tokenizer_test5 / evaluation /language_fertility.json
ljcamargo's picture
Upload evaluation/language_fertility.json with huggingface_hub
4613b0a verified
Raw
History Blame Contribute Delete
48.6 kB
[
{
"code": "amu",
"autonym": "Ñomndaa, Ñomndaa Suljaaꞌ",
"spanish_name": "Amuzgo de Guerrero",
"inali_name": "amuzgo del norte",
"english_name": "Guerrero Amuzgo",
"samples": 4,
"chars": 2015,
"utf8_bytes": 2521,
"tokens": 468,
"chars_per_token": 4.305555555555555,
"tokens_per_char": 0.23225806451612904,
"bytes_per_token": 5.386752136752137,
"tokens_per_byte": 0.18564061880206267,
"round_trip": true
},
{
"code": "azg",
"autonym": "Jnꞌoon",
"spanish_name": "Amuzgo de San Pedro Amuzgos",
"inali_name": "amuzgo alto del este",
"english_name": "San Pedro Amuzgos Amuzgo",
"samples": 1,
"chars": 503,
"utf8_bytes": 608,
"tokens": 190,
"chars_per_token": 2.6473684210526316,
"tokens_per_char": 0.37773359840954274,
"bytes_per_token": 3.2,
"tokens_per_byte": 0.3125,
"round_trip": true
},
{
"code": "ctp",
"autonym": "Chaꞌtñan",
"spanish_name": "Chatino de la Zona Alta Occidental",
"inali_name": "chatino occidental alto",
"english_name": "Western Highland Chatino",
"samples": 2,
"chars": 1007,
"utf8_bytes": 1167,
"tokens": 332,
"chars_per_token": 3.033132530120482,
"tokens_per_char": 0.32969215491559084,
"bytes_per_token": 3.5150602409638556,
"tokens_per_byte": 0.28449014567266495,
"round_trip": true
},
{
"code": "cya",
"autonym": "Chaꞌtñan",
"spanish_name": "Chatino de Nopala",
"inali_name": "chatino oriental bajo",
"english_name": "Nopala Chatino",
"samples": 2,
"chars": 1007,
"utf8_bytes": 1019,
"tokens": 190,
"chars_per_token": 5.3,
"tokens_per_char": 0.18867924528301888,
"bytes_per_token": 5.363157894736842,
"tokens_per_byte": 0.18645731108930325,
"round_trip": true
},
{
"code": "pei",
"autonym": "",
"spanish_name": "Chichimeco Jonaz",
"inali_name": "chichimeco jonaz",
"english_name": "Chichimeco-Jonaz",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1725,
"tokens": 423,
"chars_per_token": 3.5721040189125297,
"tokens_per_char": 0.2799470549305096,
"bytes_per_token": 4.078014184397163,
"tokens_per_byte": 0.24521739130434783,
"round_trip": true
},
{
"code": "chj",
"autonym": "Jmiih kia’ dzä ‘vï ï, Jujmi",
"spanish_name": "Chinanteco de Ojitlán",
"inali_name": "chinanteco del norte",
"english_name": "Ojitlán Chinantec",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1740,
"tokens": 591,
"chars_per_token": 2.55668358714044,
"tokens_per_char": 0.39113170086035737,
"bytes_per_token": 2.9441624365482233,
"tokens_per_byte": 0.3396551724137931,
"round_trip": true
},
{
"code": "cuc",
"autonym": "Jau² jm⁴³",
"spanish_name": "Chinanteco de Usila",
"inali_name": "chinanteco del oeste central alto",
"english_name": "Usila Chinantec",
"samples": 4,
"chars": 2015,
"utf8_bytes": 2521,
"tokens": 830,
"chars_per_token": 2.427710843373494,
"tokens_per_char": 0.4119106699751861,
"bytes_per_token": 3.0373493975903614,
"tokens_per_byte": 0.32923443078143594,
"round_trip": true
},
{
"code": "cco",
"autonym": "Jmíiˊ",
"spanish_name": "Chinanteco de Comaltepec",
"inali_name": "chinanteco de la Sierra",
"english_name": "Comaltepec Chinantec",
"samples": 1,
"chars": 503,
"utf8_bytes": 599,
"tokens": 182,
"chars_per_token": 2.7637362637362637,
"tokens_per_char": 0.36182902584493043,
"bytes_per_token": 3.291208791208791,
"tokens_per_byte": 0.3038397328881469,
"round_trip": true
},
{
"code": "coz",
"autonym": "",
"spanish_name": "Chocholteco",
"inali_name": "chocholteco del oeste",
"english_name": "Chocholtec",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1591,
"tokens": 467,
"chars_per_token": 3.235546038543897,
"tokens_per_char": 0.30906684315023164,
"bytes_per_token": 3.4068522483940042,
"tokens_per_byte": 0.29352608422375864,
"round_trip": true
},
{
"code": "ctu",
"autonym": "Ch'ol, Lakty’añ",
"spanish_name": "Ch'ol",
"inali_name": "ch’ol del noroeste",
"english_name": "Chol",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1753,
"tokens": 365,
"chars_per_token": 4.13972602739726,
"tokens_per_char": 0.2415618795499669,
"bytes_per_token": 4.802739726027397,
"tokens_per_byte": 0.20821448944666288,
"round_trip": true
},
{
"code": "chf",
"autonym": "Yocot'an",
"spanish_name": "Chontal de Tabasco",
"inali_name": "chontal de Tabasco central",
"english_name": "Tabasco Chontal",
"samples": 4,
"chars": 2015,
"utf8_bytes": 2165,
"tokens": 658,
"chars_per_token": 3.0623100303951367,
"tokens_per_char": 0.32655086848635234,
"bytes_per_token": 3.290273556231003,
"tokens_per_byte": 0.3039260969976905,
"round_trip": true
},
{
"code": "cac",
"autonym": "Koti'",
"spanish_name": "Chuj",
"inali_name": "Chuj",
"english_name": "Chuj",
"samples": 3,
"chars": 1445,
"utf8_bytes": 1614,
"tokens": 456,
"chars_per_token": 3.168859649122807,
"tokens_per_char": 0.31557093425605537,
"bytes_per_token": 3.539473684210526,
"tokens_per_byte": 0.2825278810408922,
"round_trip": true
},
{
"code": "crn",
"autonym": "Naáyeri Nyuuca",
"spanish_name": "Cora de El Nayar",
"inali_name": "cora meseño",
"english_name": "El Nayar Cora",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1664,
"tokens": 565,
"chars_per_token": 2.674336283185841,
"tokens_per_char": 0.3739245532759762,
"bytes_per_token": 2.945132743362832,
"tokens_per_byte": 0.3395432692307692,
"round_trip": true
},
{
