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

{
  " \n": 50440,
  " Afri": 50380,
  " Afrịka": 50725,
  " Ameri": 50648,
  " Igbo": 50467,
  " Ihe": 50518,
  " Lagos": 50603,
  " Mahadum": 50512,
  " Mgbe": 50606,
  " Nai": 50413,
  " Naijiria": 50457,
  " Naị": 50385,
  " Naịjirịa": 50399,
  " Ndị": 50420,
  " Nke": 50605,
  " Onye": 50455,
  " Otu": 50727,
  " Steeti": 50659,
  " abụ": 50330,
  " abụọ": 50348,
  " adị": 50733,
  " afọ": 50314,
  " aga": 50523,
  " agba": 50566,
  " agha": 50487,
  " agụ": 50589,
  " agụmakwụkwọ": 50663,
  " aha": 50417,
  " ahịa": 50432,
  " ahụ": 50287,
  " ahụike": 50744,
  " akp": 50533,
  " akwụkwọ": 50334,
  " akụ": 50351,
  " akụkọ": 50392,
  " akụkụ": 50717,
  " ala": 50400,
  " ama": 50391,
  " anya": 50375,
  " anyị": 50521,
  " anọ": 50480,
  " arụ": 50759,
  " asa": 50450,
  " asaa": 50686,
  " asatọ": 50704,
  " asọmpi": 50726,
  " asụsụ": 50611,
  " atọ": 50418,
  " atụ": 50557,
  " atụmatụ": 50721,
  " azụ": 50616,
  " banyere": 50555,
  " bọọ": 50629,
  " bọọlụ": 50651,
  " bụ": 50274,
  " bụla": 50697,
  " bụrụ": 50401,
  " chọ": 50728,
  " chọrọ": 50747,
  " dị": 50278,
  " dịka": 50368,
  " ebe": 50332,
  " ebu": 50573,
  " ede": 50712,
  " egwu": 50370,
  " egwuregwu": 50517,
  " eji": 50597,
  " elu": 50544,
  " eme": 50405,
  " enwe": 50540,
  " enweghị": 50710,
  " enye": 50734,
  " etu": 50696,
  " eze": 50713,
  " ezi": 50473,
  " gaa": 50645,
  " gara": 50433,
  " gb": 50382,
  " gba": 50377,
  " gbara": 50514,
  " gbasara": 50581,
  " gburu": 50595,
  " gburugburu": 50722,
  " gosi": 50491,
  " gosipụtara": 50698,
  " guzo": 50680,
  " gwara": 50757,
  " gị": 50665,
  " gọọmentị": 50490,
  " gụ": 50383,
  " gụnyere": 50442,
  " họ": 50572,
  " họpụtara": 50654,
  " iche": 50373,
  " igwe": 50706,
  " ihe": 50280,
  " ihu": 50691,
  " iji": 50357,
  " ike": 50345,
  " ikike": 50586,
  " ikpe": 50429,
  " ime": 50421,
  " iri": 50353,
  " ise": 50508,
  " isi": 50322,
  " isii": 50619,
  " iwu": 50412,
  " ji": 50371,
  " jiri": 50762,
  " kacha": 50465,
  " kachasị": 50579,
  " karịrị": 50763,
  " kp": 50365,
  " kpọ": 50751,
  " kpọrọ": 50553,
  " kw": 50335,
  " kwa": 50409,
  " kwu": 50444,
  " kwuo": 50632,
  " kwuru": 50366,
  " kwụ": 50685,
  " kọ": 50452,
  " maara": 50678,
  " maka": 50298,
  " malitere": 50478,
  " mara": 50641,
  " maọ": 50741,
  " mba": 50341,
  " mbụ": 50376,
  " mechara": 50711,
  " mee": 50527,
  " meriri": 50674,
  " mgb": 50549,
  " mgba": 50439,
  " mgbasa": 50669,
  " mgbe": 50346,
  " mkp": 50363,
  " mkpa": 50536,
  " mma": 50306,
  " mmadụ": 50344,
  " mme": 50343,
  " mmekọrịta": 50761,
  " mmiri": 50443,
  " mmụ": 50662,
  " mpaghara": 50437,
  " mụrụ": 50492,
  " naanị": 50656,
  " nakwa": 50534,
  " narị": 50684,
  " nche": 50509,
  " nchekwa": 50657,
  " nchị": 50694,
  " nde": 50568,
  " ndi": 50596,
  " ndu": 50720,
  " ndị": 50275,
