Upload evaluation/language_fertility.csv with huggingface_hub

evaluation/language_fertility.csv

@@ -0,0 +1,107 @@
+code,autonym,spanish_name,inali_name,english_name,samples,chars,utf8_bytes,tokens,chars_per_token,tokens_per_char,bytes_per_token,tokens_per_byte,round_trip
+cya,Chaꞌtñan,Chatino de Nopala,chatino oriental bajo,Nopala Chatino,2,1007,1019,251,4.01195219123506,0.24925521350546176,4.059760956175299,0.2463199214916585,True
+tzo,Bats'i k'op,Tsotsil,tsotsil del centro,Tsotsil,4,2015,2199,531,3.7947269303201505,0.26352357320099257,4.141242937853107,0.24147339699863574,True
+sei,Cmiique Iitom,Seri,seri,Seri,3,1511,1531,413,3.6585956416464893,0.27332892124420916,3.7070217917675543,0.2697583278902678,True
+mio,Tuhun Ñuun Ñucaan,Mixteco de Pinotepa Nacional,mixteco del oeste de la costa,Pinotepa Nacional Mixtec,4,2015,2186,557,3.6175942549371634,0.27642679900744416,3.9245960502693,0.25480329368709975,True
+yua,Maaya t'aan,Maya de Yucatán,maya,Yucatec Maya,5,2519,2945,700,3.5985714285714288,0.277888050813815,4.207142857142857,0.23769100169779286,True
+trc,Xnaꞌánj nu̱ꞌ,Triqui de Copala,triqui de San Juan Copala,Copala Triqui,3,1511,1791,421,3.5890736342042757,0.2786234281932495,4.254156769596199,0.2350642099385818,True
+tzh,Bats'il k'op,Tzeltal,tseltal del occidente,Tzeltal,2,1007,1102,282,3.5709219858156027,0.2800397219463754,3.9078014184397163,0.2558983666061706,True
+nhw,Nahuatl,Náhuatl Huasteco Occidental,náhuatl de la Huasteca potosina,Western Huasteca Nahuatl,4,2015,2015,573,3.5165794066317626,0.2843672456575682,3.5165794066317626,0.2843672456575682,True
+top,"Lichiwin Tutunaku, Tutunakú",Totonaco de Papantla,totonaco de la costa,Papantla Totonac,5,2519,2582,717,3.513249651324965,0.2846367606192934,3.601115760111576,0.27769171185127806,True
+nhe,Mexkatl,Náhuatl Huasteco Oriental,náhuatl de la Huasteca veracruzana,Eastern Huasteca Nahuatl,4,2015,2083,579,3.4801381692573403,0.2873449131513648,3.597582037996546,0.27796447431589055,True
+zai,Diidxazá,Zapoteco del Istmo,zapoteco de la planicie costera,Isthmus Zapotec,4,2015,2234,583,3.456260720411664,0.2893300248138958,3.8319039451114922,0.26096687555953446,True
+nhm,"Ika mejikano, Ika nauatl",Náhuatl de Morelos,mexicano central bajo,Morelos Nahuatl,3,1511,1511,439,3.441913439635535,0.29053606882859034,3.441913439635535,0.29053606882859034,True
+ncx,,Náhuatl de Puebla Central,náhuatl del centro de Puebla,"Nahuatl, Central Puebla",5,2519,2554,742,3.394878706199461,0.2945613338626439,3.442048517520216,0.29052466718872355,True
+amu,"Ñomndaa, Ñomndaa Suljaaꞌ",Amuzgo de Guerrero,amuzgo del norte,Guerrero Amuzgo,4,2015,2521,596,3.3808724832214767,0.29578163771712157,4.22986577181208,0.2364141213804046,True
+mhc,Mocho',Motozintleco,mocho’,Mocho,4,2015,2021,596,3.3808724832214767,0.29578163771712157,3.390939597315436,0.29490351311232066,True
+tpp,Lhichiwin,Tepehua de Pisaflores,tepehua del norte,Pisaflores Tepehua,4,2015,2099,598,3.369565217391304,0.2967741935483871,3.5100334448160537,0.2848975702715579,True
