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,2,1007,1019,190,5.3,0.18867924528301888,5.363157894736842,0.18645731108930325,True
+sei,Cmiique Iitom,Seri,seri,Seri,3,1511,1531,298,5.070469798657718,0.1972203838517538,5.1375838926174495,0.1946440235140431,True
+trc,Xnaꞌánj nu̱ꞌ,Triqui de Copala,triqui de San Juan Copala,Copala Triqui,3,1511,1791,305,4.954098360655737,0.20185307743216413,5.872131147540983,0.1702959240647683,True
+tzo,Bats'i k'op,Tsotsil,tsotsil del centro,Tsotsil,4,2015,2199,413,4.878934624697337,0.20496277915632755,5.324455205811138,0.18781264211005003,True
+yua,Maaya t'aan,Maya de Yucatán,maya,Yucatec Maya,5,2519,2945,565,4.458407079646018,0.2242953552997221,5.212389380530974,0.19185059422750425,True
+top,"Lichiwin Tutunaku, Tutunakú",Totonaco de Papantla,totonaco de la costa,Papantla Totonac,5,2519,2582,574,4.388501742160279,0.2278682016673283,4.498257839721254,0.22230828814872192,True
+nhw,Nahuatl,Náhuatl Huasteco Occidental,náhuatl de la Huasteca potosina,Western Huasteca Nahuatl,4,2015,2015,460,4.380434782608695,0.228287841191067,4.380434782608695,0.228287841191067,True
+mio,Tuhun Ñuun Ñucaan,Mixteco de Pinotepa Nacional,mixteco del oeste de la costa,Pinotepa Nacional Mixtec,4,2015,2186,462,4.361471861471862,0.2292803970223325,4.731601731601732,0.21134492223238793,True
+nhe,Mexkatl,Náhuatl Huasteco Oriental,náhuatl de la Huasteca veracruzana,Eastern Huasteca Nahuatl,4,2015,2083,462,4.361471861471862,0.2292803970223325,4.508658008658009,0.22179548727796447,True
+amu,"Ñomndaa, Ñomndaa Suljaaꞌ",Amuzgo de Guerrero,amuzgo del norte,Guerrero Amuzgo,4,2015,2521,468,4.305555555555555,0.23225806451612904,5.386752136752137,0.18564061880206267,True
+mhc,Mocho',Motozintleco,mocho’,Mocho,4,2015,2021,470,4.287234042553192,0.23325062034739455,4.3,0.23255813953488372,True
+tzh,Bats'il k'op,Tzeltal,tseltal del occidente,Tzeltal,2,1007,1102,236,4.266949152542373,0.23435948361469713,4.669491525423729,0.21415607985480944,True
+nhm,"Ika mejikano, Ika nauatl",Náhuatl de Morelos,mexicano central bajo,Morelos Nahuatl,3,1511,1511,360,4.197222222222222,0.23825281270681667,4.197222222222222,0.23825281270681667,True
+zai,Diidxazá,Zapoteco del Istmo,zapoteco de la planicie costera,Isthmus Zapotec,4,2015,2234,482,4.180497925311204,0.2392059553349876,4.634854771784233,0.21575649059982094,True
+ctu,"Ch'ol, Lakty’añ",Ch'ol,ch’ol del noroeste,Chol,3,1511,1753,365,4.13972602739726,0.2415618795499669,4.802739726027397,0.20821448944666288,True
+ncx,,Náhuatl de Puebla Central,náhuatl del centro de Puebla,"Nahuatl, Central Puebla",5,2519,2554,615,4.095934959349593,0.2441445017864232,4.152845528455285,0.2407987470634299,True
+mat,bot’una,Matlatzinca de San Francisco,matlatzinca,"Matlatzinca, San Francisco",3,1511,1619,373,4.050938337801608,0.2468563864990073,4.340482573726542,0.23038912909203213,True
+tpp,Lhichiwin,Tepehua de Pisaflores,tepehua del norte,Pisaflores Tepehua,4,2015,2099,498,4.046184738955823,0.24714640198511167,4.214859437751004,0.2372558361124345,True
