adapted_tokenizers/added-opt-hau/opt_500-add_full-hau-opt/added_tokens.json

{
  " APC": 50469,
  " Abdu": 50610,
  " Abubakar": 50742,
  " Abuja": 50629,
  " Afirka": 50701,
  " Alha": 50726,
  " Amurka": 50484,
  " Arewa": 50652,
  " Bayan": 50698,
  " Buhari": 50392,
  " DUBA": 50764,
  " Daga": 50693,
  " Gwamnan": 50750,
  " Gwamnat": 50680,
  " Hausa": 50447,
  " Huk": 50569,
  " Hukumar": 50627,
  " Idan": 50623,
  " Jami": 50757,
  " Jihar": 50474,
  " KAR": 50607,
  " KARANTA": 50633,
  " KU": 50582,
  " Kaduna": 50630,
  " Kano": 50451,
  " Kuma": 50687,
  " Legit": 50450,
  " Majalisar": 50699,
  " Mala": 50639,
  " Muh": 50487,
  " Muhamma": 50504,
  " Muhammadu": 50691,
  " Musul": 50708,
  " Najeriya": 50318,
  " PDP": 50525,
  " Shugaban": 50442,
  " Wannan": 50578,
  " abin": 50337,
  " abo": 50673,
  " abu": 50411,
  " abubu": 50572,
  " ada": 50521,
  " addin": 50718,
  " ai": 50730,
  " aika": 50601,
  " aiki": 50384,
  " aikin": 50420,
  " akan": 50489,
  " ake": 50341,
  " akwai": 50483,
  " ala": 50554,
  " amf": 50359,
  " amfani": 50369,
  " amin": 50548,
  " amince": 50670,
  " amma": 50376,
  " arz": 50675,
  " ayy": 50559,
  " ayyukan": 50672,
  " babban": 50468,
  " babu": 50495,
  " bada": 50697,
  " bai": 50400,
  " baki": 50743,
  " bakin": 50717,
  " bangar": 50711,
  " bara": 50722,
  " bata": 50744,
  " baya": 50422,
  " bayan": 50300,
  " bayar": 50625,
  " bayyana": 50343,
  " binc": 50513,
  " bincike": 50707,
  " bindi": 50573,
  " birnin": 50545,
  " bisa": 50590,
  " biy": 50349,
  " biyu": 50372,
  " buka": 50403,
  " bukatar": 50587,
  " cewa": 50281,
  " cewar": 50517,
  " ci": 50299,
  " cika": 50600,
  " ciki": 50460,
  " cikin": 50278,
  " cin": 50477,
  " cutar": 50544,
  " daban": 50602,
  " dace": 50700,
  " daga": 50282,
  " dai": 50312,
  " daidai": 50728,
  " dake": 50455,
  " dali": 50512,
  " dama": 50496,
  " damar": 50686,
  " dauk": 50409,
  " dauki": 50713,
  " dawo": 50685,
  " daya": 50379,
  " duk": 50314,
  " dukkan": 50752,
  " duniya": 50435,
  " fada": 50657,
  " fara": 50365,
  " farko": 50480,
  " fitar": 50640,
  " fito": 50577,
  " fus": 50608,
  " gaba": 50311,
  " gaban": 50620,
  " gabata": 50703,
  " gabatar": 50724,
  " gan": 50688,
  " ganin": 50458,
  " gano": 50732,
  " garin": 50568,
  " gi": 50320,
  " gida": 50463,
  " gidan": 50448,
  " girma": 50729,
  " guda": 50539,
  " gudan": 50438,
  " gudanar": 50473,
  " gwa": 50694,
  " gwamnan": 50655,
  " gwamnat": 50353,
  " gwamnati": 50541,
  " gwamnatin": 50443,
  " hada": 50490,
  " hai": 50540,
  " haka": 50336,
  " hakan": 50444,
  " halin": 50660,
  " han": 50289,
  " hana": 50658,
  " hanka": 50533,
  " hankali": 50651,
  " hann": 50406,
  " hannu": 50552,
  " hannun": 50659,
  " hanyar": 50439,
  " harkokin": 50761,
  " hu": 50551,
  " huk": 50342,
  " hukum": 50751,
  " hukumar": 50433,
  " idan": 50389,
  " ili": 50741,
  " ina": 50598,
  " inda": 50348,
  " irin": 50413,
  " ita": 50429,
  " iya": 50307,
  " jagor": 50734,
  " jama": 50505,
  " jami": 50430,
  " jari": 50594,