"code": "cok",
"autonym": "Cuéimarusaꞌna",
"spanish_name": "Cora de Santa Teresa",
"inali_name": "cora tereseño",
"english_name": "Santa Teresa Cora",
"samples": 1,
"chars": 503,
"utf8_bytes": 503,
"tokens": 172,
"chars_per_token": 2.9244186046511627,
"tokens_per_char": 0.341948310139165,
"bytes_per_token": 2.9244186046511627,
"tokens_per_byte": 0.341948310139165,
"round_trip": true
},
{
"code": "cux",
"autonym": "Cuicateco yeⁿꞌe Tepeuxila",
"spanish_name": "Cuicateco de Tepeuxila",
"inali_name": "cuicateco del centro",
"english_name": "Tepeuxila Cuicatec",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1828,
"tokens": 407,
"chars_per_token": 3.7125307125307123,
"tokens_per_char": 0.26935804103242883,
"bytes_per_token": 4.4914004914004915,
"tokens_per_byte": 0.22264770240700218,
"round_trip": true
},
{
"code": "var",
"autonym": "Warijio",
"spanish_name": "Guarijío",
"inali_name": "guarijío del norte",
"english_name": "Huarijío",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1648,
"tokens": 498,
"chars_per_token": 3.034136546184739,
"tokens_per_char": 0.32958305757776307,
"bytes_per_token": 3.3092369477911645,
"tokens_per_byte": 0.30218446601941745,
"round_trip": true
},
{
"code": "hus",
"autonym": "Teenek",
"spanish_name": "Huasteco",
"inali_name": "huasteco del occidente",
"english_name": "Huastec",
"samples": 3,
"chars": 1450,
"utf8_bytes": 1585,
"tokens": 378,
"chars_per_token": 3.835978835978836,
"tokens_per_char": 0.26068965517241377,
"bytes_per_token": 4.193121693121693,
"tokens_per_byte": 0.2384858044164038,
"round_trip": true
},
{
"code": "huv",
"autonym": "Ombeayiüts",
"spanish_name": "Huave de San Mateo del Mar",
"inali_name": "huave del oeste",
"english_name": "San Mateo del Mar Huave",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1600,
"tokens": 376,
"chars_per_token": 4.0186170212765955,
"tokens_per_char": 0.24884182660489743,
"bytes_per_token": 4.25531914893617,
"tokens_per_byte": 0.235,
"round_trip": true
},
{
"code": "hch",
"autonym": "Wixárika, Wixárika Niukiyari",
"spanish_name": "Huichol",
"inali_name": "huichol del norte",
"english_name": "Huichol",
"samples": 5,
"chars": 2519,
"utf8_bytes": 2752,
"tokens": 844,
"chars_per_token": 2.984597156398104,
"tokens_per_char": 0.3350535926955141,
"bytes_per_token": 3.2606635071090047,
"tokens_per_byte": 0.3066860465116279,
"round_trip": true
},
{
"code": "jac",
"autonym": "Abxubal, Abꞌxubꞌal Poptiꞌ",
"spanish_name": "Jakalteko",
"inali_name": "Jakalteko",
"english_name": "Jakalteko",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1689,
"tokens": 523,
"chars_per_token": 2.8891013384321225,
"tokens_per_char": 0.34612839179351423,
"bytes_per_token": 3.229445506692161,
"tokens_per_byte": 0.30965068087625813,
"round_trip": true
},
{
"code": "quc",
"autonym": "K'iche', Qach'abel",
"spanish_name": "Kiché",
"inali_name": "K’iche’ (oriental)",
"english_name": "K’iche’",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1558,
"tokens": 470,
"chars_per_token": 3.2148936170212767,
"tokens_per_char": 0.3110522832561218,
"bytes_per_token": 3.3148936170212764,
"tokens_per_byte": 0.30166880616174585,
"round_trip": true
},
{
"code": "klb",
"autonym": "Kiliwa",
"spanish_name": "Kiliwa",
"inali_name": "kiliwa",
"english_name": "Kiliwa",
"samples": 1,
"chars": 503,
"utf8_bytes": 528,
"tokens": 168,
"chars_per_token": 2.994047619047619,
"tokens_per_char": 0.33399602385685884,
"bytes_per_token": 3.142857142857143,
"tokens_per_byte": 0.3181818181818182,
"round_trip": true
},
{
"code": "dih",
"autonym": "Kumiai",
"spanish_name": "Kumiai",
"inali_name": "kumiai",
"english_name": "Kumiai",
"samples": 2,
"chars": 1007,
"utf8_bytes": 1048,
"tokens": 305,
"chars_per_token": 3.301639344262295,
"tokens_per_char": 0.3028798411122145,
"bytes_per_token": 3.4360655737704917,
"tokens_per_byte": 0.29103053435114506,
"round_trip": true
},
{
"code": "lac",
"autonym": "Jach-t'aan",
"spanish_name": "Lacandón",
"inali_name": "lacandón",
"english_name": "Lacandon",
"samples": 5,
"chars": 2519,
"utf8_bytes": 2820,
"tokens": 673,
"chars_per_token": 3.7429420505200595,
"tokens_per_char": 0.26716951171099645,
"bytes_per_token": 4.190193164933135,
"tokens_per_byte": 0.23865248226950356,
"round_trip": true
},
{
"code": "mam",
"autonym": "Qyol Mam, Yol Mam",
"spanish_name": "Mam",
"inali_name": "Mam de la frontera",
"english_name": "Mam",
"samples": 4,
"chars": 2015,
"utf8_bytes": 2083,
"tokens": 602,
"chars_per_token": 3.3471760797342194,
"tokens_per_char": 0.2987593052109181,
"bytes_per_token": 3.4601328903654487,
"tokens_per_byte": 0.28900624099855976,
"round_trip": true
},
{
"code": "mat",
"autonym": "bot’una",
"spanish_name": "Matlatzinca de San Francisco",
"inali_name": "matlatzinca",
"english_name": "Matlatzinca, San Francisco",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1619,
"tokens": 373,
"chars_per_token": 4.050938337801608,
"tokens_per_char": 0.2468563864990073,
"bytes_per_token": 4.340482573726542,
"tokens_per_byte": 0.23038912909203213,
"round_trip": true
},
{
"code": "yua",
"autonym": "Maaya t'aan",
"spanish_name": "Maya de Yucatán",
"inali_name": "maya",
"english_name": "Yucatec Maya",
"samples": 5,
"chars": 2519,
"utf8_bytes": 2945,
"tokens": 565,
"chars_per_token": 4.458407079646018,
"tokens_per_char": 0.2242953552997221,
"bytes_per_token": 5.212389380530974,