  " ndọrọ": 50436,
  " ndụ": 50403,
  " nga": 50550,
  " ngalaba": 50702,
  " ngosi": 50505,
  " ngwa": 50625,
  " niile": 50430,
  " nj": 50506,
  " njem": 50666,
  " nji": 50624,
  " nk": 50326,
  " nka": 50546,
  " nke": 50271,
  " nkiri": 50364,
  " nku": 50692,
  " nkuzi": 50760,
  " nn": 50561,
  " nna": 50507,
  " nne": 50628,
  " nnu": 50633,
  " nnukwu": 50688,
  " nnọ": 50756,
  " nri": 50474,
  " nso": 50530,
  " nsogbu": 50736,
  " nta": 50594,
  " ntu": 50575,
  " ntuli": 50621,
  " nw": 50303,
  " nwa": 50321,
  " nwaanyị": 50714,
  " nwanyị": 50394,
  " nwe": 50369,
  " nwee": 50743,
  " nwere": 50329,
  " nweta": 50703,
  " nwetara": 50609,
  " nwoke": 50484,
  " nwu": 50682,
  " nwunye": 50739,
  " nwụrụ": 50677,
  " ny": 50359,
  " nye": 50548,
  " nyere": 50488,
  " nyocha": 50634,
  " nọ": 50396,
  " obere": 50709,
  " obi": 50486,
  " obibi": 50729,
  " obodo": 50386,
  " oche": 50660,
  " oge": 50398,
  " ojii": 50731,
  " oke": 50526,
  " okp": 50564,
  " okwu": 50459,
  " ole": 50716,
  " ome": 50522,
  " omume": 50630,
  " onwe": 50438,
  " onye": 50281,
  " onyeisi": 50560,
  " osi": 50493,
  " otu": 50308,
  " ozi": 50425,
  " pụtara": 50626,
  " ruo": 50415,
  " rụ": 50462,
  " rụrụ": 50658,
  " siri": 50676,
  " sitere": 50638,
  " steeti": 50407,
  " sị": 50423,
  " tupu": 50610,
  " tụ": 50673,
  " ugbu": 50503,
  " ugbua": 50752,
  " ukwu": 50599,
  " usoro": 50460,
  " uwe": 50479,
  " uweojii": 50604,
  " yana": 50724,
  " ó": 50520,
  " ónyé": 50681,
  " ị": 50294,
  " ịgba": 50668,
  " ịzụ": 50705,
  " Ọ": 50301,
  " ọ": 50268,
  " ọbụ": 50617,
  " ọbụla": 50687,
  " ọchị": 50390,
  " ọchịchị": 50414,
  " ọdị": 50494,
  " ọgwụ": 50649,
  " ọgụ": 50598,
  " ọha": 50653,
  " ọhụrụ": 50563,
  " ọka": 50461,
  " ọkacha": 50707,
  " ọkwa": 50593,
  " ọkụ": 50577,
  " ọma": 50554,
  " ọmụ": 50742,
  " ọn": 50339,
  " ọnwa": 50539,
  " ọnọdụ": 50715,
  " ọnụ": 50419,
  " ọrịa": 50569,
  " ọrụ": 50292,
  " ọsọ": 50670,
  " ọtụtụ": 50384,
  " ọzọ": 50352,
  " Ụ": 50456,
  " Ụlọ": 50732,
  " ụ": 50276,
  " ụbọchị": 50562,
  " ụdị": 50567,
  " ụfọdụ": 50502,
  " ụgbọ": 50532,
  " ụka": 50755,
  " ụlọ": 50315,
  " ụmụ": 50337,
  " ụmụaka": 50664,
  " ụwa": 50496,
  " ụzọ": 50547,
  " “": 50748,
  "Ihe": 50689,
  "abụ": 50738,
  "achị": 50740,
  "adị": 50583,
  "afọ": 50318,
  "agba": 50411,
  "ahụ": 50393,
  "akp": 50446,
  "akpọ": 50571,
  "akwado": 50753,
  "akwụkwọ": 50636,
  "akụ": 50637,
  "anwe": 50558,
  "anyị": 50565,
  "anị": 50623,
  "anọ": 50516,
  "anụ": 50735,
  "arị": 50361,
  "arụ": 50499,
  "atụ": 50723,
  "azụ": 50497,
  "bata": 50758,
  "bere": 50397,
  "bodo": 50360,
  "bịa": 50543,
  "bọ": 50372,
  "bọchị": 50416,
  "bụ": 50270,
  "bụrụ": 50708,
  "chara": 50469,
  "chiri": 50559,
  "chị": 50297,
  "chọ": 50482,
  "dia": 50650,
  "doro": 50642,
  "dum": 50427,
  "dị": 50269,
  "dọrọ": 50402,
  "dụ": 50290,
  "ebe": 50524,
