tokenizer_test3 / evaluation /language_fertility.json
ljcamargo's picture
Upload evaluation/language_fertility.json with huggingface_hub
ab1b0a7 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": 396,
"chars_per_token": 5.088383838383838,
"tokens_per_char": 0.1965260545905707,
"bytes_per_token": 6.366161616161616,
"tokens_per_byte": 0.15708052360174535,
"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": 206,
"chars_per_token": 2.441747572815534,
"tokens_per_char": 0.4095427435387674,
"bytes_per_token": 2.9514563106796117,
"tokens_per_byte": 0.33881578947368424,
"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": 345,
"chars_per_token": 2.918840579710145,
"tokens_per_char": 0.3426017874875869,
"bytes_per_token": 3.382608695652174,
"tokens_per_byte": 0.29562982005141386,
"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": 166,
"chars_per_token": 6.066265060240964,
"tokens_per_char": 0.16484607745779542,
"bytes_per_token": 6.13855421686747,
"tokens_per_byte": 0.16290480863591755,
"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": 361,
"chars_per_token": 4.185595567867036,
"tokens_per_char": 0.23891462607544672,
"bytes_per_token": 4.778393351800554,
"tokens_per_byte": 0.20927536231884059,
"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": 708,
"chars_per_token": 2.134180790960452,
"tokens_per_char": 0.4685638649900728,
"bytes_per_token": 2.457627118644068,
"tokens_per_byte": 0.4068965517241379,
"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": 953,
"chars_per_token": 2.114375655823715,
"tokens_per_char": 0.47295285359801487,
"bytes_per_token": 2.645330535152151,
"tokens_per_byte": 0.37802459341531136,
"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": 204,
"chars_per_token": 2.465686274509804,
"tokens_per_char": 0.40556660039761433,
"bytes_per_token": 2.9362745098039214,
"tokens_per_byte": 0.34056761268781305,
"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": 546,
"chars_per_token": 2.7673992673992673,
"tokens_per_char": 0.3613500992720053,
"bytes_per_token": 2.913919413919414,
"tokens_per_byte": 0.3431803896920176,
"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": 338,
"chars_per_token": 4.470414201183432,
"tokens_per_char": 0.22369291859695567,
"bytes_per_token": 5.186390532544379,
"tokens_per_byte": 0.19281232173416998,
"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": 712,
"chars_per_token": 2.830056179775281,
"tokens_per_char": 0.3533498759305211,
"bytes_per_token": 3.0407303370786516,
"tokens_per_byte": 0.3288683602771363,
"round_trip": true
},
{
"code": "cac",
"autonym": "Koti'",
"spanish_name": "Chuj",
"inali_name": "Chuj",
"english_name": "Chuj",
"samples": 3,
"chars": 1445,
"utf8_bytes": 1614,
"tokens": 489,
"chars_per_token": 2.955010224948875,
"tokens_per_char": 0.3384083044982699,
"bytes_per_token": 3.3006134969325154,
"tokens_per_byte": 0.30297397769516726,
"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": 585,
"chars_per_token": 2.582905982905983,
"tokens_per_char": 0.3871608206485771,
"bytes_per_token": 2.8444444444444446,
"tokens_per_byte": 0.3515625,
"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": 198,
"chars_per_token": 2.54040404040404,
"tokens_per_char": 0.39363817097415504,
"bytes_per_token": 2.54040404040404,
"tokens_per_byte": 0.39363817097415504,
"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": 349,
"chars_per_token": 4.329512893982808,
"tokens_per_char": 0.23097286565188616,
"bytes_per_token": 5.237822349570201,
"tokens_per_byte": 0.19091903719912473,
"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": 539,
"chars_per_token": 2.803339517625232,
"tokens_per_char": 0.356717405691595,
"bytes_per_token": 3.057513914656772,
"tokens_per_byte": 0.3270631067961165,
"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": 351,
"chars_per_token": 4.131054131054131,
"tokens_per_char": 0.24206896551724139,
"bytes_per_token": 4.515669515669516,
"tokens_per_byte": 0.22145110410094637,
"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": 366,
"chars_per_token": 4.128415300546448,
"tokens_per_char": 0.24222369291859697,
"bytes_per_token": 4.371584699453552,
"tokens_per_byte": 0.22875,