+huv,Ombeayiüts,Huave de San Mateo del Mar,huave del oeste,San Mateo del Mar Huave,3,1511,1600,376,4.0186170212765955,0.24884182660489743,4.25531914893617,0.235,True
+maz,Jñatjo,Mazahua Central,mazahua de oriente,Central Mazahua,3,1511,1702,380,3.9763157894736842,0.2514890800794176,4.478947368421053,0.22326674500587543,True
+tee,Lhima'alh'ama',Tepehua de Huehuetla,tepehua del sur,Huehuetla Tepehua,4,2015,2052,522,3.8601532567049808,0.25905707196029776,3.9310344827586206,0.2543859649122807,True
+hus,Teenek,Huasteco,huasteco del occidente,Huastec,3,1450,1585,378,3.835978835978836,0.26068965517241377,4.193121693121693,0.2384858044164038,True
+toj,Tojol-ab'al,Tojolabal,tojolabal,Tojolabal,4,2015,2196,529,3.8090737240075616,0.26253101736972706,4.151228733459357,0.24089253187613843,True
+ocu,pjiekak'joo,Tlahuica,tlahuica,Tlahuica,3,1511,1644,398,3.7964824120603016,0.2634017207147584,4.130653266331659,0.24209245742092458,True
+meh,Tu̱ꞌun káꞌánꞌ kájí,Mixteco del Suroeste de Tlaxiaco,mixteco del suroeste,Southwestern Tlaxiaco Mixtec,3,1511,1552,400,3.7775,0.26472534745201853,3.88,0.25773195876288657,True
+yaq,Yo'em noki,Yaqui,yaqui,Yaqui,4,2015,2110,535,3.7663551401869158,0.2655086848635236,3.94392523364486,0.25355450236966826,True
+maj,"Kinꞌekꞌatiya, Ntaxjo̱",Mazateco de Jalapa de Díaz,mazateco del este bajo,Jalapa de Díaz Mazatec,1,503,507,134,3.753731343283582,0.2664015904572565,3.783582089552239,0.26429980276134124,True
+lac,Jach-t'aan,Lacandón,lacandón,Lacandon,5,2519,2820,673,3.7429420505200595,0.26716951171099645,4.190193164933135,0.23865248226950356,True
+mie,Tūhun sāsávī,Mixteco de Ocotepec,mixteco de Sierra sur noroeste,Ocotepec Mixtec,4,2015,2238,540,3.7314814814814814,0.2679900744416873,4.144444444444445,0.24128686327077747,True
+cux,Cuicateco yeⁿꞌe Tepeuxila,Cuicateco de Tepeuxila,cuicateco del centro,Tepeuxila Cuicatec,3,1511,1828,407,3.7125307125307123,0.26935804103242883,4.4914004914004915,0.22264770240700218,True
+nhy,Nāhuatlahtōlli,Náhuatl del Norte de Oaxaca,náhuatl de Oaxaca,Northern Oaxaca Nahuatl,5,2519,2587,683,3.6881405563689604,0.27113934100833664,3.787701317715959,0.26401236954000773,True
+tsz,"P’urhe, P’urhépecha",Purépecha,purépecha,Purepecha,3,1511,1590,413,3.6585956416464893,0.27332892124420916,3.8498789346246975,0.259748427672956,True
+ncj,Mexicatl,Náhuatl del Norte de Puebla,náhuatl alto del norte de Puebla,Northern Puebla Nahuatl,4,2015,2035,551,3.6569872958257714,0.27344913151364764,3.6932849364791287,0.27076167076167074,True
+pia,Oob No'ok,Pima Bajo,pima del sur,Pima Bajo,4,2015,2189,554,3.637184115523466,0.2749379652605459,3.9512635379061374,0.25308359981726813,True
+ntp,Oodamicʌdʌ,Tepehuano del Norte,tepehuano del norte,Northern Tepehuan,3,1511,1638,417,3.6235011990407675,0.2759761747187293,3.9280575539568345,0.25457875457875456,True
+nhx,Melaꞌtájto̱l,Náhuatl del Istmo-Mecayapan,náhuatl del Istmo,Isthmus-Mecayapan Nahuatl,1,503,503,139,3.618705035971223,0.27634194831013914,3.618705035971223,0.27634194831013914,True