"tokens_per_byte": 0.19185059422750425,
"round_trip": true
},
{
"code": "mfy",
"autonym": "Yorem Nokpo",
"spanish_name": "Mayo",
"inali_name": "mayo",
"english_name": "Mayo",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1555,
"tokens": 470,
"chars_per_token": 3.2148936170212767,
"tokens_per_char": 0.3110522832561218,
"bytes_per_token": 3.3085106382978724,
"tokens_per_byte": 0.3022508038585209,
"round_trip": true
},
{
"code": "maz",
"autonym": "Jñatjo",
"spanish_name": "Mazahua Central",
"inali_name": "mazahua de oriente",
"english_name": "Central Mazahua",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1702,
"tokens": 380,
"chars_per_token": 3.9763157894736842,
"tokens_per_char": 0.2514890800794176,
"bytes_per_token": 4.478947368421053,
"tokens_per_byte": 0.22326674500587543,
"round_trip": true
},
{
"code": "mmc",
"autonym": "Jñatjo",
"spanish_name": "Mazahua de Michoacán",
"inali_name": "mazahua de occidente",
"english_name": "Michoacán Mazahua",
"samples": 2,
"chars": 1007,
"utf8_bytes": 1069,
"tokens": 338,
"chars_per_token": 2.9792899408284024,
"tokens_per_char": 0.3356504468718967,
"bytes_per_token": 3.162721893491124,
"tokens_per_byte": 0.3161833489242282,
"round_trip": true
},
{
"code": "vmp",
"autonym": "En naxijen",
"spanish_name": "Mazateco de Soyaltepec",
"inali_name": "mazateco del noreste",
"english_name": "Soyaltepec Mazatec",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1661,
"tokens": 484,
"chars_per_token": 3.121900826446281,
"tokens_per_char": 0.3203176704169424,
"bytes_per_token": 3.4318181818181817,
"tokens_per_byte": 0.2913907284768212,
"round_trip": true
},
{
"code": "mzi",
"autonym": "En ningotsie",
"spanish_name": "Mazateco de Ixcatlán",
"inali_name": "mazateco de la presa bajo",
"english_name": "Ixcatlán Mazatec",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1686,
"tokens": 461,
"chars_per_token": 3.27765726681128,
"tokens_per_char": 0.30509596293845137,
"bytes_per_token": 3.6572668112798263,
"tokens_per_byte": 0.2734282325029656,
"round_trip": true
},
{
"code": "maj",
"autonym": "Kinꞌekꞌatiya, Ntaxjo̱",
"spanish_name": "Mazateco de Jalapa de Díaz",
"inali_name": "mazateco del este bajo",
"english_name": "Jalapa de Díaz Mazatec",
"samples": 1,
"chars": 503,
"utf8_bytes": 507,
"tokens": 134,
"chars_per_token": 3.753731343283582,
"tokens_per_char": 0.2664015904572565,
"bytes_per_token": 3.783582089552239,
"tokens_per_byte": 0.26429980276134124,
"round_trip": true
},
{
"code": "maq",
"autonym": "Hne naja, Nne nangui ngaxni",
"spanish_name": "Mazateco de Chiquihuitlán",
"inali_name": "mazateco del sur",
"english_name": "Chiquihuitlán Mazatec",
"samples": 2,
"chars": 1007,
"utf8_bytes": 1099,
"tokens": 330,
"chars_per_token": 3.0515151515151517,
"tokens_per_char": 0.32770605759682225,
"bytes_per_token": 3.33030303030303,
"tokens_per_byte": 0.3002729754322111,
"round_trip": true
},
{
"code": "vmy",
"autonym": "Enre naxinanda nguifi",
"spanish_name": "Mazateco de Ayautla",
"inali_name": "mazateco del sureste",
"english_name": "Ayautla Mazatec",
"samples": 1,
"chars": 503,
"utf8_bytes": 556,
"tokens": 173,
"chars_per_token": 2.907514450867052,
"tokens_per_char": 0.34393638170974156,
"bytes_per_token": 3.213872832369942,
"tokens_per_byte": 0.31115107913669066,
"round_trip": true
},
{
"code": "mau",
"autonym": "Én‑ná",
"spanish_name": "Mazateco de Huautla",
"inali_name": "mazateco del centro",
"english_name": "Huautla Mazatec",
"samples": 5,
"chars": 2519,
"utf8_bytes": 2838,
"tokens": 761,
"chars_per_token": 3.3101182654402104,
"tokens_per_char": 0.3021040095275903,
"bytes_per_token": 3.729303547963206,
"tokens_per_byte": 0.2681465821000705,
"round_trip": true
},
{
"code": "mto",
"autonym": "Ayöök",
"spanish_name": "Mixe de Totontepec",
"inali_name": "mixe alto del norte",
"english_name": "Totontepec Mixe",
"samples": 4,
"chars": 2015,
"utf8_bytes": 2331,
"tokens": 718,
"chars_per_token": 2.8064066852367686,
"tokens_per_char": 0.3563275434243176,
"bytes_per_token": 3.246518105849582,
"tokens_per_byte": 0.308022308022308,
"round_trip": true
},
{
"code": "mxp",
"autonym": "Ayuujk",
"spanish_name": "Mixe de Tlahuitoltepec",
"inali_name": "mixe alto del centro",
"english_name": "Tlahuitoltepec Mixe",
"samples": 2,
"chars": 1007,
"utf8_bytes": 1141,
"tokens": 400,
"chars_per_token": 2.5175,
"tokens_per_char": 0.3972194637537239,
"bytes_per_token": 2.8525,
"tokens_per_byte": 0.35056967572305,
"round_trip": true
},
{
"code": "mxq",
"autonym": "Ayuk",
"spanish_name": "Mixe de Juquila",
"inali_name": "mixe medio del este",
"english_name": "Juquila Mixe",
"samples": 4,
"chars": 2015,
"utf8_bytes": 2509,
"tokens": 675,
"chars_per_token": 2.9851851851851854,
"tokens_per_char": 0.3349875930521092,
"bytes_per_token": 3.717037037037037,
"tokens_per_byte": 0.269031486648067,
"round_trip": true
},
{
"code": "xta",
"autonym": "Tu̱'un sâvi",
"spanish_name": "Mixteco de Alcozauca",
"inali_name": "mixteco de Guerrero del noreste central",
"english_name": "Alcozauca Mixtec",
"samples": 2,
"chars": 1007,
"utf8_bytes": 1075,
"tokens": 306,
"chars_per_token": 3.2908496732026142,
"tokens_per_char": 0.3038728897715988,
"bytes_per_token": 3.5130718954248366,
"tokens_per_byte": 0.2846511627906977,
"round_trip": true
},
{
"code": "mxv",
"autonym": "Tuꞌun Savi de Metlatónoc y Cochoapa el Grande, Tuꞌun savi",