"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": 856,
"chars_per_token": 2.942757009345794,
"tokens_per_char": 0.33981738785232235,
"bytes_per_token": 3.2149532710280373,
"tokens_per_byte": 0.311046511627907,
"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": 563,
"chars_per_token": 2.6838365896980463,
"tokens_per_char": 0.37260092653871607,
"bytes_per_token": 3.0,
"tokens_per_byte": 0.3333333333333333,
"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": 475,
"chars_per_token": 3.1810526315789476,
"tokens_per_char": 0.314361350099272,
"bytes_per_token": 3.28,
"tokens_per_byte": 0.3048780487804878,
"round_trip": true
},
{
"code": "klb",
"autonym": "Kiliwa",
"spanish_name": "Kiliwa",
"inali_name": "kiliwa",
"english_name": "Kiliwa",
"samples": 1,
"chars": 503,
"utf8_bytes": 528,
"tokens": 185,
"chars_per_token": 2.718918918918919,
"tokens_per_char": 0.36779324055666,
"bytes_per_token": 2.854054054054054,
"tokens_per_byte": 0.3503787878787879,
"round_trip": true
},
{
"code": "dih",
"autonym": "Kumiai",
"spanish_name": "Kumiai",
"inali_name": "kumiai",
"english_name": "Kumiai",
"samples": 2,
"chars": 1007,
"utf8_bytes": 1048,
"tokens": 337,
"chars_per_token": 2.9881305637982196,
"tokens_per_char": 0.3346573982125124,
"bytes_per_token": 3.1097922848664687,
"tokens_per_byte": 0.32156488549618323,
"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": 624,
"chars_per_token": 4.0368589743589745,
"tokens_per_char": 0.24771734815402938,
"bytes_per_token": 4.519230769230769,
"tokens_per_byte": 0.22127659574468084,
"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": 642,
"chars_per_token": 3.1386292834890965,
"tokens_per_char": 0.3186104218362283,
"bytes_per_token": 3.2445482866043616,
"tokens_per_byte": 0.3082093134901584,
"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": 319,
"chars_per_token": 4.736677115987461,
"tokens_per_char": 0.21111846459298478,
"bytes_per_token": 5.075235109717869,
"tokens_per_byte": 0.19703520691785054,
"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": 605,
"chars_per_token": 4.163636363636364,
"tokens_per_char": 0.24017467248908297,
"bytes_per_token": 4.867768595041323,
"tokens_per_byte": 0.20543293718166383,
"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": 465,
"chars_per_token": 3.249462365591398,
"tokens_per_char": 0.30774321641297153,
"bytes_per_token": 3.3440860215053765,
"tokens_per_byte": 0.2990353697749196,
"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": 328,
"chars_per_token": 4.6067073170731705,
"tokens_per_char": 0.21707478491065518,
"bytes_per_token": 5.189024390243903,
"tokens_per_byte": 0.1927144535840188,
"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": 359,
"chars_per_token": 2.8050139275766015,
"tokens_per_char": 0.35650446871896724,
"bytes_per_token": 2.977715877437326,
"tokens_per_byte": 0.33582787652011226,
"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": 514,
"chars_per_token": 2.9396887159533076,
"tokens_per_char": 0.34017207147584383,
"bytes_per_token": 3.2315175097276265,
"tokens_per_byte": 0.3094521372667068,
"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": 502,
"chars_per_token": 3.00996015936255,
"tokens_per_char": 0.33223031105228323,
"bytes_per_token": 3.358565737051793,
"tokens_per_byte": 0.2977461447212337,
"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": 146,
"chars_per_token": 3.4452054794520546,
"tokens_per_char": 0.29025844930417494,
"bytes_per_token": 3.4726027397260273,
"tokens_per_byte": 0.2879684418145957,
"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": 351,
"chars_per_token": 2.868945868945869,
"tokens_per_char": 0.3485600794438927,
"bytes_per_token": 3.131054131054131,
"tokens_per_byte": 0.31938125568698816,
"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": 188,
"chars_per_token": 2.675531914893617,
"tokens_per_char": 0.37375745526838966,
"bytes_per_token": 2.9574468085106385,
"tokens_per_byte": 0.3381294964028777,
"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": 818,
"chars_per_token": 3.0794621026894866,
"tokens_per_char": 0.32473203652242955,
"bytes_per_token": 3.469437652811736,
"tokens_per_byte": 0.288231148696265,