+pei,,Chichimeco Jonaz,chichimeco jonaz,Chichimeco-Jonaz,3,1511,1725,423,3.5721040189125297,0.2799470549305096,4.078014184397163,0.24521739130434783,True
+zoq,,Zoque de Tabasco,zoque del este,"Zoque, Tabasco",3,1511,1605,423,3.5721040189125297,0.2799470549305096,3.7943262411347516,0.2635514018691589,True
+azn,Meshikan de San Agustin Buenaventura y de Santa Cruz,Náhuatl de Durango Occidental,mexicano del noroeste,Western Durango Nahuatl,4,2007,2026,576,3.484375,0.28699551569506726,3.517361111111111,0.2843040473840079,True
+poi,Nuntajɨ̱yi,Popoluca de la Sierra,popoluca de la Sierra,Highland Popoluca,3,1511,1764,435,3.4735632183908045,0.2878888153540701,4.055172413793104,0.2465986394557823,True
+tos,Totonaco,Totonaco de la Sierra,totonaco central del sur,Highland Totonac,4,2015,2088,588,3.42687074829932,0.29181141439205954,3.5510204081632653,0.28160919540229884,True
+mza,Tu'un va'a,Mixteco de Santa María Zacatepec,mixteco de Sierra sur oeste,Santa María Zacatepec Mixtec,3,1511,1780,441,3.4263038548752833,0.29185969556585045,4.036281179138322,0.24775280898876403,True
+tla,,Tepehuano del Suroeste,tepehuano del sur alto,"Tepehuan, Southwestern",2,1007,1216,294,3.425170068027211,0.2919563058589871,4.136054421768708,0.24177631578947367,True
+ngu,Nauatlajtojli,Náhuatl de Guerrero,mexicano de Guerrero,Guerrero Nahuatl,4,2015,2020,590,3.4152542372881354,0.29280397022332505,3.4237288135593222,0.29207920792079206,True
+mix,"Sa'an Savi Snuviko, Sa'an savi",Mixteco de Mixtepec,mixteco de Ñumi,Mixtepec Mixtec,3,1511,1669,444,3.4031531531531534,0.2938451356717406,3.759009009009009,0.2660275614140204,True
+nsu,"Nahuatl, Nahuatlajtoli",Náhuatl de la Sierra Negra,"náhuatl de la Sierra negra, sur",Sierra Negra Nahuatl,3,1511,1548,444,3.4031531531531534,0.2938451356717406,3.4864864864864864,0.2868217054263566,True
+mxt,Sa'an Xiñi Savi,Mixteco de Jamiltepec,mixteco de Oaxaca de costa central baja,Jamiltepec Mixtec,3,1511,1672,446,3.3878923766816142,0.29516876240900064,3.7488789237668163,0.26674641148325356,True
+zaq,Tisa,Zapoteco de Aloápam,zapoteco de San Miguel Aloápam,Aloápam Zapotec,3,1511,1675,446,3.3878923766816142,0.29516876240900064,3.7556053811659194,0.2662686567164179,True
+nch,Nāhuatlahtōlli,Náhuatl Huasteco Central,mexicano de la Huasteca Hidalguense,Central Huasteca Nahuatl,3,1511,1511,451,3.350332594235033,0.2984778292521509,3.350332594235033,0.2984778292521509,True
+mam,"Qyol Mam, Yol Mam",Mam,Mam de la frontera,Mam,4,2015,2083,602,3.3471760797342194,0.2987593052109181,3.4601328903654487,0.28900624099855976,True
+tqt,Xinulajgsípij Totonaco,Totonaco del Cerro Xinolatépetl,totonaco del cerro Xinolatépetl,Totonaco del cerro Xinolatépetl,4,2015,2057,606,3.325082508250825,0.3007444168734491,3.3943894389438944,0.29460379192999514,True
+mau,Én‑ná,Mazateco de Huautla,mazateco del centro,Huautla Mazatec,5,2519,2838,761,3.3101182654402104,0.3021040095275903,3.729303547963206,0.2681465821000705,True
+dih,Kumiai,Kumiai,kumiai,Kumiai,2,1007,1048,305,3.301639344262295,0.3028798411122145,3.4360655737704917,0.29103053435114506,True