+tee,Lhima'alh'ama',Tepehua de Huehuetla,tepehua del sur,Huehuetla Tepehua,4,2015,2052,603,3.341625207296849,0.2992555831265509,3.4029850746268657,0.29385964912280704,True
+huv,Ombeayiüts,Huave de San Mateo del Mar,huave del oeste,San Mateo del Mar Huave,3,1511,1600,465,3.249462365591398,0.30774321641297153,3.4408602150537635,0.290625,True
+maj,"Kinꞌekꞌatiya, Ntaxjo̱",Mazateco de Jalapa de Díaz,mazateco del este bajo,Jalapa de Díaz Mazatec,1,503,507,156,3.2243589743589745,0.3101391650099404,3.25,0.3076923076923077,True
+cux,Cuicateco yeⁿꞌe Tepeuxila,Cuicateco de Tepeuxila,cuicateco del centro,Tepeuxila Cuicatec,3,1511,1828,469,3.2217484008528783,0.31039046988749175,3.8976545842217485,0.2565645514223195,True
+meh,Tu̱ꞌun káꞌánꞌ kájí,Mixteco del Suroeste de Tlaxiaco,mixteco del suroeste,Southwestern Tlaxiaco Mixtec,3,1511,1552,470,3.2148936170212767,0.3110522832561218,3.302127659574468,0.30283505154639173,True
+ctu,"Ch'ol, Lakty’añ",Ch'ol,ch’ol del noroeste,Chol,3,1511,1753,471,3.208067940552017,0.3117140966247518,3.721868365180467,0.26868225898459785,True
+mat,bot’una,Matlatzinca de San Francisco,matlatzinca,"Matlatzinca, San Francisco",3,1511,1619,478,3.1610878661087867,0.31634679020516215,3.3870292887029287,0.29524397776405187,True
+ncj,Mexicatl,Náhuatl del Norte de Puebla,náhuatl alto del norte de Puebla,Northern Puebla Nahuatl,4,2015,2035,640,3.1484375,0.3176178660049628,3.1796875,0.3144963144963145,True
+yaq,Yo'em noki,Yaqui,yaqui,Yaqui,4,2015,2110,642,3.1386292834890965,0.3186104218362283,3.2866043613707165,0.3042654028436019,True
+lac,Jach-t'aan,Lacandón,lacandón,Lacandon,5,2519,2820,803,3.136986301369863,0.31877729257641924,3.511830635118306,0.2847517730496454,True
+maz,Jñatjo,Mazahua Central,mazahua de oriente,Central Mazahua,3,1511,1702,484,3.121900826446281,0.3203176704169424,3.5165289256198347,0.28437132784958874,True
+toj,Tojol-ab'al,Tojolabal,tojolabal,Tojolabal,4,2015,2196,647,3.114374034003091,0.3210918114143921,3.394126738794436,0.2946265938069217,True
+mie,Tūhun sāsávī,Mixteco de Ocotepec,mixteco de Sierra sur noroeste,Ocotepec Mixtec,4,2015,2238,648,3.109567901234568,0.3215880893300248,3.4537037037037037,0.289544235924933,True
+tos,Totonaco,Totonaco de la Sierra,totonaco central del sur,Highland Totonac,4,2015,2088,651,3.0952380952380953,0.3230769230769231,3.207373271889401,0.3117816091954023,True
+azn,Meshikan de San Agustin Buenaventura y de Santa Cruz,Náhuatl de Durango Occidental,mexicano del noroeste,Western Durango Nahuatl,4,2007,2026,652,3.0782208588957056,0.32486297957149973,3.107361963190184,0.32181638696939785,True
+ocu,pjiekak'joo,Tlahuica,tlahuica,Tlahuica,3,1511,1644,491,3.0773930753564156,0.3249503639973527,3.3482688391038695,0.298661800486618,True
+nhy,Nāhuatlahtōlli,Náhuatl del Norte de Oaxaca,náhuatl de Oaxaca,Northern Oaxaca Nahuatl,5,2519,2587,820,3.071951219512195,0.3255260023818976,3.1548780487804877,0.31696946269810594,True
+hus,Teenek,Huasteco,huasteco del occidente,Huastec,3,1450,1585,473,3.06553911205074,0.32620689655172413,3.350951374207188,0.29842271293375394,True