"spanish_name": "Mixteco de Metlatónoc",
"inali_name": "mixteco de Guerrero del este medio",
"english_name": "Metlatónoc Mixtec",
"samples": 1,
"chars": 503,
"utf8_bytes": 568,
"tokens": 214,
"chars_per_token": 2.350467289719626,
"tokens_per_char": 0.4254473161033797,
"bytes_per_token": 2.6542056074766354,
"tokens_per_byte": 0.3767605633802817,
"round_trip": true
},
{
"code": "miy",
"autonym": "Tu̱n savi̱ꞌ Tu̱tyoo̱ꞌ",
"spanish_name": "Mixteco de Ayutla",
"inali_name": "mixteco de Ayutla",
"english_name": "Ayutla Mixtec",
"samples": 4,
"chars": 2015,
"utf8_bytes": 2417,
"tokens": 613,
"chars_per_token": 3.2871125611745513,
"tokens_per_char": 0.3042183622828784,
"bytes_per_token": 3.9429037520391517,
"tokens_per_byte": 0.25362019031857674,
"round_trip": true
},
{
"code": "mxt",
"autonym": "Sa'an Xiñi Savi",
"spanish_name": "Mixteco de Jamiltepec",
"inali_name": "mixteco de Oaxaca de costa central baja",
"english_name": "Jamiltepec Mixtec",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1672,
"tokens": 446,
"chars_per_token": 3.3878923766816142,
"tokens_per_char": 0.29516876240900064,
"bytes_per_token": 3.7488789237668163,
"tokens_per_byte": 0.26674641148325356,
"round_trip": true
},
{
"code": "mza",
"autonym": "Tu'un va'a",
"spanish_name": "Mixteco de Santa María Zacatepec",
"inali_name": "mixteco de Sierra sur oeste",
"english_name": "Santa María Zacatepec Mixtec",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1780,
"tokens": 441,
"chars_per_token": 3.4263038548752833,
"tokens_per_char": 0.29185969556585045,
"bytes_per_token": 4.036281179138322,
"tokens_per_byte": 0.24775280898876403,
"round_trip": true
},
{
"code": "meh",
"autonym": "Tu̱ꞌun káꞌánꞌ kájí",
"spanish_name": "Mixteco del Suroeste de Tlaxiaco",
"inali_name": "mixteco del suroeste",
"english_name": "Southwestern Tlaxiaco Mixtec",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1552,
"tokens": 400,
"chars_per_token": 3.7775,
"tokens_per_char": 0.26472534745201853,
"bytes_per_token": 3.88,
"tokens_per_byte": 0.25773195876288657,
"round_trip": true
},
{
"code": "mix",
"autonym": "Sa'an Savi Snuviko, Sa'an savi",
"spanish_name": "Mixteco de Mixtepec",
"inali_name": "mixteco de Ñumi",
"english_name": "Mixtepec Mixtec",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1669,
"tokens": 444,
"chars_per_token": 3.4031531531531534,
"tokens_per_char": 0.2938451356717406,
"bytes_per_token": 3.759009009009009,
"tokens_per_byte": 0.2660275614140204,
"round_trip": true
},
{
"code": "xtn",
"autonym": "Saꞌan savi",
"spanish_name": "Mixteco de Tlaxiaco del Norte",
"inali_name": "mixteco del norte bajo",
"english_name": "Northern Tlaxiaco Mixtec",
"samples": 4,
"chars": 2015,
"utf8_bytes": 2174,
"tokens": 619,
"chars_per_token": 3.255250403877221,
"tokens_per_char": 0.30719602977667493,
"bytes_per_token": 3.5121163166397413,
"tokens_per_byte": 0.2847286108555658,
"round_trip": true
},
{
"code": "mks",
"autonym": "Tu̱hun ndáhví",
"spanish_name": "Mixteco de Silacayoapan",
"inali_name": "mixteco del oeste alto",
"english_name": "Silacayoapan Mixtec",
"samples": 1,
"chars": 503,
"utf8_bytes": 549,
"tokens": 167,
"chars_per_token": 3.0119760479041915,
"tokens_per_char": 0.3320079522862823,
"bytes_per_token": 3.287425149700599,
"tokens_per_byte": 0.30418943533697634,
"round_trip": true
},
{
"code": "mie",
"autonym": "Tūhun sāsávī",
"spanish_name": "Mixteco de Ocotepec",
"inali_name": "mixteco de Sierra sur noroeste",
"english_name": "Ocotepec Mixtec",
"samples": 4,
"chars": 2015,
"utf8_bytes": 2238,
"tokens": 540,
"chars_per_token": 3.7314814814814814,
"tokens_per_char": 0.2679900744416873,
"bytes_per_token": 4.144444444444445,
"tokens_per_byte": 0.24128686327077747,
"round_trip": true
},
{
"code": "mio",
"autonym": "Tuhun Ñuun Ñucaan",
"spanish_name": "Mixteco de Pinotepa Nacional",
"inali_name": "mixteco del oeste de la costa",
"english_name": "Pinotepa Nacional Mixtec",
"samples": 4,
"chars": 2015,
"utf8_bytes": 2186,
"tokens": 462,
"chars_per_token": 4.361471861471862,
"tokens_per_char": 0.2292803970223325,
"bytes_per_token": 4.731601731601732,
"tokens_per_byte": 0.21134492223238793,
"round_trip": true
},
{
"code": "nhx",
"autonym": "Melaꞌtájto̱l",
"spanish_name": "Náhuatl del Istmo-Mecayapan",
"inali_name": "náhuatl del Istmo",
"english_name": "Isthmus-Mecayapan Nahuatl",
"samples": 1,
"chars": 503,
"utf8_bytes": 503,
"tokens": 139,
"chars_per_token": 3.618705035971223,
"tokens_per_char": 0.27634194831013914,
"bytes_per_token": 3.618705035971223,
"tokens_per_byte": 0.27634194831013914,
"round_trip": true
},
{
"code": "nhe",
"autonym": "Mexkatl",
"spanish_name": "Náhuatl Huasteco Oriental",
"inali_name": "náhuatl de la Huasteca veracruzana",
"english_name": "Eastern Huasteca Nahuatl",
"samples": 4,
"chars": 2015,
"utf8_bytes": 2083,
"tokens": 462,
"chars_per_token": 4.361471861471862,
"tokens_per_char": 0.2292803970223325,
"bytes_per_token": 4.508658008658009,
"tokens_per_byte": 0.22179548727796447,
"round_trip": true
},
{
"code": "nhw",
"autonym": "Nahuatl",
"spanish_name": "Náhuatl Huasteco Occidental",
"inali_name": "náhuatl de la Huasteca potosina",
"english_name": "Western Huasteca Nahuatl",
"samples": 4,
"chars": 2015,
"utf8_bytes": 2015,
"tokens": 460,
"chars_per_token": 4.380434782608695,
"tokens_per_char": 0.228287841191067,
"bytes_per_token": 4.380434782608695,