+xta,Tu̱'un sâvi,Mixteco de Alcozauca,mixteco de Guerrero del noreste central,Alcozauca Mixtec,2,1007,1075,306,3.2908496732026142,0.3038728897715988,3.5130718954248366,0.2846511627906977,True
+miy,Tu̱n savi̱ꞌ Tu̱tyoo̱ꞌ,Mixteco de Ayutla,mixteco de Ayutla,Ayutla Mixtec,4,2015,2417,613,3.2871125611745513,0.3042183622828784,3.9429037520391517,0.25362019031857674,True
+mzi,En ningotsie,Mazateco de Ixcatlán,mazateco de la presa bajo,Ixcatlán Mazatec,3,1511,1686,461,3.27765726681128,0.30509596293845137,3.6572668112798263,0.2734282325029656,True
+zaa,Titsaꞌ,Zapoteco de la Sierra de Juárez,"zapoteco serrano, bajo",Sierra de Juárez Zapotec,3,1511,1620,462,3.2705627705627704,0.3057577763070814,3.5064935064935066,0.2851851851851852,True
+pmq,Xi'iuy,Pame del Norte,pame del norte,Northern Pame,3,1511,1738,464,3.2564655172413794,0.3070814030443415,3.7456896551724137,0.2669735327963176,True
+xtn,Saꞌan savi,Mixteco de Tlaxiaco del Norte,mixteco del norte bajo,Northern Tlaxiaco Mixtec,4,2015,2174,619,3.255250403877221,0.30719602977667493,3.5121163166397413,0.2847286108555658,True
+coz,,Chocholteco,chocholteco del oeste,Chocholtec,3,1511,1591,467,3.235546038543897,0.30906684315023164,3.4068522483940042,0.29352608422375864,True
+pls,Ngigua,Popoloca de San Marcos Tlacoyalco,popoloca del norte,San Marcos Tlacoyalco Popoloca,1,503,513,156,3.2243589743589745,0.3101391650099404,3.2884615384615383,0.30409356725146197,True
+mfy,Yorem Nokpo,Mayo,mayo,Mayo,3,1511,1555,470,3.2148936170212767,0.3110522832561218,3.3085106382978724,0.3022508038585209,True
+quc,"K'iche', Qach'abel",Kiché,K’iche’ (oriental),K’iche’,3,1511,1558,470,3.2148936170212767,0.3110522832561218,3.3148936170212764,0.30166880616174585,True
+thh,ralámuli raicha,Tarahumara del Norte,tarahumara del norte,"Tarahumara, Northern",3,1511,1676,473,3.1945031712473573,0.3130377233620119,3.543340380549683,0.2822195704057279,True
+trs,Nânj Nï̀nꞌïn,Triqui de Chicahuaxtla,triqui de la alta,Chicahuaxtla Triqui,5,2519,2774,789,3.1926489226869457,0.3132195315601429,3.5158428390367553,0.28442682047584716,True
+knj,K'anjob'al,Kaanjobal,Q’anjob’al,Akateko,3,1511,1635,476,3.1743697478991595,0.31502316346790205,3.4348739495798317,0.291131498470948,True
+cac,Koti',Chuj,Chuj,Chuj,3,1445,1614,456,3.168859649122807,0.31557093425605537,3.539473684210526,0.2825278810408922,True
+vmp,En naxijen,Mazateco de Soyaltepec,mazateco del noreste,Soyaltepec Mazatec,3,1511,1661,484,3.121900826446281,0.3203176704169424,3.4318181818181817,0.2913907284768212,True
+pbs,Xi'oi,Pame Central,pame del centro,Central Pame,3,1511,1671,488,3.096311475409836,0.3229649238914626,3.4241803278688523,0.29204069419509276,True
+zoh,Tzunitzame,Zoque de Chimalapa,zoque del oeste,Chimalapa Zoque,4,2015,2225,651,3.0952380952380953,0.3230769230769231,3.4178187403993854,0.29258426966292134,True
+ood,"Oʼodham ha-ñeʼokĭ, Oʼodham ñiok",Pápago-Pima,pápago,Tohono O’odham,3,1511,1539,493,3.0649087221095335,0.32627399073461283,3.1217038539553754,0.3203378817413905,True