+zaq,Tisa,Zapoteco de Aloápam,zapoteco de San Miguel Aloápam,Aloápam Zapotec,3,1511,1675,503,3.003976143141153,0.3328921244209133,3.3300198807157058,0.30029850746268655,True
+pls,Ngigua,Popoloca de San Marcos Tlacoyalco,popoloca del norte,San Marcos Tlacoyalco Popoloca,1,503,513,168,2.994047619047619,0.33399602385685884,3.0535714285714284,0.32748538011695905,True
+pia,Oob No'ok,Pima Bajo,pima del sur,Pima Bajo,4,2015,2189,676,2.980769230769231,0.33548387096774196,3.2381656804733727,0.30881681132937416,True
+nsu,"Nahuatl, Nahuatlajtoli",Náhuatl de la Sierra Negra,"náhuatl de la Sierra negra, sur",Sierra Negra Nahuatl,3,1511,1548,509,2.968565815324165,0.3368630046326936,3.0412573673870336,0.32881136950904394,True
+ntp,Oodamicʌdʌ,Tepehuano del Norte,tepehuano del norte,Northern Tepehuan,3,1511,1638,509,2.968565815324165,0.3368630046326936,3.218074656188605,0.31074481074481075,True
+mix,"Sa'an Savi Snuviko, Sa'an savi",Mixteco de Mixtepec,mixteco de Ñumi,Mixtepec Mixtec,3,1511,1669,512,2.951171875,0.3388484447385837,3.259765625,0.3067705212702217,True
+tqt,Xinulajgsípij Totonaco,Totonaco del Cerro Xinolatépetl,totonaco del cerro Xinolatépetl,Totonaco del cerro Xinolatépetl,4,2015,2057,683,2.950219619326501,0.3389578163771712,3.0117130307467055,0.332036947010209,True
+tsz,"P’urhe, P’urhépecha",Purépecha,purépecha,Purepecha,3,1511,1590,513,2.94541910331384,0.33951025810721375,3.0994152046783627,0.32264150943396225,True
+zoq,,Zoque de Tabasco,zoque del este,"Zoque, Tabasco",3,1511,1605,514,2.9396887159533076,0.34017207147584383,3.122568093385214,0.3202492211838006,True
+nch,Nāhuatlahtōlli,Náhuatl Huasteco Central,mexicano de la Huasteca Hidalguense,Central Huasteca Nahuatl,3,1511,1511,515,2.933980582524272,0.34083388484447386,2.933980582524272,0.34083388484447386,True
+pei,,Chichimeco Jonaz,chichimeco jonaz,Chichimeco-Jonaz,3,1511,1725,515,2.933980582524272,0.34083388484447386,3.349514563106796,0.2985507246376812,True
+ngu,Nauatlajtojli,Náhuatl de Guerrero,mexicano de Guerrero,Guerrero Nahuatl,4,2015,2020,691,2.9160636758321274,0.34292803970223323,2.923299565846599,0.3420792079207921,True
+mxt,Sa'an Xiñi Savi,Mixteco de Jamiltepec,mixteco de Oaxaca de costa central baja,Jamiltepec Mixtec,3,1511,1672,519,2.9113680154142583,0.343481138318994,3.2215799614643545,0.3104066985645933,True
+mza,Tu'un va'a,Mixteco de Santa María Zacatepec,mixteco de Sierra sur oeste,Santa María Zacatepec Mixtec,3,1511,1780,520,2.9057692307692307,0.3441429516876241,3.423076923076923,0.29213483146067415,True
+coz,,Chocholteco,chocholteco del oeste,Chocholtec,3,1511,1591,521,2.9001919385796544,0.3448047650562541,3.053742802303263,0.3274670018856065,True
+zaa,Titsaꞌ,Zapoteco de la Sierra de Juárez,"zapoteco serrano, bajo",Sierra de Juárez Zapotec,3,1511,1620,521,2.9001919385796544,0.3448047650562541,3.109404990403071,0.3216049382716049,True
+nhx,Melaꞌtájto̱l,Náhuatl del Istmo-Mecayapan,náhuatl del Istmo,Isthmus-Mecayapan Nahuatl,1,503,503,174,2.8908045977011496,0.34592445328031807,2.8908045977011496,0.34592445328031807,True