  " ji": 50287,
  " jihar": 50319,
  " jin": 50478,
  " jir": 50676,
  " kafa": 50494,
  " kafin": 50580,
  " kai": 50316,
  " kal": 50756,
  " kam": 50401,
  " kama": 50382,
  " kamar": 50378,
  " kamata": 50589,
  " kamf": 50570,
  " kana": 50740,
  " kar": 50279,
  " kara": 50331,
  " karanta": 50727,
  " kare": 50662,
  " karin": 50654,
  " karka": 50584,
  " karkashin": 50644,
  " kasa": 50296,
  " kasan": 50414,
  " kasance": 50431,
  " kasar": 50297,
  " kasashen": 50536,
  " kashe": 50476,
  " kasu": 50509,
  " kawai": 50563,
  " kawo": 50502,
  " kaya": 50747,
  " kayan": 50571,
  " kir": 50611,
  " kira": 50499,
  " kokar": 50592,
  " kokarin": 50653,
  " koma": 50531,
  " kowa": 50566,
  " kowan": 50696,
  " ku": 50265,
  " kudi": 50558,
  " kudin": 50579,
  " kula": 50616,
  " kuma": 50272,
  " kun": 50518,
  " kungiyar": 50432,
  " kuwa": 50619,
  " kwa": 50347,
  " kwam": 50588,
  " kwan": 50427,
  " kwana": 50647,
  " kya": 50364,
  " kyau": 50609,
  " kyauta": 50763,
  " labar": 50418,
  " labarai": 50532,
  " labaran": 50628,
  " labarin": 50650,
  " lafiya": 50510,
  " lai": 50664,
  " lamarin": 50716,
  " loka": 50324,
  " lokaci": 50557,
  " lokacin": 50356,
  " mafi": 50528,
  " magana": 50646,
  " mai": 50286,
  " majalisar": 50553,
  " maka": 50522,
  " makar": 50576,
  " mala": 50690,
  " mama": 50738,
  " manyan": 50604,
  " mara": 50731,
  " masa": 50434,
  " masu": 50304,
  " mata": 50308,
  " matsa": 50333,
  " matsayin": 50410,
  " maza": 50631,
  " miliyan": 50746,
  " muka": 50549,
  " mulki": 50733,
  " muna": 50762,
  " musa": 50491,
  " musamman": 50535,
  " musu": 50486,
  " mutan": 50332,
  " mutane": 50360,
  " mutanen": 50596,
  " mutu": 50677,
  " mutum": 50421,
  " nau": 50739,
  " neman": 50500,
  " nuna": 50397,
  " raho": 50575,
  " ranar": 50344,
  " rashin": 50527,
  " ri": 50523,
  " riki": 50754,
  " rubu": 50583,
  " ruwa": 50479,
  " saboda": 50404,
  " sabon": 50681,
  " sai": 50317,
  " saka": 50424,
  " sakamakon": 50624,
  " sama": 50538,
  " samar": 50520,
  " samu": 50345,
  " samun": 50395,
  " sana": 50649,
  " sanar": 50472,
  " sanda": 50618,
  " sannan": 50550,
  " sanya": 50560,
  " sau": 50534,
  " sauran": 50457,
  " sha": 50292,
  " shafin": 50666,
  " shai": 50695,
  " shawara": 50759,
  " shekar": 50352,
  " shekara": 50445,
  " shekarar": 50493,
  " shekaru": 50511,
  " shi": 50275,
  " shiga": 50426,
  " shir": 50501,
  " shirin": 50586,
  " shirya": 50702,
  " shugaban": 50322,
  " siya": 50530,
  " siyasa": 50667,
  " sojo": 50671,
  " sosai": 50684,
  " suka": 50283,
  " suke": 50387,
  " suna": 50329,
  " taba": 50758,
  " tabba": 50399,
  " tabbatar": 50459,
  " taima": 50492,
  " taimaka": 50614,
  " takar": 50454,
  " takarar": 50599,
  " tana": 50449,
  " tara": 50526,
  " tarayya": 50720,
  " tare": 50321,
  " taron": 50564,
  " tatta": 50497,
  " tattauna": 50736,
  " tsa": 50303,
  " tsakanin": 50461,
  " tsar": 50338,
  " tsarin": 50581,
  " tsaro": 50508,
  " tso": 50475,
  " tsohon": 50632,
  " uku": 50562,
  " wadan": 50350,