+chf,Yocot'an,Chontal de Tabasco,chontal de Tabasco central,Tabasco Chontal,4,2015,2165,658,3.0623100303951367,0.32655086848635234,3.290273556231003,0.3039260969976905,True
+zos,Otetzame,Zoque de Francisco León,zoque del noroeste,Francisco León Zoque,3,1511,1590,495,3.0525252525252524,0.32759761747187294,3.212121212121212,0.3113207547169811,True
+maq,"Hne naja, Nne nangui ngaxni",Mazateco de Chiquihuitlán,mazateco del sur,Chiquihuitlán Mazatec,2,1007,1099,330,3.0515151515151517,0.32770605759682225,3.33030303030303,0.3002729754322111,True
+var,Warijio,Guarijío,guarijío del norte,Huarijío,3,1511,1648,498,3.034136546184739,0.32958305757776307,3.3092369477911645,0.30218446601941745,True
+ctp,Chaꞌtñan,Chatino de la Zona Alta Occidental,chatino occidental alto,Western Highland Chatino,2,1007,1167,332,3.033132530120482,0.32969215491559084,3.5150602409638556,0.28449014567266495,True
+zoc,Tzunitzame,Zoque de Copainalá,zoque del centro,Copainalá Zoque,4,2015,2235,666,3.0255255255255253,0.33052109181141437,3.355855855855856,0.2979865771812081,True
+mks,Tu̱hun ndáhví,Mixteco de Silacayoapan,mixteco del oeste alto,Silacayoapan Mixtec,1,503,549,167,3.0119760479041915,0.3320079522862823,3.287425149700599,0.30418943533697634,True
+klb,Kiliwa,Kiliwa,kiliwa,Kiliwa,1,503,528,168,2.994047619047619,0.33399602385685884,3.142857142857143,0.3181818181818182,True
+zpr,Diste’,Zapoteco de Santiago Xanica,"zapoteco de la Sierra sur, del sureste bajo",Santiago Xanica Zapotec,3,1511,1589,505,2.992079207920792,0.33421575115817337,3.1465346534653467,0.31780994336060414,True
+mxq,Ayuk,Mixe de Juquila,mixe medio del este,Juquila Mixe,4,2015,2509,675,2.9851851851851854,0.3349875930521092,3.717037037037037,0.269031486648067,True
+hch,"Wixárika, Wixárika Niukiyari",Huichol,huichol del norte,Huichol,5,2519,2752,844,2.984597156398104,0.3350535926955141,3.2606635071090047,0.3066860465116279,True
+mmc,Jñatjo,Mazahua de Michoacán,mazahua de occidente,Michoacán Mazahua,2,1007,1069,338,2.9792899408284024,0.3356504468718967,3.162721893491124,0.3161833489242282,True
+tar,Ralámuli raꞌíchala,Tarahumara Central,tarahumara del centro,Central Tarahumara,3,1511,1585,511,2.9569471624266144,0.3381866313699537,3.101761252446184,0.322397476340694,True
+cok,Cuéimarusaꞌna,Cora de Santa Teresa,cora tereseño,Santa Teresa Cora,1,503,503,172,2.9244186046511627,0.341948310139165,2.9244186046511627,0.341948310139165,True
+kek,Q'eqchi',Q'eqchi',Q’eqchi’,Q’eqchi’,3,1511,1736,519,2.9113680154142583,0.343481138318994,3.3448940269749516,0.298963133640553,True
+vmy,Enre naxinanda nguifi,Mazateco de Ayautla,mazateco del sureste,Ayautla Mazatec,1,503,556,173,2.907514450867052,0.34393638170974156,3.213872832369942,0.31115107913669066,True
+jac,"Abxubal, Abꞌxubꞌal Poptiꞌ",Jakalteko,Jakalteko,Jakalteko,3,1511,1689,523,2.8891013384321225,0.34612839179351423,3.229445506692161,0.30965068087625813,True
