tokenizer_256K / evaluation /language_fertility.csv
ljcamargo's picture
Upload evaluation/language_fertility.csv with huggingface_hub
f568504 verified
Raw
History Blame Contribute Delete
18.5 kB
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,2,1007,1019,188,5.3563829787234045,0.18669314796425024,5.420212765957447,0.1844946025515211,True
trc,Xnaꞌánj nu̱ꞌ,Triqui de Copala,triqui de San Juan Copala,Copala Triqui,3,1511,1791,296,5.10472972972973,0.19589675711449372,6.050675675675675,0.1652707984366276,True
sei,Cmiique Iitom,Seri,seri,Seri,3,1511,1531,297,5.087542087542087,0.19655857048312375,5.154882154882155,0.19399085564990204,True
tzo,Bats'i k'op,Tsotsil,tsotsil del centro,Tsotsil,4,2015,2199,414,4.867149758454106,0.2054590570719603,5.311594202898551,0.1882673942701228,True
yua,Maaya t'aan,Maya de Yucatán,maya,Yucatec Maya,5,2519,2945,563,4.474245115452931,0.22350138944025408,5.230905861456483,0.19117147707979626,True
nhw,Nahuatl,Náhuatl Huasteco Occidental,náhuatl de la Huasteca potosina,Western Huasteca Nahuatl,4,2015,2015,455,4.428571428571429,0.22580645161290322,4.428571428571429,0.22580645161290322,True
top,"Lichiwin Tutunaku, Tutunakú",Totonaco de Papantla,totonaco de la costa,Papantla Totonac,5,2519,2582,573,4.396160558464223,0.2274712187375943,4.506108202443281,0.22192099147947328,True
nhe,Mexkatl,Náhuatl Huasteco Oriental,náhuatl de la Huasteca veracruzana,Eastern Huasteca Nahuatl,4,2015,2083,459,4.389978213507625,0.22779156327543423,4.538126361655773,0.22035525684109458,True
mio,Tuhun Ñuun Ñucaan,Mixteco de Pinotepa Nacional,mixteco del oeste de la costa,Pinotepa Nacional Mixtec,4,2015,2186,464,4.342672413793103,0.23027295285359803,4.711206896551724,0.21225983531564502,True
tzh,Bats'il k'op,Tzeltal,tseltal del occidente,Tzeltal,2,1007,1102,234,4.303418803418803,0.2323733862959285,4.7094017094017095,0.21234119782214156,True
amu,"Ñomndaa, Ñomndaa Suljaaꞌ",Amuzgo de Guerrero,amuzgo del norte,Guerrero Amuzgo,4,2015,2521,469,4.29637526652452,0.2327543424317618,5.3752665245202556,0.18603728679095596,True
mhc,Mocho',Motozintleco,mocho’,Mocho,4,2015,2021,469,4.29637526652452,0.2327543424317618,4.309168443496802,0.23206333498268183,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,4,2015,2234,487,4.137577002053388,0.24168734491315136,4.587268993839836,0.2179946284691137,True
tpp,Lhichiwin,Tepehua de Pisaflores,tepehua del norte,Pisaflores Tepehua,4,2015,2099,489,4.120654396728017,0.24267990074441687,4.292433537832311,0.2329680800381134,True
ctu,"Ch'ol, Lakty’añ",Ch'ol,ch’ol del noroeste,Chol,3,1511,1753,367,4.11716621253406,0.242885506287227,4.776566757493188,0.20935539075869938,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
huv,Ombeayiüts,Huave de San Mateo del Mar,huave del oeste,San Mateo del Mar Huave,3,1511,1600,373,4.050938337801608,0.2468563864990073,4.289544235924933,0.233125,True
mat,bot’una,Matlatzinca de San Francisco,matlatzinca,"Matlatzinca, San Francisco",3,1511,1619,374,4.040106951871658,0.24751819986763732,4.328877005347594,0.23100679431747992,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,4,2015,2052,520,3.875,0.25806451612903225,3.9461538461538463,0.253411306042885,True
