
"tengku": 31358,
"tentera": 31948,
"teph": 31441,
"tephrit": 31303,
"tephritidae": 31526,
"terengganu": 31067,
"terhad": 31954,
"terut": 31274,
"terutamanya": 31276,
"teu": 30861,
"teub": 31521,
"teuing": 30901,
"tha": 30611,
"thom": 31367,
"tiasa": 30655,
"tig": 31572,
"tilu": 31777,
"timbalan": 30787,
"tingga": 30897,
"tinimbang": 31226,
"tipul": 32006,
"tipula": 32019,
"tipulidae": 32021,
"tiyang": 31875,
"tre": 31415,
"troya": 30900,
"tug": 30772,
"tuluy": 31677,
"tumb": 30798,
"tumbu": 30850,
"tunggil": 31385,
"turk": 31228,
"tutumbu": 30683,
"tuw": 30984,
"tuwawu": 31969,
"ubat": 30892,
"uel": 30589,
"uga": 30841,
"ugi": 31255,
"ulekl": 31401,
"umno": 30983,
"umumnyo": 31689,
"undi": 31455,
"unggal": 31726,
"universiti": 31594,
"untuak": 32028,
"upami": 31867,
"ureueng": 31037,
"utamo": 30941,
"utawa": 31852,
"utawi": 31004,
"vasque": 30605,
"vcard": 32020,
"veg": 31492,
"vl": 31637,
"waktos": 31342,
"walanda": 31432,
"wangsa": 31708,
"wangun": 31306,
"warsa": 30682,
"wates": 31707,
"wawengkon": 31868,
"wayah": 31294,
"wek": 31570,
"wektu": 30804,
"wenten": 30555,
"wer": 30773,
"wewengkon": 30609,
"wikip": 30890,
"wiw": 31218,
"wiwit": 31894,
"woh": 30886,
"wonten": 31920,
"worms": 30521,
"yaiku": 31794,
"yening": 30906,
"yito": 31963,
"yout": 30582,
"zealand": 31117,
"°": 31045,
"°c": 30857,
"²": 31698,
"ı": 31675,
"ł": 30915,
"α": 30980,
"ε": 31442,
"ι": 30828,
"ο": 31245,
"а": 31626,
"е": 30613,
"и": 31588,
"н": 31076,
"о": 31155,
"р": 31153,
"с": 31865,
"ا": 30631,
"ال": 30551,
"ر": 31557,
"ل": 31499,
"م": 31065,
"ن": 30528,
"و": 30968,
"ي": 31241,
"ᄋ": 31525,
"ᅡ": 31399,
"ᅵ": 31534,
"ᆫ": 31363,
"—": 31586,
"•": 30896,
"…": 31785
}