"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": 744,
"chars_per_token": 2.7083333333333335,
"tokens_per_char": 0.36923076923076925,
"bytes_per_token": 3.1330645161290325,
"tokens_per_byte": 0.31917631917631917,
"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": 405,
"chars_per_token": 2.4864197530864196,
"tokens_per_char": 0.40218470705064546,
"bytes_per_token": 2.8172839506172838,
"tokens_per_byte": 0.3549517966695881,
"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": 830,
"chars_per_token": 2.427710843373494,
"tokens_per_char": 0.4119106699751861,
"bytes_per_token": 3.02289156626506,
"tokens_per_byte": 0.33080908728577124,
"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": 353,
"chars_per_token": 2.8526912181303117,
"tokens_per_char": 0.35054617676266137,
"bytes_per_token": 3.045325779036827,
"tokens_per_byte": 0.3283720930232558,
"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": 235,
"chars_per_token": 2.1404255319148935,
"tokens_per_char": 0.4671968190854871,
"bytes_per_token": 2.4170212765957446,
"tokens_per_byte": 0.4137323943661972,
"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": 704,
"chars_per_token": 2.862215909090909,
"tokens_per_char": 0.34937965260545906,
"bytes_per_token": 3.4332386363636362,
"tokens_per_byte": 0.29127016963177493,
"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": 510,
"chars_per_token": 2.962745098039216,
"tokens_per_char": 0.3375248180013236,
"bytes_per_token": 3.2784313725490195,
"tokens_per_byte": 0.3050239234449761,
"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": 508,
"chars_per_token": 2.9744094488188977,
"tokens_per_char": 0.33620119126406356,
"bytes_per_token": 3.5039370078740157,
"tokens_per_byte": 0.2853932584269663,
"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": 444,
"chars_per_token": 3.4031531531531534,
"tokens_per_char": 0.2938451356717406,
"bytes_per_token": 3.4954954954954953,
"tokens_per_byte": 0.2860824742268041,
"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": 482,
"chars_per_token": 3.1348547717842323,
"tokens_per_char": 0.3189940436796823,
"bytes_per_token": 3.462655601659751,
"tokens_per_byte": 0.28879568603954464,
"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": 664,
"chars_per_token": 3.0346385542168677,
"tokens_per_char": 0.32952853598014886,
"bytes_per_token": 3.2740963855421685,
"tokens_per_byte": 0.30542778288868444,
"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": 177,
"chars_per_token": 2.84180790960452,
"tokens_per_char": 0.3518886679920477,
"bytes_per_token": 3.1016949152542375,
"tokens_per_byte": 0.3224043715846995,
"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": 612,
"chars_per_token": 3.292483660130719,
"tokens_per_char": 0.3037220843672457,
"bytes_per_token": 3.656862745098039,
"tokens_per_byte": 0.2734584450402145,
"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": 584,
"chars_per_token": 3.4503424657534247,
"tokens_per_char": 0.28982630272952853,
"bytes_per_token": 3.743150684931507,
"tokens_per_byte": 0.26715462031107046,
"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": 173,
"chars_per_token": 2.907514450867052,
"tokens_per_char": 0.34393638170974156,
"bytes_per_token": 2.907514450867052,
"tokens_per_byte": 0.34393638170974156,
"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": 508,
"chars_per_token": 3.966535433070866,
"tokens_per_char": 0.2521091811414392,
"bytes_per_token": 4.100393700787402,
"tokens_per_byte": 0.24387902064330294,
"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": 453,
"chars_per_token": 4.448123620309051,
"tokens_per_char": 0.2248138957816377,
"bytes_per_token": 4.448123620309051,
"tokens_per_byte": 0.2248138957816377,
"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": 797,
"chars_per_token": 3.1606022584692597,
"tokens_per_char": 0.3163953949980151,
"bytes_per_token": 3.245922208281054,
"tokens_per_byte": 0.3080788558175493,
"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": 500,
"chars_per_token": 3.022,
"tokens_per_char": 0.3309066843150232,
"bytes_per_token": 3.096,
"tokens_per_byte": 0.32299741602067183,
"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": 625,