+mam,"Qyol Mam, Yol Mam",Mam,Mam de la frontera,Mam,4,2015,2083,699,2.882689556509299,0.34689826302729526,2.9799713876967098,0.3355736917906865,True
+xtn,Saꞌan savi,Mixteco de Tlaxiaco del Norte,mixteco del norte bajo,Northern Tlaxiaco Mixtec,4,2015,2174,701,2.8744650499286735,0.34789081885856077,3.101283880171184,0.3224471021159154,True
+mzi,En ningotsie,Mazateco de Ixcatlán,mazateco de la presa bajo,Ixcatlán Mazatec,3,1511,1686,527,2.8671726755218216,0.3487756452680344,3.1992409867172675,0.3125741399762752,True
+miy,Tu̱n savi̱ꞌ Tu̱tyoo̱ꞌ,Mixteco de Ayutla,mixteco de Ayutla,Ayutla Mixtec,4,2015,2417,707,2.85007072135785,0.35086848635235734,3.4186704384724185,0.2925113777410012,True
+quc,"K'iche', Qach'abel",Kiché,K’iche’ (oriental),K’iche’,3,1511,1558,536,2.8190298507462686,0.35473196558570486,2.906716417910448,0.34403080872913994,True
+dih,Kumiai,Kumiai,kumiai,Kumiai,2,1007,1048,359,2.8050139275766015,0.35650446871896724,2.9192200557103063,0.3425572519083969,True
+mau,Én‑ná,Mazateco de Huautla,mazateco del centro,Huautla Mazatec,5,2519,2838,899,2.8020022246941045,0.3568876538308853,3.156840934371524,0.3167723749119098,True
+pmq,Xi'iuy,Pame del Norte,pame del norte,Northern Pame,3,1511,1738,540,2.7981481481481483,0.357379219060225,3.2185185185185183,0.31070195627157654,True
+vmp,En naxijen,Mazateco de Soyaltepec,mazateco del noreste,Soyaltepec Mazatec,3,1511,1661,540,2.7981481481481483,0.357379219060225,3.075925925925926,0.325105358217941,True
+trs,Nânj Nï̀nꞌïn,Triqui de Chicahuaxtla,triqui de la alta,Chicahuaxtla Triqui,5,2519,2774,901,2.7957824639289677,0.35768161969035334,3.078801331853496,0.32480173035328047,True
+ctp,Chaꞌtñan,Chatino de la Zona Alta Occidental,chatino occidental alto,Western Highland Chatino,2,1007,1167,364,2.7664835164835164,0.3614697120158888,3.206043956043956,0.31191088260497,True
+mfy,Yorem Nokpo,Mayo,mayo,Mayo,3,1511,1555,548,2.7572992700729926,0.3626737260092654,2.8375912408759123,0.352411575562701,True
+thh,ralámuli raicha,Tarahumara del Norte,tarahumara del norte,"Tarahumara, Northern",3,1511,1676,548,2.7572992700729926,0.3626737260092654,3.0583941605839415,0.3269689737470167,True
+tla,,Tepehuano del Suroeste,tepehuano del sur alto,"Tepehuan, Southwestern",2,1007,1216,366,2.751366120218579,0.3634558093346574,3.3224043715846996,0.30098684210526316,True
+poi,Nuntajɨ̱yi,Popoluca de la Sierra,popoluca de la Sierra,Highland Popoluca,3,1511,1764,550,2.747272727272727,0.3639973527465255,3.207272727272727,0.31179138321995464,True
+xta,Tu̱'un sâvi,Mixteco de Alcozauca,mixteco de Guerrero del noreste central,Alcozauca Mixtec,2,1007,1075,368,2.7364130434782608,0.365441906653426,2.921195652173913,0.34232558139534885,True
+zos,Otetzame,Zoque de Francisco León,zoque del noroeste,Francisco León Zoque,3,1511,1590,553,2.732368896925859,0.36598279285241564,2.875226039783002,0.34779874213836476,True
+mks,Tu̱hun ndáhví,Mixteco de Silacayoapan,mixteco del oeste alto,Silacayoapan Mixtec,1,503,549,185,2.718918918918919,0.36779324055666,2.9675675675675675,0.33697632058287796,True