hus,Teenek,Huasteco,huasteco del occidente,Huastec,3,1450,1585,378,3.835978835978836,0.26068965517241377,4.193121693121693,0.2384858044164038,True
yaq,Yo'em noki,Yaqui,yaqui,Yaqui,4,2015,2110,528,3.816287878787879,0.2620347394540943,3.996212121212121,0.2502369668246445,True
ocu,pjiekak'joo,Tlahuica,tlahuica,Tlahuica,3,1511,1644,396,3.8156565656565657,0.26207809397749837,4.151515151515151,0.24087591240875914,True
toj,Tojol-ab'al,Tojolabal,tojolabal,Tojolabal,4,2015,2196,529,3.8090737240075616,0.26253101736972706,4.151228733459357,0.24089253187613843,True
maj,"Kinꞌekꞌatiya, Ntaxjo̱",Mazateco de Jalapa de Díaz,mazateco del este bajo,Jalapa de Díaz Mazatec,1,503,507,133,3.781954887218045,0.2644135188866799,3.81203007518797,0.26232741617357,True
lac,Jach-t'aan,Lacandón,lacandón,Lacandon,5,2519,2820,670,3.7597014925373133,0.26597856292179434,4.208955223880597,0.2375886524822695,True
mie,Tūhun sāsávī,Mixteco de Ocotepec,mixteco de Sierra sur noroeste,Ocotepec Mixtec,4,2015,2238,537,3.7523277467411544,0.2665012406947891,4.167597765363128,0.23994638069705093,True
meh,Tu̱ꞌun káꞌánꞌ kájí,Mixteco del Suroeste de Tlaxiaco,mixteco del suroeste,Southwestern Tlaxiaco Mixtec,3,1511,1552,404,3.74009900990099,0.2673726009265387,3.8415841584158414,0.2603092783505155,True
cux,Cuicateco yeⁿꞌe Tepeuxila,Cuicateco de Tepeuxila,cuicateco del centro,Tepeuxila Cuicatec,3,1511,1828,405,3.730864197530864,0.2680344142951688,4.51358024691358,0.2215536105032823,True
nhy,Nāhuatlahtōlli,Náhuatl del Norte de Oaxaca,náhuatl de Oaxaca,Northern Oaxaca Nahuatl,5,2519,2587,679,3.7098674521354935,0.2695514092894006,3.8100147275405005,0.26246617703904135,True
tsz,"P’urhe, P’urhépecha",Purépecha,purépecha,Purepecha,3,1511,1590,411,3.67639902676399,0.27200529450694905,3.8686131386861313,0.25849056603773585,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,4,2015,2189,551,3.6569872958257714,0.27344913151364764,3.972776769509982,0.2517131110095934,True
ntp,Oodamicʌdʌ,Tepehuano del Norte,tepehuano del norte,Northern Tepehuan,3,1511,1638,418,3.6148325358851676,0.27663798808735934,3.9186602870813396,0.25518925518925517,True
nhx,Melaꞌtájto̱l,Náhuatl del Istmo-Mecayapan,náhuatl del Istmo,Isthmus-Mecayapan Nahuatl,1,503,503,140,3.592857142857143,0.2783300198807157,3.592857142857143,0.2783300198807157,True
zoq,,Zoque de Tabasco,zoque del este,"Zoque, Tabasco",3,1511,1605,422,3.580568720379147,0.27928524156187956,3.8033175355450237,0.26292834890965733,True
pei,,Chichimeco Jonaz,chichimeco jonaz,Chichimeco-Jonaz,3,1511,1725,424,3.563679245283019,0.28060886829913967,4.068396226415095,0.24579710144927536,True
tos,Totonaco,Totonaco de la Sierra,totonaco central del sur,Highland Totonac,4,2015,2088,574,3.510452961672474,0.284863523573201,3.637630662020906,0.27490421455938696,True
azn,Meshikan de San Agustin Buenaventura y de Santa Cruz,Náhuatl de Durango Occidental,mexicano del noroeste,Western Durango Nahuatl,4,2007,2026,577,3.4783362218370883,0.28749377179870456,3.511265164644714,0.28479763079960513,True
poi,Nuntajɨ̱yi,Popoluca de la Sierra,popoluca de la Sierra,Highland Popoluca,3,1511,1764,438,3.449771689497717,0.2898742554599603,4.027397260273973,0.24829931972789115,True