"tokens_per_byte": 0.228287841191067,
"round_trip": true
},
{
"code": "nhy",
"autonym": "Nāhuatlahtōlli",
"spanish_name": "Náhuatl del Norte de Oaxaca",
"inali_name": "náhuatl de Oaxaca",
"english_name": "Northern Oaxaca Nahuatl",
"samples": 5,
"chars": 2519,
"utf8_bytes": 2587,
"tokens": 683,
"chars_per_token": 3.6881405563689604,
"tokens_per_char": 0.27113934100833664,
"bytes_per_token": 3.787701317715959,
"tokens_per_byte": 0.26401236954000773,
"round_trip": true
},
{
"code": "nsu",
"autonym": "Nahuatl, Nahuatlajtoli",
"spanish_name": "Náhuatl de la Sierra Negra",
"inali_name": "náhuatl de la Sierra negra, sur",
"english_name": "Sierra Negra Nahuatl",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1548,
"tokens": 444,
"chars_per_token": 3.4031531531531534,
"tokens_per_char": 0.2938451356717406,
"bytes_per_token": 3.4864864864864864,
"tokens_per_byte": 0.2868217054263566,
"round_trip": true
},
{
"code": "ncj",
"autonym": "Mexicatl",
"spanish_name": "Náhuatl del Norte de Puebla",
"inali_name": "náhuatl alto del norte de Puebla",
"english_name": "Northern Puebla Nahuatl",
"samples": 4,
"chars": 2015,
"utf8_bytes": 2035,
"tokens": 551,
"chars_per_token": 3.6569872958257714,
"tokens_per_char": 0.27344913151364764,
"bytes_per_token": 3.6932849364791287,
"tokens_per_byte": 0.27076167076167074,
"round_trip": true
},
{
"code": "ncx",
"autonym": "",
"spanish_name": "Náhuatl de Puebla Central",
"inali_name": "náhuatl del centro de Puebla",
"english_name": "Nahuatl, Central Puebla",
"samples": 5,
"chars": 2519,
"utf8_bytes": 2554,
"tokens": 615,
"chars_per_token": 4.095934959349593,
"tokens_per_char": 0.2441445017864232,
"bytes_per_token": 4.152845528455285,
"tokens_per_byte": 0.2407987470634299,
"round_trip": true
},
{
"code": "azn",
"autonym": "Meshikan de San Agustin Buenaventura y de Santa Cruz",
"spanish_name": "Náhuatl de Durango Occidental",
"inali_name": "mexicano del noroeste",
"english_name": "Western Durango Nahuatl",
"samples": 4,
"chars": 2007,
"utf8_bytes": 2026,
"tokens": 576,
"chars_per_token": 3.484375,
"tokens_per_char": 0.28699551569506726,
"bytes_per_token": 3.517361111111111,
"tokens_per_byte": 0.2843040473840079,
"round_trip": true
},
{
"code": "ngu",
"autonym": "Nauatlajtojli",
"spanish_name": "Náhuatl de Guerrero",
"inali_name": "mexicano de Guerrero",
"english_name": "Guerrero Nahuatl",
"samples": 4,
"chars": 2015,
"utf8_bytes": 2020,
"tokens": 590,
"chars_per_token": 3.4152542372881354,
"tokens_per_char": 0.29280397022332505,
"bytes_per_token": 3.4237288135593222,
"tokens_per_byte": 0.29207920792079206,
"round_trip": true
},
{
"code": "nhm",
"autonym": "Ika mejikano, Ika nauatl",
"spanish_name": "Náhuatl de Morelos",
"inali_name": "mexicano central bajo",
"english_name": "Morelos Nahuatl",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1511,
"tokens": 360,
"chars_per_token": 4.197222222222222,
"tokens_per_char": 0.23825281270681667,
"bytes_per_token": 4.197222222222222,
"tokens_per_byte": 0.23825281270681667,
"round_trip": true
},
{
"code": "nch",
"autonym": "Nāhuatlahtōlli",
"spanish_name": "Náhuatl Huasteco Central",
"inali_name": "mexicano de la Huasteca Hidalguense",
"english_name": "Central Huasteca Nahuatl",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1511,
"tokens": 451,
"chars_per_token": 3.350332594235033,
"tokens_per_char": 0.2984778292521509,
"bytes_per_token": 3.350332594235033,
"tokens_per_byte": 0.2984778292521509,
"round_trip": true
},
{
"code": "plo",
"autonym": "",
"spanish_name": "Popoluca de Oluta",
"inali_name": "oluteco",
"english_name": "Popoluca, Oluta",
"samples": 1,
"chars": 499,
"utf8_bytes": 540,
"tokens": 177,
"chars_per_token": 2.8192090395480225,
"tokens_per_char": 0.35470941883767537,
"bytes_per_token": 3.0508474576271185,
"tokens_per_byte": 0.3277777777777778,
"round_trip": true
},
{
"code": "otm",
"autonym": "Nyuhu",
"spanish_name": "Otomí de la Sierra Oriental",
"inali_name": "otomí de la Sierra",
"english_name": "Eastern Highland Otomi",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1745,
"tokens": 523,
"chars_per_token": 2.8891013384321225,
"tokens_per_char": 0.34612839179351423,
"bytes_per_token": 3.3365200764818357,
"tokens_per_byte": 0.2997134670487106,
"round_trip": true
},
{
"code": "otq",
"autonym": "Ñhöñhö",
"spanish_name": "Otomí de Querétaro",
"inali_name": "otomí del noroeste",
"english_name": "Querétaro Otomi",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1834,
"tokens": 523,
"chars_per_token": 2.8891013384321225,
"tokens_per_char": 0.34612839179351423,
"bytes_per_token": 3.5066921606118546,
"tokens_per_byte": 0.2851690294438386,
"round_trip": true
},
{
"code": "ppi",
"autonym": "Paipai",
"spanish_name": "Paipai",
"inali_name": "paipai",
"english_name": "Paipai",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1554,
"tokens": 530,
"chars_per_token": 2.8509433962264152,
"tokens_per_char": 0.35076108537392453,
"bytes_per_token": 2.9320754716981132,
"tokens_per_byte": 0.3410553410553411,
"round_trip": true
},
{
"code": "pmq",
"autonym": "Xi'iuy",
"spanish_name": "Pame del Norte",
"inali_name": "pame del norte",
"english_name": "Northern Pame",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1738,
"tokens": 464,
"chars_per_token": 3.2564655172413794,
"tokens_per_char": 0.3070814030443415,
"bytes_per_token": 3.7456896551724137,