+ood,"Oʼodham ha-ñeʼokĭ, Oʼodham ñiok",Pápago-Pima,pápago,Tohono O’odham,3,1511,1539,556,2.7176258992805757,0.3679682329583058,2.7679856115107913,0.3612735542560104,True
+zpr,Diste’,Zapoteco de Santiago Xanica,"zapoteco de la Sierra sur, del sureste bajo",Santiago Xanica Zapotec,3,1511,1589,558,2.707885304659498,0.3692918596955658,2.847670250896057,0.35116425424795467,True
+maq,"Hne naja, Nne nangui ngaxni",Mazateco de Chiquihuitlán,mazateco del sur,Chiquihuitlán Mazatec,2,1007,1099,372,2.706989247311828,0.36941410129096325,2.954301075268817,0.33848953594176523,True
+cac,Koti',Chuj,Chuj,Chuj,3,1445,1614,536,2.6958955223880596,0.37093425605536334,3.0111940298507465,0.33209417596034696,True
+knj,K'anjob'al,Kaanjobal,Q’anjob’al,Akateko,3,1511,1635,565,2.674336283185841,0.3739245532759762,2.893805309734513,0.345565749235474,True
+mmc,Jñatjo,Mazahua de Michoacán,mazahua de occidente,Michoacán Mazahua,2,1007,1069,381,2.643044619422572,0.37835153922542203,2.8057742782152233,0.35640785781103834,True
+klb,Kiliwa,Kiliwa,kiliwa,Kiliwa,1,503,528,191,2.6335078534031413,0.3797216699801193,2.764397905759162,0.36174242424242425,True
+pbs,Xi'oi,Pame Central,pame del centro,Central Pame,3,1511,1671,576,2.623263888888889,0.3812045003309067,2.9010416666666665,0.34470377019748655,True
+var,Warijio,Guarijío,guarijío del norte,Huarijío,3,1511,1648,577,2.6187175043327557,0.3818663136995367,2.856152512998267,0.35012135922330095,True
+zoc,Tzunitzame,Zoque de Copainalá,zoque del centro,Copainalá Zoque,4,2015,2235,773,2.606727037516171,0.38362282878411913,2.891332470892626,0.3458612975391499,True
+chf,Yocot'an,Chontal de Tabasco,chontal de Tabasco central,Tabasco Chontal,4,2015,2165,776,2.5966494845360826,0.38511166253101736,2.7899484536082473,0.3584295612009238,True
+tar,Ralámuli raꞌíchala,Tarahumara Central,tarahumara del centro,Central Tarahumara,3,1511,1585,587,2.574105621805792,0.3884844473858372,2.700170357751278,0.37034700315457414,True
+zoh,Tzunitzame,Zoque de Chimalapa,zoque del oeste,Chimalapa Zoque,4,2015,2225,784,2.57015306122449,0.3890818858560794,2.8380102040816326,0.35235955056179774,True
+otq,Ñhöñhö,Otomí de Querétaro,otomí del noroeste,Querétaro Otomi,3,1511,1834,590,2.5610169491525423,0.39046988749172734,3.1084745762711865,0.321701199563795,True
+otm,Nyuhu,Otomí de la Sierra Oriental,otomí de la Sierra,Eastern Highland Otomi,3,1511,1745,592,2.552364864864865,0.39179351422898745,2.947635135135135,0.33925501432664756,True
+vmy,Enre naxinanda nguifi,Mazateco de Ayautla,mazateco del sureste,Ayautla Mazatec,1,503,556,198,2.54040404040404,0.39363817097415504,2.808080808080808,0.35611510791366907,True
+hch,"Wixárika, Wixárika Niukiyari",Huichol,huichol del norte,Huichol,5,2519,2752,994,2.53420523138833,0.3946010321556173,2.7686116700201207,0.36119186046511625,True
+zor,Otetzame,Zoque de Rayón,zoque del norte bajo,Rayón Zoque,3,1511,1712,600,2.5183333333333335,0.3970880211780278,2.8533333333333335,0.35046728971962615,True
+cco,Jmíiˊ,Chinanteco de Comaltepec,chinanteco de la Sierra,Comaltepec Chinantec,1,503,599,200,2.515,0.3976143141153082,2.995,0.333889816360601,True