ngu,Nauatlajtojli,Náhuatl de Guerrero,mexicano de Guerrero,Guerrero Nahuatl,4,2015,2020,587,3.4327086882453153,0.2913151364764268,3.4412265758091993,0.2905940594059406,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
mix,"Sa'an Savi Snuviko, Sa'an savi",Mixteco de Mixtepec,mixteco de Ñumi,Mixtepec Mixtec,3,1511,1669,442,3.418552036199095,0.2925215089344805,3.776018099547511,0.2648292390653086,True
tla,,Tepehuano del Suroeste,tepehuano del sur alto,"Tepehuan, Southwestern",2,1007,1216,295,3.4135593220338984,0.2929493545183714,4.122033898305085,0.24259868421052633,True
zaq,Tisa,Zapoteco de Aloápam,zapoteco de San Miguel Aloápam,Aloápam Zapotec,3,1511,1675,444,3.4031531531531534,0.2938451356717406,3.7725225225225225,0.2650746268656716,True
mxt,Sa'an Xiñi Savi,Mixteco de Jamiltepec,mixteco de Oaxaca de costa central baja,Jamiltepec Mixtec,3,1511,1672,445,3.3955056179775283,0.2945069490403706,3.757303370786517,0.2661483253588517,True
nsu,"Nahuatl, Nahuatlajtoli",Náhuatl de la Sierra Negra,"náhuatl de la Sierra negra, sur",Sierra Negra Nahuatl,3,1511,1548,445,3.3955056179775283,0.2945069490403706,3.4786516853932583,0.2874677002583979,True
mam,"Qyol Mam, Yol Mam",Mam,Mam de la frontera,Mam,4,2015,2083,600,3.3583333333333334,0.2977667493796526,3.4716666666666667,0.28804608737397985,True
nch,Nāhuatlahtōlli,Náhuatl Huasteco Central,mexicano de la Huasteca Hidalguense,Central Huasteca Nahuatl,3,1511,1511,450,3.3577777777777778,0.29781601588352086,3.3577777777777778,0.29781601588352086,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,5,2519,2838,763,3.3014416775884667,0.30289797538705837,3.7195281782437744,0.26885130373502464,True
mzi,En ningotsie,Mazateco de Ixcatlán,mazateco de la presa bajo,Ixcatlán Mazatec,3,1511,1686,459,3.291938997821351,0.30377233620119126,3.673202614379085,0.2722419928825623,True
dih,Kumiai,Kumiai,kumiai,Kumiai,2,1007,1048,306,3.2908496732026142,0.3038728897715988,3.4248366013071894,0.2919847328244275,True
miy,Tu̱n savi̱ꞌ Tu̱tyoo̱ꞌ,Mixteco de Ayutla,mixteco de Ayutla,Ayutla Mixtec,4,2015,2417,614,3.281758957654723,0.3047146401985112,3.936482084690554,0.2540339263549855,True
xta,Tu̱'un sâvi,Mixteco de Alcozauca,mixteco de Guerrero del noreste central,Alcozauca Mixtec,2,1007,1075,307,3.2801302931596092,0.30486593843098314,3.501628664495114,0.2855813953488372,True
zaa,Titsaꞌ,Zapoteco de la Sierra de Juárez,"zapoteco serrano, bajo",Sierra de Juárez Zapotec,3,1511,1620,463,3.263498920086393,0.3064195896757114,3.4989200863930887,0.2858024691358025,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
pls,Ngigua,Popoloca de San Marcos Tlacoyalco,popoloca del norte,San Marcos Tlacoyalco Popoloca,1,503,513,155,3.2451612903225806,0.3081510934393638,3.3096774193548386,0.30214424951267055,True
mfy,Yorem Nokpo,Mayo,mayo,Mayo,3,1511,1555,467,3.235546038543897,0.30906684315023164,3.329764453961456,0.30032154340836015,True
quc,"K'iche', Qach'abel",Kiché,K’iche’ (oriental),K’iche’,3,1511,1558,467,3.235546038543897,0.30906684315023164,3.336188436830835,0.29974326059050066,True
thh,ralámuli raicha,Tarahumara del Norte,tarahumara del norte,"Tarahumara, Northern",3,1511,1676,469,3.2217484008528783,0.31039046988749175,3.5735607675906182,0.2798329355608592,True