"tokens_per_byte": 0.2669735327963176,
"round_trip": true
},
{
"code": "pbs",
"autonym": "Xi'oi",
"spanish_name": "Pame Central",
"inali_name": "pame del centro",
"english_name": "Central Pame",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1671,
"tokens": 488,
"chars_per_token": 3.096311475409836,
"tokens_per_char": 0.3229649238914626,
"bytes_per_token": 3.4241803278688523,
"tokens_per_byte": 0.29204069419509276,
"round_trip": true
},
{
"code": "ood",
"autonym": "Oʼodham ha-ñeʼokĭ, Oʼodham ñiok",
"spanish_name": "Pápago-Pima",
"inali_name": "pápago",
"english_name": "Tohono O’odham",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1539,
"tokens": 493,
"chars_per_token": 3.0649087221095335,
"tokens_per_char": 0.32627399073461283,
"bytes_per_token": 3.1217038539553754,
"tokens_per_byte": 0.3203378817413905,
"round_trip": true
},
{
"code": "pia",
"autonym": "Oob No'ok",
"spanish_name": "Pima Bajo",
"inali_name": "pima del sur",
"english_name": "Pima Bajo",
"samples": 4,
"chars": 2015,
"utf8_bytes": 2189,
"tokens": 554,
"chars_per_token": 3.637184115523466,
"tokens_per_char": 0.2749379652605459,
"bytes_per_token": 3.9512635379061374,
"tokens_per_byte": 0.25308359981726813,
"round_trip": true
},
{
"code": "pls",
"autonym": "Ngigua",
"spanish_name": "Popoloca de San Marcos Tlacoyalco",
"inali_name": "popoloca del norte",
"english_name": "San Marcos Tlacoyalco Popoloca",
"samples": 1,
"chars": 503,
"utf8_bytes": 513,
"tokens": 156,
"chars_per_token": 3.2243589743589745,
"tokens_per_char": 0.3101391650099404,
"bytes_per_token": 3.2884615384615383,
"tokens_per_byte": 0.30409356725146197,
"round_trip": true
},
{
"code": "poi",
"autonym": "Nuntajɨ̱yi",
"spanish_name": "Popoluca de la Sierra",
"inali_name": "popoluca de la Sierra",
"english_name": "Highland Popoluca",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1764,
"tokens": 435,
"chars_per_token": 3.4735632183908045,
"tokens_per_char": 0.2878888153540701,
"bytes_per_token": 4.055172413793104,
"tokens_per_byte": 0.2465986394557823,
"round_trip": true
},
{
"code": "knj",
"autonym": "K'anjob'al",
"spanish_name": "Kaanjobal",
"inali_name": "Q’anjob’al",
"english_name": "Akateko",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1635,
"tokens": 476,
"chars_per_token": 3.1743697478991595,
"tokens_per_char": 0.31502316346790205,
"bytes_per_token": 3.4348739495798317,
"tokens_per_byte": 0.291131498470948,
"round_trip": true
},
{
"code": "mhc",
"autonym": "Mocho'",
"spanish_name": "Motozintleco",
"inali_name": "mocho’",
"english_name": "Mocho",
"samples": 4,
"chars": 2015,
"utf8_bytes": 2021,
"tokens": 470,
"chars_per_token": 4.287234042553192,
"tokens_per_char": 0.23325062034739455,
"bytes_per_token": 4.3,
"tokens_per_byte": 0.23255813953488372,
"round_trip": true
},
{
"code": "kek",
"autonym": "Q'eqchi'",
"spanish_name": "Q'eqchi'",
"inali_name": "Q’eqchi’",
"english_name": "Q’eqchi’",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1736,
"tokens": 519,
"chars_per_token": 2.9113680154142583,
"tokens_per_char": 0.343481138318994,
"bytes_per_token": 3.3448940269749516,
"tokens_per_byte": 0.298963133640553,
"round_trip": true
},
{
"code": "sei",
"autonym": "Cmiique Iitom",
"spanish_name": "Seri",
"inali_name": "seri",
"english_name": "Seri",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1531,
"tokens": 298,
"chars_per_token": 5.070469798657718,
"tokens_per_char": 0.1972203838517538,
"bytes_per_token": 5.1375838926174495,
"tokens_per_byte": 0.1946440235140431,
"round_trip": true
},
{
"code": "thh",
"autonym": "ralámuli raicha",
"spanish_name": "Tarahumara del Norte",
"inali_name": "tarahumara del norte",
"english_name": "Tarahumara, Northern",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1676,
"tokens": 473,
"chars_per_token": 3.1945031712473573,
"tokens_per_char": 0.3130377233620119,
"bytes_per_token": 3.543340380549683,
"tokens_per_byte": 0.2822195704057279,
"round_trip": true
},
{
"code": "tar",
"autonym": "Ralámuli raꞌíchala",
"spanish_name": "Tarahumara Central",
"inali_name": "tarahumara del centro",
"english_name": "Central Tarahumara",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1585,
"tokens": 511,
"chars_per_token": 2.9569471624266144,
"tokens_per_char": 0.3381866313699537,
"bytes_per_token": 3.101761252446184,
"tokens_per_byte": 0.322397476340694,
"round_trip": true
},
{
"code": "tsz",
"autonym": "P’urhe, P’urhépecha",
"spanish_name": "Purépecha",
"inali_name": "purépecha",
"english_name": "Purepecha",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1590,
"tokens": 413,
"chars_per_token": 3.6585956416464893,
"tokens_per_char": 0.27332892124420916,
"bytes_per_token": 3.8498789346246975,
"tokens_per_byte": 0.259748427672956,
"round_trip": true
},
{
"code": "tee",
"autonym": "Lhima'alh'ama'",
"spanish_name": "Tepehua de Huehuetla",
"inali_name": "tepehua del sur",
"english_name": "Huehuetla Tepehua",
"samples": 4,
"chars": 2015,
"utf8_bytes": 2052,
"tokens": 522,
"chars_per_token": 3.8601532567049808,
"tokens_per_char": 0.25905707196029776,
"bytes_per_token": 3.9310344827586206,
"tokens_per_byte": 0.2543859649122807,
"round_trip": true
},
{
"code": "tpp",
"autonym": "Lhichiwin",
"spanish_name": "Tepehua de Pisaflores",
"inali_name": "tepehua del norte",
"english_name": "Pisaflores Tepehua",
"samples": 4,
"chars": 2015,