+ppi,Paipai,Paipai,paipai,Paipai,3,1511,1554,602,2.509966777408638,0.3984116479152879,2.5813953488372094,0.38738738738738737,True
+jac,"Abxubal, Abꞌxubꞌal Poptiꞌ",Jakalteko,Jakalteko,Jakalteko,3,1511,1689,605,2.497520661157025,0.400397088021178,2.7917355371900827,0.35820011841326227,True
+mto,Ayöök,Mixe de Totontepec,mixe alto del norte,Totontepec Mixe,4,2015,2331,808,2.493811881188119,0.40099255583126553,2.88490099009901,0.34663234663234666,True
+kek,Q'eqchi',Q'eqchi',Q’eqchi’,Q’eqchi’,3,1511,1736,608,2.4851973684210527,0.40238252812706815,2.8552631578947367,0.35023041474654376,True
+mxq,Ayuk,Mixe de Juquila,mixe medio del este,Juquila Mixe,4,2015,2509,814,2.4754299754299756,0.40397022332506205,3.0823095823095823,0.32443204463929853,True
+crn,Naáyeri Nyuuca,Cora de El Nayar,cora meseño,El Nayar Cora,3,1511,1664,612,2.468954248366013,0.40502978160158837,2.718954248366013,0.36778846153846156,True
+cok,Cuéimarusaꞌna,Cora de Santa Teresa,cora tereseño,Santa Teresa Cora,1,503,503,210,2.395238095238095,0.41749502982107356,2.395238095238095,0.41749502982107356,True
+plo,,Popoluca de Oluta,oluteco,"Popoluca, Oluta",1,499,540,210,2.376190476190476,0.42084168336673344,2.5714285714285716,0.3888888888888889,True
+azg,Jnꞌoon,Amuzgo de San Pedro Amuzgos,amuzgo alto del este,San Pedro Amuzgos Amuzgo,1,503,608,214,2.350467289719626,0.4254473161033797,2.8411214953271027,0.3519736842105263,True
+stp,Oꞌdam,Tepehuano del Sureste,tepehuano del sur bajo,Southeastern Tepehuan,3,1511,1570,656,2.3033536585365852,0.43414956982131037,2.393292682926829,0.4178343949044586,True
+mxp,Ayuujk,Mixe de Tlahuitoltepec,mixe alto del centro,Tlahuitoltepec Mixe,2,1007,1141,448,2.247767857142857,0.4448857994041708,2.546875,0.39263803680981596,True
+chj,"Jmiih kia’ dzä ‘vï ï, Jujmi",Chinanteco de Ojitlán,chinanteco del norte,Ojitlán Chinantec,3,1511,1740,676,2.235207100591716,0.44738583719391134,2.57396449704142,0.38850574712643676,True
+tpx,Meꞌpa̱a̱ Wíꞌi̱i̱n,Tlapaneco de Acatepec,tlapaneco del suroeste,Acatepec Me’phaa,3,1511,1695,690,2.189855072463768,0.456651224354732,2.4565217391304346,0.40707964601769914,True
+mxv,"Tuꞌun Savi de Metlatónoc y Cochoapa el Grande, Tuꞌun savi",Mixteco de Metlatónoc,mixteco de Guerrero del este medio,Metlatónoc Mixtec,1,503,568,232,2.168103448275862,0.46123260437375746,2.4482758620689653,0.4084507042253521,True
+toc,Tutunakú,Totonaco de Coyutla,totonaco central del norte,Coyutla Totonac,1,503,505,233,2.1587982832618025,0.46322067594433397,2.167381974248927,0.4613861386138614,True
+cuc,Jau² jm⁴³,Chinanteco de Usila,chinanteco del oeste central alto,Usila Chinantec,4,2015,2521,942,2.1390658174097665,0.4674937965260546,2.6762208067940554,0.37366124553748514,True
+tpl,Meꞌpa̱a̱ Wíꞌi̱i̱n,Tlapaneco de Tacoapa,tlapaneco del centro,Tlacoapa Me’phaa,3,1511,1948,709,2.1311706629055007,0.4692256783587028,2.7475317348378,0.3639630390143737,True
+tcf,Mè'phàà Mañuwìín,Tlapaneco a de Malinaltepec,tlapaneco central bajo,Malinaltepec Me’phaa,2,1007,1248,485,2.0762886597938146,0.4816285998013903,2.57319587628866,0.3886217948717949,True