"chars_per_token": 3.224,
"tokens_per_char": 0.31017369727047145,
"bytes_per_token": 3.256,
"tokens_per_byte": 0.3071253071253071,
"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": 735,
"chars_per_token": 3.4272108843537414,
"tokens_per_char": 0.29178245335450576,
"bytes_per_token": 3.4748299319727893,
"tokens_per_byte": 0.28778386844166015,
"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": 604,
"chars_per_token": 3.3228476821192054,
"tokens_per_char": 0.3009466865969108,
"bytes_per_token": 3.3543046357615895,
"tokens_per_byte": 0.2981243830207305,
"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": 631,
"chars_per_token": 3.1933438985736924,
"tokens_per_char": 0.31315136476426797,
"bytes_per_token": 3.2012678288431062,
"tokens_per_byte": 0.3123762376237624,
"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": 455,
"chars_per_token": 3.320879120879121,
"tokens_per_char": 0.3011250827266711,
"bytes_per_token": 3.320879120879121,
"tokens_per_byte": 0.3011250827266711,
"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": 481,
"chars_per_token": 3.141372141372141,
"tokens_per_char": 0.3183322303110523,
"bytes_per_token": 3.141372141372141,
"tokens_per_byte": 0.3183322303110523,
"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": 199,
"chars_per_token": 2.507537688442211,
"tokens_per_char": 0.39879759519038077,
"bytes_per_token": 2.71356783919598,
"tokens_per_byte": 0.3685185185185185,
"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": 590,
"chars_per_token": 2.5610169491525423,
"tokens_per_char": 0.39046988749172734,
"bytes_per_token": 2.957627118644068,
"tokens_per_byte": 0.33810888252148996,
"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": 558,
"chars_per_token": 2.707885304659498,
"tokens_per_char": 0.3692918596955658,
"bytes_per_token": 3.2867383512544803,
"tokens_per_byte": 0.3042529989094875,
"round_trip": true
},
{
"code": "ppi",
"autonym": "Paipai",
"spanish_name": "Paipai",
"inali_name": "paipai",
"english_name": "Paipai",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1554,
"tokens": 571,
"chars_per_token": 2.6462346760070052,
"tokens_per_char": 0.37789543348775645,
"bytes_per_token": 2.7215411558669,
"tokens_per_byte": 0.36743886743886744,
"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": 430,
"chars_per_token": 3.513953488372093,
"tokens_per_char": 0.28457974851091994,
"bytes_per_token": 4.0418604651162795,
"tokens_per_byte": 0.2474108170310702,
"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": 518,
"chars_per_token": 2.916988416988417,
"tokens_per_char": 0.342819324950364,
"bytes_per_token": 3.2258687258687258,
"tokens_per_byte": 0.3099940155595452,
"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": 530,
"chars_per_token": 2.8509433962264152,
"tokens_per_char": 0.35076108537392453,
"bytes_per_token": 2.9037735849056605,
"tokens_per_byte": 0.3443794671864847,
"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": 514,
"chars_per_token": 3.9202334630350193,
"tokens_per_char": 0.25508684863523573,
"bytes_per_token": 4.2587548638132295,
"tokens_per_byte": 0.23481041571493833,
"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": 162,
"chars_per_token": 3.1049382716049383,
"tokens_per_char": 0.3220675944333996,
"bytes_per_token": 3.1666666666666665,
"tokens_per_byte": 0.3157894736842105,
"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": 399,
"chars_per_token": 3.7869674185463658,
"tokens_per_char": 0.2640635340833885,
"bytes_per_token": 4.421052631578948,
"tokens_per_byte": 0.2261904761904762,
"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": 526,
"chars_per_token": 2.8726235741444865,
"tokens_per_char": 0.34811383189940437,
"bytes_per_token": 3.1083650190114067,
"tokens_per_byte": 0.3217125382262997,
"round_trip": true
},
{
"code": "mhc",
"autonym": "Mocho'",
"spanish_name": "Motozintleco",
"inali_name": "mocho’",
"english_name": "Mocho",
"samples": 4,
"chars": 2015,
"utf8_bytes": 2021,
"tokens": 655,
"chars_per_token": 3.0763358778625953,
"tokens_per_char": 0.3250620347394541,
"bytes_per_token": 3.0854961832061067,
"tokens_per_byte": 0.32409698169223156,
"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": 546,