"utf8_bytes": 2099,
"tokens": 498,
"chars_per_token": 4.046184738955823,
"tokens_per_char": 0.24714640198511167,
"bytes_per_token": 4.214859437751004,
"tokens_per_byte": 0.2372558361124345,
"round_trip": true
},
{
"code": "ntp",
"autonym": "Oodamicʌdʌ",
"spanish_name": "Tepehuano del Norte",
"inali_name": "tepehuano del norte",
"english_name": "Northern Tepehuan",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1638,
"tokens": 417,
"chars_per_token": 3.6235011990407675,
"tokens_per_char": 0.2759761747187293,
"bytes_per_token": 3.9280575539568345,
"tokens_per_byte": 0.25457875457875456,
"round_trip": true
},
{
"code": "tla",
"autonym": "",
"spanish_name": "Tepehuano del Suroeste",
"inali_name": "tepehuano del sur alto",
"english_name": "Tepehuan, Southwestern",
"samples": 2,
"chars": 1007,
"utf8_bytes": 1216,
"tokens": 294,
"chars_per_token": 3.425170068027211,
"tokens_per_char": 0.2919563058589871,
"bytes_per_token": 4.136054421768708,
"tokens_per_byte": 0.24177631578947367,
"round_trip": true
},
{
"code": "stp",
"autonym": "Oꞌdam",
"spanish_name": "Tepehuano del Sureste",
"inali_name": "tepehuano del sur bajo",
"english_name": "Southeastern Tepehuan",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1570,
"tokens": 583,
"chars_per_token": 2.5917667238421958,
"tokens_per_char": 0.385837193911317,
"bytes_per_token": 2.692967409948542,
"tokens_per_byte": 0.37133757961783437,
"round_trip": true
},
{
"code": "ocu",
"autonym": "pjiekak'joo",
"spanish_name": "Tlahuica",
"inali_name": "tlahuica",
"english_name": "Tlahuica",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1644,
"tokens": 398,
"chars_per_token": 3.7964824120603016,
"tokens_per_char": 0.2634017207147584,
"bytes_per_token": 4.130653266331659,
"tokens_per_byte": 0.24209245742092458,
"round_trip": true
},
{
"code": "tcf",
"autonym": "Mè'phàà Mañuwìín",
"spanish_name": "Tlapaneco a de Malinaltepec",
"inali_name": "tlapaneco central bajo",
"english_name": "Malinaltepec Me’phaa",
"samples": 2,
"chars": 1007,
"utf8_bytes": 1248,
"tokens": 428,
"chars_per_token": 2.352803738317757,
"tokens_per_char": 0.42502482621648463,
"bytes_per_token": 2.9158878504672896,
"tokens_per_byte": 0.34294871794871795,
"round_trip": true
},
{
"code": "tpx",
"autonym": "Meꞌpa̱a̱ Wíꞌi̱i̱n",
"spanish_name": "Tlapaneco de Acatepec",
"inali_name": "tlapaneco del suroeste",
"english_name": "Acatepec Me’phaa",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1695,
"tokens": 589,
"chars_per_token": 2.565365025466893,
"tokens_per_char": 0.38980807412309726,
"bytes_per_token": 2.877758913412564,
"tokens_per_byte": 0.34749262536873154,
"round_trip": true
},
{
"code": "tpl",
"autonym": "Meꞌpa̱a̱ Wíꞌi̱i̱n",
"spanish_name": "Tlapaneco de Tacoapa",
"inali_name": "tlapaneco del centro",
"english_name": "Tlacoapa Me’phaa",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1948,
"tokens": 628,
"chars_per_token": 2.406050955414013,
"tokens_per_char": 0.41561879549966907,
"bytes_per_token": 3.1019108280254777,
"tokens_per_byte": 0.32238193018480493,
"round_trip": true
},
{
"code": "toj",
"autonym": "Tojol-ab'al",
"spanish_name": "Tojolabal",
"inali_name": "tojolabal",
"english_name": "Tojolabal",
"samples": 4,
"chars": 2015,
"utf8_bytes": 2196,
"tokens": 529,
"chars_per_token": 3.8090737240075616,
"tokens_per_char": 0.26253101736972706,
"bytes_per_token": 4.151228733459357,
"tokens_per_byte": 0.24089253187613843,
"round_trip": true
},
{
"code": "toc",
"autonym": "Tutunakú",
"spanish_name": "Totonaco de Coyutla",
"inali_name": "totonaco central del norte",
"english_name": "Coyutla Totonac",
"samples": 1,
"chars": 503,
"utf8_bytes": 505,
"tokens": 209,
"chars_per_token": 2.4066985645933014,
"tokens_per_char": 0.415506958250497,
"bytes_per_token": 2.416267942583732,
"tokens_per_byte": 0.41386138613861384,
"round_trip": true
},
{
"code": "tqt",
"autonym": "Xinulajgsípij Totonaco",
"spanish_name": "Totonaco del Cerro Xinolatépetl",
"inali_name": "totonaco del cerro Xinolatépetl",
"english_name": "Totonaco del cerro Xinolatépetl",
"samples": 4,
"chars": 2015,
"utf8_bytes": 2057,
"tokens": 606,
"chars_per_token": 3.325082508250825,
"tokens_per_char": 0.3007444168734491,
"bytes_per_token": 3.3943894389438944,
"tokens_per_byte": 0.29460379192999514,
"round_trip": true
},
{
"code": "top",
"autonym": "Lichiwin Tutunaku, Tutunakú",
"spanish_name": "Totonaco de Papantla",
"inali_name": "totonaco de la costa",
"english_name": "Papantla Totonac",
"samples": 5,
"chars": 2519,
"utf8_bytes": 2582,
"tokens": 574,
"chars_per_token": 4.388501742160279,
"tokens_per_char": 0.2278682016673283,
"bytes_per_token": 4.498257839721254,
"tokens_per_byte": 0.22230828814872192,
"round_trip": true
},
{
"code": "tos",
"autonym": "Totonaco",
"spanish_name": "Totonaco de la Sierra",
"inali_name": "totonaco central del sur",
"english_name": "Highland Totonac",
"samples": 4,
"chars": 2015,
"utf8_bytes": 2088,
"tokens": 588,
"chars_per_token": 3.42687074829932,
"tokens_per_char": 0.29181141439205954,
"bytes_per_token": 3.5510204081632653,
"tokens_per_byte": 0.28160919540229884,
"round_trip": true
},
{
"code": "trc",
"autonym": "Xnaꞌánj nu̱ꞌ",
"spanish_name": "Triqui de Copala",
"inali_name": "triqui de San Juan Copala",
"english_name": "Copala Triqui",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1791,
"tokens": 305,