  " wadanda": 50419,
  " wadannan": 50648,
  " wajen": 50357,
  " waki": 50645,
  " wan": 50268,
  " wanda": 50302,
  " wani": 50291,
  " wannan": 50288,
  " wasa": 50723,
  " wasan": 50428,
  " wasu": 50323,
  " wata": 50339,
  " watan": 50373,
  " wato": 50755,
  " wayar": 50689,
  " waɗ": 50705,
  " wu": 50556,
  " wurin": 50617,
  " yace": 50547,
  " yadda": 50328,
  " yake": 50366,
  " yan": 50274,
  " yana": 50310,
  " yankin": 50485,
  " yanzu": 50374,
  " yar": 50407,
  " yau": 50466,
  " yawa": 50519,
  " yawan": 50506,
  " yayi": 50524,
  " yayin": 50425,
  " yi": 50271,
  " yin": 50363,
  " za": 50266,
  " zabe": 50626,
  " zaben": 50456,
  " zai": 50315,
  " zama": 50388,
  " zaman": 50417,
  " zan": 50481,
  " zar": 50423,
  " zargin": 50612,
  " zu": 50622,
  " zuwa": 50313,
  " Ƙ": 50712,
  " ƙ": 50298,
  " ƙa": 50415,
  " ƙar": 50661,
  " ƙasa": 50692,
  " ɗ": 50380,
  " ɗa": 50507,
  " ‘": 50325,
  " ’": 50488,
  " “": 50334,
  ".”": 50514,
  "ANTA": 50606,
  "Ya": 50543,
  "aika": 50452,
  "amma": 50440,
  "anar": 50305,
  "ancin": 50725,
  "anin": 50327,
  "annan": 50391,
  "ansa": 50656,
  "antar": 50635,
  "araba": 50636,
  "arai": 50446,
  "bakar": 50715,
  "bba": 50354,
  "bban": 50381,
  "bbar": 50748,
  "boda": 50375,
  "bun": 50714,
  "buwar": 50704,
  "cce": 50678,
  "cebook": 50561,
  "cen": 50621,
  "dai": 50470,
  "dda": 50290,
  "dun": 50396,
  "duna": 50585,
  "fiya": 50398,
  "fiyar": 50605,
  "gaba": 50760,
  "ganta": 50668,
  "hausa": 50441,
  "himman": 50641,
  "ikin": 50273,
  "inu": 50679,
  "irka": 50615,
  "itin": 50436,
  "iyar": 50284,
  "iye": 50546,
  "iyo": 50453,
  "iyoyin": 50749,
  "iyya": 50465,
  "iyyar": 50358,
  "jali": 50370,
  "jalisar": 50416,
  "jeriya": 50309,
  "jiya": 50642,
  "kanin": 50412,
  "kara": 50361,
  "kiya": 50482,
  "kokin": 50471,
  "kon": 50355,
  "kwa": 50335,
  "kwai": 50393,
  "lata": 50735,
  "legit": 50542,
  "liyan": 50537,
  "llafa": 50683,
  "llon": 50593,
  "mai": 50408,
  "makon": 50503,
  "mala": 50719,
  "marin": 50706,
  "mba": 50462,
  "mman": 50377,
  "onin": 50753,
  "rewa": 50634,
  "sai": 50595,
  "sali": 50515,
  "sana": 50709,
  "sar": 50269,
  "sara": 50437,
  "sarar": 50710,
  "shen": 50351,
  "shin": 50294,
  "sib": 50737,
  "sino": 50597,
  "ssa": 50721,
  "sul": 50669,
  "tsa": 50306,
  "tum": 50394,
  "ugaba": 50516,
  "ugaban": 50295,
  "uhari": 50386,
  "ukan": 50368,
  "ukar": 50591,
  "umma": 50643,
  "unan": 50529,
  "undun": 50663,
  "undunar": 50674,
  "ungiyar": 50362,
  "uniya": 50371,
  "urar": 50567,
  "urin": 50383,
  "urka": 50467,
  "utar": 50385,
  "uwa": 50276,
  "uwar": 50390,
  "wai": 50498,
  "wam": 50285,
  "wamn": 50301,
  "wamna": 50574,
  "wamnan": 50464,
  "wamnat": 50326,
  "wara": 50603,
  "warar": 50682,
  "witter": 50613,
  "yar": 50267,
  "yen": 50402,
  "yin": 50277,
  "yoyi": 50745,
  "yoyin": 50565,
  "yya": 50367,
  "yyan": 50330,
  "yyana": 50340,
  "ƙ": 50280,
  "ƙa": 50555,
  "ɓ": 50405,
  "ɔ": 50665,
  "ɗ": 50293,
  "ɗa": 50637,
  "ɛ": 50638,
  "’": 50270,
  "”": 50346
}