  "egosi": 50730,
  "eji": 50528,
  "ekwu": 50531,
  "elu": 50700,
  "enwe": 50535,
  "enye": 50602,
  "eru": 50683,
  "esịrị": 50749,
  "eti": 50328,
  "etiti": 50501,
  "fọ": 50285,
  "fọdụ": 50447,
  "gara": 50647,
  "gba": 50295,
  "gbe": 50310,
  "gbo": 50355,
  "gboro": 50754,
  "gbu": 50342,
  "gburu": 50618,
  "gbọ": 50410,
  "ghachi": 50672,
  "ghara": 50389,
  "gharị": 50471,
  "ghi": 50580,
  "ghị": 50305,
  "ghọ": 50646,
  "gide": 50485,
  "gos": 50556,
  "gosi": 50395,
  "gw": 50320,
  "gwa": 50449,
  "gwe": 50585,
  "gwu": 50312,
  "gwure": 50463,
  "gwuregwu": 50464,
  "gwọ": 50584,
  "gwụ": 50476,
  "gọ": 50699,
  "gụ": 50350,
  "hadum": 50445,
  "hịa": 50367,
  "họ": 50441,
  "hụ": 50279,
  "hụrụ": 50466,
  "ihe": 50545,
  "ihi": 50477,
  "ikpe": 50613,
  "iwu": 50582,
  "jii": 50451,
  "jiria": 50435,
  "jirịa": 50388,
  "jụ": 50570,
  "karị": 50590,
  "kike": 50513,
  "kp": 50277,
  "kpa": 50701,
  "kpe": 50349,
  "kpo": 50622,
  "kpụ": 50695,
  "kwa": 50288,
  "kwado": 50495,
  "kwara": 50408,
  "kwe": 50481,
  "kwu": 50291,
  "kwọ": 50309,
  "kwụ": 50300,
  "kwụkwọ": 50311,
  "kà": 50607,
  "kọ": 50284,
  "kọrịta": 50515,
  "kọta": 50431,
  "kọwa": 50750,
  "kụ": 50296,
  "kụkọ": 50510,
  "laba": 50591,
  "litere": 50434,
  "lị": 50541,
  "lọ": 50293,
  "lụ": 50454,
  "makwụkwọ": 50601,
  "mara": 50693,
  "matụ": 50661,
  "mba": 50472,
  "mentị": 50424,
  "mgbe": 50718,
  "miri": 50719,
  "mme": 50614,
  "mpi": 50468,
  "mume": 50511,
  "mụ": 50302,
  "mụrụ": 50644,
  "nala": 50690,
  "nter": 50675,
  "nwa": 50600,
  "nwe": 50354,
  "nya": 50331,
  "nyan": 50592,
  "nyanwụ": 50627,
  "nye": 50273,
  "nyere": 50324,
  "nyi": 50453,
  "nyo": 50578,
  "nyocha": 50737,
  "nyé": 50631,
  "nyị": 50325,
  "nụ": 50608,
  "ocha": 50448,
  "oge": 50406,
  "ojii": 50587,
  "okp": 50588,
  "okpuru": 50667,
  "okwu": 50551,
  "olu": 50525,
  "otu": 50538,
  "paghara": 50426,
  "pụ": 50282,
  "pụrụ": 50458,
  "pụta": 50316,
  "pụtara": 50327,
  "rị": 50283,
  "rịa": 50338,
  "rịka": 50679,
  "rịrị": 50652,
  "rịta": 50504,
  "rọ": 50304,
  "rụ": 50272,
  "sara": 50537,
  "soro": 50422,
  "sti": 50612,
  "sị": 50317,
  "sịrị": 50470,
  "sọ": 50387,
  "sọmpi": 50620,
  "sụ": 50358,
  "sụsụ": 50489,
  "tara": 50299,
  "teeti": 50374,
  "tere": 50347,
  "tinye": 50574,
  "tional": 50498,
  "tú": 50746,
  "tị": 50552,
  "tọ": 50323,
  "tụ": 50286,
  "tụta": 50635,
  "tụtụ": 50356,
  "wara": 50483,
  "warị": 50615,
  "wụ": 50378,
  "zinụlọ": 50655,
  "ziri": 50745,
  "zọ": 50313,
  "zụ": 50336,
  "ị": 50267,
  "ịa": 50319,
  "ịka": 50640,
  "ịrị": 50529,
  "Ọ": 50289,
  "Ọrụ": 50576,
  "ọ": 50266,
  "ọdụ": 50500,
  "ọn": 50379,
  "ọnwa": 50475,
  "ọrọ": 50307,
  "ọrụ": 50519,
  "ọv": 50542,
  "ọvanọ": 50671,
  "ọọ": 50340,
  "ọọmentị": 50428,
  "Ụ": 50404,
  "ụ": 50265,
  "ụbọchị": 50643,
  "ụlọ": 50381,
  "ụrụ": 50333,
  "ụzọ": 50639,
  "’": 50362
}