"chars_per_token": 4.954098360655737,
"tokens_per_char": 0.20185307743216413,
"bytes_per_token": 5.872131147540983,
"tokens_per_byte": 0.1702959240647683,
"round_trip": true
},
{
"code": "trs",
"autonym": "Nânj Nï̀nꞌïn",
"spanish_name": "Triqui de Chicahuaxtla",
"inali_name": "triqui de la alta",
"english_name": "Chicahuaxtla Triqui",
"samples": 5,
"chars": 2519,
"utf8_bytes": 2774,
"tokens": 789,
"chars_per_token": 3.1926489226869457,
"tokens_per_char": 0.3132195315601429,
"bytes_per_token": 3.5158428390367553,
"tokens_per_byte": 0.28442682047584716,
"round_trip": true
},
{
"code": "tzh",
"autonym": "Bats'il k'op",
"spanish_name": "Tzeltal",
"inali_name": "tseltal del occidente",
"english_name": "Tzeltal",
"samples": 2,
"chars": 1007,
"utf8_bytes": 1102,
"tokens": 236,
"chars_per_token": 4.266949152542373,
"tokens_per_char": 0.23435948361469713,
"bytes_per_token": 4.669491525423729,
"tokens_per_byte": 0.21415607985480944,
"round_trip": true
},
{
"code": "tzo",
"autonym": "Bats'i k'op",
"spanish_name": "Tsotsil",
"inali_name": "tsotsil del centro",
"english_name": "Tsotsil",
"samples": 4,
"chars": 2015,
"utf8_bytes": 2199,
"tokens": 413,
"chars_per_token": 4.878934624697337,
"tokens_per_char": 0.20496277915632755,
"bytes_per_token": 5.324455205811138,
"tokens_per_byte": 0.18781264211005003,
"round_trip": true
},
{
"code": "yaq",
"autonym": "Yo'em noki",
"spanish_name": "Yaqui",
"inali_name": "yaqui",
"english_name": "Yaqui",
"samples": 4,
"chars": 2015,
"utf8_bytes": 2110,
"tokens": 535,
"chars_per_token": 3.7663551401869158,
"tokens_per_char": 0.2655086848635236,
"bytes_per_token": 3.94392523364486,
"tokens_per_byte": 0.25355450236966826,
"round_trip": true
},
{
"code": "zaq",
"autonym": "Tisa",
"spanish_name": "Zapoteco de Aloápam",
"inali_name": "zapoteco de San Miguel Aloápam",
"english_name": "Aloápam Zapotec",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1675,
"tokens": 446,
"chars_per_token": 3.3878923766816142,
"tokens_per_char": 0.29516876240900064,
"bytes_per_token": 3.7556053811659194,
"tokens_per_byte": 0.2662686567164179,
"round_trip": true
},
{
"code": "zaa",
"autonym": "Titsaꞌ",
"spanish_name": "Zapoteco de la Sierra de Juárez",
"inali_name": "zapoteco serrano, bajo",
"english_name": "Sierra de Juárez Zapotec",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1620,
"tokens": 462,
"chars_per_token": 3.2705627705627704,
"tokens_per_char": 0.3057577763070814,
"bytes_per_token": 3.5064935064935066,
"tokens_per_byte": 0.2851851851851852,
"round_trip": true
},
{
"code": "zpr",
"autonym": "Diste’",
"spanish_name": "Zapoteco de Santiago Xanica",
"inali_name": "zapoteco de la Sierra sur, del sureste bajo",
"english_name": "Santiago Xanica Zapotec",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1589,
"tokens": 505,
"chars_per_token": 2.992079207920792,
"tokens_per_char": 0.33421575115817337,
"bytes_per_token": 3.1465346534653467,
"tokens_per_byte": 0.31780994336060414,
"round_trip": true
},
{
"code": "zai",
"autonym": "Diidxazá",
"spanish_name": "Zapoteco del Istmo",
"inali_name": "zapoteco de la planicie costera",
"english_name": "Isthmus Zapotec",
"samples": 4,
"chars": 2015,
"utf8_bytes": 2234,
"tokens": 482,
"chars_per_token": 4.180497925311204,
"tokens_per_char": 0.2392059553349876,
"bytes_per_token": 4.634854771784233,
"tokens_per_byte": 0.21575649059982094,
"round_trip": true
},
{
"code": "zoc",
"autonym": "Tzunitzame",
"spanish_name": "Zoque de Copainalá",
"inali_name": "zoque del centro",
"english_name": "Copainalá Zoque",
"samples": 4,
"chars": 2015,
"utf8_bytes": 2235,
"tokens": 666,
"chars_per_token": 3.0255255255255253,
"tokens_per_char": 0.33052109181141437,
"bytes_per_token": 3.355855855855856,
"tokens_per_byte": 0.2979865771812081,
"round_trip": true
},
{
"code": "zoq",
"autonym": "",
"spanish_name": "Zoque de Tabasco",
"inali_name": "zoque del este",
"english_name": "Zoque, Tabasco",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1605,
"tokens": 423,
"chars_per_token": 3.5721040189125297,
"tokens_per_char": 0.2799470549305096,
"bytes_per_token": 3.7943262411347516,
"tokens_per_byte": 0.2635514018691589,
"round_trip": true
},
{
"code": "zor",
"autonym": "Otetzame",
"spanish_name": "Zoque de Rayón",
"inali_name": "zoque del norte bajo",
"english_name": "Rayón Zoque",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1712,
"tokens": 523,
"chars_per_token": 2.8891013384321225,
"tokens_per_char": 0.34612839179351423,
"bytes_per_token": 3.273422562141491,
"tokens_per_byte": 0.3054906542056075,
"round_trip": true
},
{
"code": "zos",
"autonym": "Otetzame",
"spanish_name": "Zoque de Francisco León",
"inali_name": "zoque del noroeste",
"english_name": "Francisco León Zoque",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1590,
"tokens": 495,
"chars_per_token": 3.0525252525252524,
"tokens_per_char": 0.32759761747187294,
"bytes_per_token": 3.212121212121212,
"tokens_per_byte": 0.3113207547169811,
"round_trip": true
},
{
"code": "zoh",
"autonym": "Tzunitzame",
"spanish_name": "Zoque de Chimalapa",
"inali_name": "zoque del oeste",
"english_name": "Chimalapa Zoque",
"samples": 4,
"chars": 2015,
"utf8_bytes": 2225,
"tokens": 651,
"chars_per_token": 3.0952380952380953,
"tokens_per_char": 0.3230769230769231,
"bytes_per_token": 3.4178187403993854,
"tokens_per_byte": 0.29258426966292134,
"round_trip": true
}
]