coz,,Chocholteco,chocholteco del oeste,Chocholtec,3,1511,1591,471,3.208067940552017,0.3117140966247518,3.3779193205944797,0.2960402262727844,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
cac,Koti',Chuj,Chuj,Chuj,3,1445,1614,456,3.168859649122807,0.31557093425605537,3.539473684210526,0.2825278810408922,True
knj,K'anjob'al,Kaanjobal,Q’anjob’al,Akateko,3,1511,1635,477,3.1677148846960166,0.31568497683653207,3.4276729559748427,0.29174311926605506,True
vmp,En naxijen,Mazateco de Soyaltepec,mazateco del noreste,Soyaltepec Mazatec,3,1511,1661,483,3.1283643892339543,0.3196558570483124,3.4389233954451344,0.29078868151715836,True
pbs,Xi'oi,Pame Central,pame del centro,Central Pame,3,1511,1671,488,3.096311475409836,0.3229649238914626,3.4241803278688523,0.29204069419509276,True
ood,"Oʼodham ha-ñeʼokĭ, Oʼodham ñiok",Pápago-Pima,pápago,Tohono O’odham,3,1511,1539,491,3.0773930753564156,0.3249503639973527,3.134419551934827,0.3190383365821962,True
zoh,Tzunitzame,Zoque de Chimalapa,zoque del oeste,Chimalapa Zoque,4,2015,2225,655,3.0763358778625953,0.3250620347394541,3.3969465648854964,0.2943820224719101,True
chf,Yocot'an,Chontal de Tabasco,chontal de Tabasco central,Tabasco Chontal,4,2015,2165,659,3.0576631259484066,0.3270471464019851,3.285280728376328,0.3043879907621247,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
ctp,Chaꞌtñan,Chatino de la Zona Alta Occidental,chatino occidental alto,Western Highland Chatino,2,1007,1167,330,3.0515151515151517,0.32770605759682225,3.536363636363636,0.2827763496143959,True
zoc,Tzunitzame,Zoque de Copainalá,zoque del centro,Copainalá Zoque,4,2015,2235,662,3.0438066465256797,0.32853598014888336,3.376132930513595,0.29619686800894857,True
maq,"Hne naja, Nne nangui ngaxni",Mazateco de Chiquihuitlán,mazateco del sur,Chiquihuitlán Mazatec,2,1007,1099,332,3.033132530120482,0.32969215491559084,3.3102409638554215,0.3020928116469518,True
var,Warijio,Guarijío,guarijío del norte,Huarijío,3,1511,1648,501,3.0159680638722555,0.3315684976836532,3.2894211576846306,0.30400485436893204,True
zpr,Diste’,Zapoteco de Santiago Xanica,"zapoteco de la Sierra sur, del sureste bajo",Santiago Xanica Zapotec,3,1511,1589,504,2.998015873015873,0.33355393778954334,3.1527777777777777,0.31718061674008813,True
klb,Kiliwa,Kiliwa,kiliwa,Kiliwa,1,503,528,168,2.994047619047619,0.33399602385685884,3.142857142857143,0.3181818181818182,True
mxq,Ayuk,Mixe de Juquila,mixe medio del este,Juquila Mixe,4,2015,2509,674,2.9896142433234423,0.33449131513647645,3.722551928783383,0.26863292148266243,True
hch,"Wixárika, Wixárika Niukiyari",Huichol,huichol del norte,Huichol,5,2519,2752,843,2.9881376037959666,0.33465660976578004,3.264531435349941,0.30632267441860467,True
mmc,Jñatjo,Mazahua de Michoacán,mazahua de occidente,Michoacán Mazahua,2,1007,1069,338,2.9792899408284024,0.3356504468718967,3.162721893491124,0.3161833489242282,True
mks,Tu̱hun ndáhví,Mixteco de Silacayoapan,mixteco del oeste alto,Silacayoapan Mixtec,1,503,549,169,2.9763313609467454,0.3359840954274354,3.2485207100591715,0.30783242258652094,True