+otm,Nyuhu,Otomí de la Sierra Oriental,otomí de la Sierra,Eastern Highland Otomi,3,1511,1745,523,2.8891013384321225,0.34612839179351423,3.3365200764818357,0.2997134670487106,True
+otq,Ñhöñhö,Otomí de Querétaro,otomí del noroeste,Querétaro Otomi,3,1511,1834,523,2.8891013384321225,0.34612839179351423,3.5066921606118546,0.2851690294438386,True
+zor,Otetzame,Zoque de Rayón,zoque del norte bajo,Rayón Zoque,3,1511,1712,523,2.8891013384321225,0.34612839179351423,3.273422562141491,0.3054906542056075,True
+ppi,Paipai,Paipai,paipai,Paipai,3,1511,1554,530,2.8509433962264152,0.35076108537392453,2.9320754716981132,0.3410553410553411,True
+plo,,Popoluca de Oluta,oluteco,"Popoluca, Oluta",1,499,540,177,2.8192090395480225,0.35470941883767537,3.0508474576271185,0.3277777777777778,True
+mto,Ayöök,Mixe de Totontepec,mixe alto del norte,Totontepec Mixe,4,2015,2331,718,2.8064066852367686,0.3563275434243176,3.246518105849582,0.308022308022308,True
+cco,Jmíiˊ,Chinanteco de Comaltepec,chinanteco de la Sierra,Comaltepec Chinantec,1,503,599,182,2.7637362637362637,0.36182902584493043,3.291208791208791,0.3038397328881469,True
+crn,Naáyeri Nyuuca,Cora de El Nayar,cora meseño,El Nayar Cora,3,1511,1664,565,2.674336283185841,0.3739245532759762,2.945132743362832,0.3395432692307692,True
+azg,Jnꞌoon,Amuzgo de San Pedro Amuzgos,amuzgo alto del este,San Pedro Amuzgos Amuzgo,1,503,608,190,2.6473684210526316,0.37773359840954274,3.2,0.3125,True
+stp,Oꞌdam,Tepehuano del Sureste,tepehuano del sur bajo,Southeastern Tepehuan,3,1511,1570,583,2.5917667238421958,0.385837193911317,2.692967409948542,0.37133757961783437,True
+tpx,Meꞌpa̱a̱ Wíꞌi̱i̱n,Tlapaneco de Acatepec,tlapaneco del suroeste,Acatepec Me’phaa,3,1511,1695,589,2.565365025466893,0.38980807412309726,2.877758913412564,0.34749262536873154,True
+chj,"Jmiih kia’ dzä ‘vï ï, Jujmi",Chinanteco de Ojitlán,chinanteco del norte,Ojitlán Chinantec,3,1511,1740,591,2.55668358714044,0.39113170086035737,2.9441624365482233,0.3396551724137931,True
+mxp,Ayuujk,Mixe de Tlahuitoltepec,mixe alto del centro,Tlahuitoltepec Mixe,2,1007,1141,400,2.5175,0.3972194637537239,2.8525,0.35056967572305,True
+cuc,Jau² jm⁴³,Chinanteco de Usila,chinanteco del oeste central alto,Usila Chinantec,4,2015,2521,830,2.427710843373494,0.4119106699751861,3.0373493975903614,0.32923443078143594,True
+toc,Tutunakú,Totonaco de Coyutla,totonaco central del norte,Coyutla Totonac,1,503,505,209,2.4066985645933014,0.415506958250497,2.416267942583732,0.41386138613861384,True
+tpl,Meꞌpa̱a̱ Wíꞌi̱i̱n,Tlapaneco de Tacoapa,tlapaneco del centro,Tlacoapa Me’phaa,3,1511,1948,628,2.406050955414013,0.41561879549966907,3.1019108280254777,0.32238193018480493,True
+tcf,Mè'phàà Mañuwìín,Tlapaneco a de Malinaltepec,tlapaneco central bajo,Malinaltepec Me’phaa,2,1007,1248,428,2.352803738317757,0.42502482621648463,2.9158878504672896,0.34294871794871795,True
+mxv,"Tuꞌun Savi de Metlatónoc y Cochoapa el Grande, Tuꞌun savi",Mixteco de Metlatónoc,mixteco de Guerrero del este medio,Metlatónoc Mixtec,1,503,568,214,2.350467289719626,0.4254473161033797,2.6542056074766354,0.3767605633802817,True