tar,Ralámuli raꞌíchala,Tarahumara Central,tarahumara del centro,Central Tarahumara,3,1511,1585,508,2.9744094488188977,0.33620119126406356,3.12007874015748,0.3205047318611987,True
kek,Q'eqchi',Q'eqchi',Q’eqchi’,Q’eqchi’,3,1511,1736,517,2.9226305609284333,0.34215751158173396,3.357833655705996,0.2978110599078341,True
otm,Nyuhu,Otomí de la Sierra Oriental,otomí de la Sierra,Eastern Highland Otomi,3,1511,1745,519,2.9113680154142583,0.343481138318994,3.3622350674373798,0.2974212034383954,True
cok,Cuéimarusaꞌna,Cora de Santa Teresa,cora tereseño,Santa Teresa Cora,1,503,503,173,2.907514450867052,0.34393638170974156,2.907514450867052,0.34393638170974156,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,3,1511,1689,522,2.8946360153256707,0.3454665784248842,3.235632183908046,0.30905861456483125,True
otq,Ñhöñhö,Otomí de Querétaro,otomí del noroeste,Querétaro Otomi,3,1511,1834,522,2.8946360153256707,0.3454665784248842,3.5134099616858236,0.2846237731733915,True
zor,Otetzame,Zoque de Rayón,zoque del norte bajo,Rayón Zoque,3,1511,1712,524,2.883587786259542,0.34679020516214426,3.267175572519084,0.3060747663551402,True
ppi,Paipai,Paipai,paipai,Paipai,3,1511,1554,528,2.8617424242424243,0.3494374586366645,2.9431818181818183,0.33976833976833976,True
plo,,Popoluca de Oluta,oluteco,"Popoluca, Oluta",1,499,540,176,2.835227272727273,0.3527054108216433,3.0681818181818183,0.32592592592592595,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,1,503,599,184,2.733695652173913,0.3658051689860835,3.255434782608696,0.3071786310517529,True
crn,Naáyeri Nyuuca,Cora de El Nayar,cora meseño,El Nayar Cora,3,1511,1664,564,2.6790780141843973,0.37326273990734615,2.950354609929078,0.3389423076923077,True
azg,Jnꞌoon,Amuzgo de San Pedro Amuzgos,amuzgo alto del este,San Pedro Amuzgos Amuzgo,1,503,608,189,2.6613756613756614,0.3757455268389662,3.2169312169312168,0.31085526315789475,True
stp,Oꞌdam,Tepehuano del Sureste,tepehuano del sur bajo,Southeastern Tepehuan,3,1511,1570,579,2.609671848013817,0.3831899404367968,2.7115716753022454,0.3687898089171974,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
tpx,Meꞌpa̱a̱ Wíꞌi̱i̱n,Tlapaneco de Acatepec,tlapaneco del suroeste,Acatepec Me’phaa,3,1511,1695,591,2.55668358714044,0.39113170086035737,2.8680203045685277,0.3486725663716814,True
mxp,Ayuujk,Mixe de Tlahuitoltepec,mixe alto del centro,Tlahuitoltepec Mixe,2,1007,1141,402,2.5049751243781095,0.39920556107249255,2.8383084577114426,0.3523225241016652,True
toc,Tutunakú,Totonaco de Coyutla,totonaco central del norte,Coyutla Totonac,1,503,505,207,2.429951690821256,0.4115308151093439,2.4396135265700485,0.4099009900990099,True
cuc,Jau² jm⁴³,Chinanteco de Usila,chinanteco del oeste central alto,Usila Chinantec,4,2015,2521,831,2.424789410348977,0.41240694789081883,3.033694344163658,0.32963109877032926,True
tpl,Meꞌpa̱a̱ Wíꞌi̱i̱n,Tlapaneco de Tacoapa,tlapaneco del centro,Tlacoapa Me’phaa,3,1511,1948,629,2.4022257551669317,0.41628060886829915,3.09697933227345,0.3228952772073922,True
mxv,"Tuꞌun Savi de Metlatónoc y Cochoapa el Grande, Tuꞌun savi",Mixteco de Metlatónoc,mixteco de Guerrero del este medio,Metlatónoc Mixtec,1,503,568,210,2.395238095238095,0.41749502982107356,2.704761904761905,0.36971830985915494,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