"chars_per_token": 2.7673992673992673,
"tokens_per_char": 0.3613500992720053,
"bytes_per_token": 3.1794871794871793,
"tokens_per_byte": 0.31451612903225806,
"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": 248,
"chars_per_token": 6.092741935483871,
"tokens_per_char": 0.16412971542025148,
"bytes_per_token": 6.173387096774194,
"tokens_per_byte": 0.1619856303069889,
"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": 430,
"chars_per_token": 3.513953488372093,
"tokens_per_char": 0.28457974851091994,
"bytes_per_token": 3.8976744186046512,
"tokens_per_byte": 0.256563245823389,
"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": 541,
"chars_per_token": 2.7929759704251387,
"tokens_per_char": 0.35804103242885504,
"bytes_per_token": 2.9297597042513863,
"tokens_per_byte": 0.34132492113564666,
"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": 385,
"chars_per_token": 3.9246753246753245,
"tokens_per_char": 0.25479814692256786,
"bytes_per_token": 4.12987012987013,
"tokens_per_byte": 0.24213836477987422,
"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": 583,
"chars_per_token": 3.456260720411664,
"tokens_per_char": 0.2893300248138958,
"bytes_per_token": 3.5197255574614066,
"tokens_per_byte": 0.28411306042884993,
"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": 522,
"chars_per_token": 3.8601532567049808,
"tokens_per_char": 0.25905707196029776,
"bytes_per_token": 4.021072796934866,
"tokens_per_byte": 0.2486898523106241,
"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": 361,
"chars_per_token": 4.185595567867036,
"tokens_per_char": 0.23891462607544672,
"bytes_per_token": 4.537396121883656,
"tokens_per_byte": 0.22039072039072038,
"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": 366,
"chars_per_token": 2.751366120218579,
"tokens_per_char": 0.3634558093346574,
"bytes_per_token": 3.3224043715846996,
"tokens_per_byte": 0.30098684210526316,
"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": 610,
"chars_per_token": 2.4770491803278687,
"tokens_per_char": 0.40370615486432826,
"bytes_per_token": 2.5737704918032787,
"tokens_per_byte": 0.3885350318471338,
"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": 347,
"chars_per_token": 4.354466858789626,
"tokens_per_char": 0.22964923891462607,
"bytes_per_token": 4.737752161383285,
"tokens_per_byte": 0.2110705596107056,
"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": 449,
"chars_per_token": 2.242761692650334,
"tokens_per_char": 0.4458788480635551,
"bytes_per_token": 2.779510022271715,
"tokens_per_byte": 0.359775641025641,
"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": 630,
"chars_per_token": 2.3984126984126983,
"tokens_per_char": 0.4169424222369292,
"bytes_per_token": 2.6904761904761907,
"tokens_per_byte": 0.37168141592920356,
"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": 659,
"chars_per_token": 2.2928679817905917,
"tokens_per_char": 0.43613500992720056,
"bytes_per_token": 2.9559939301972684,
"tokens_per_byte": 0.33829568788501024,
"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": 483,
"chars_per_token": 4.171842650103519,
"tokens_per_char": 0.23970223325062034,
"bytes_per_token": 4.546583850931677,
"tokens_per_byte": 0.21994535519125682,
"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": 643,
"chars_per_token": 3.1337480559875583,
"tokens_per_char": 0.31910669975186107,
"bytes_per_token": 3.1990668740279937,
"tokens_per_byte": 0.31259115216334465,
"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": 620,
"chars_per_token": 4.062903225806451,
"tokens_per_char": 0.24612941643509328,
"bytes_per_token": 4.164516129032258,
"tokens_per_byte": 0.24012393493415957,
"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": 658,
"chars_per_token": 3.0623100303951367,
"tokens_per_char": 0.32655086848635234,
"bytes_per_token": 3.1732522796352582,
"tokens_per_byte": 0.31513409961685823,
"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": 218,
"chars_per_token": 6.931192660550459,
"tokens_per_char": 0.1442753143613501,
"bytes_per_token": 8.215596330275229,
"tokens_per_byte": 0.12171970965940815,
"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": 783,
"chars_per_token": 3.2171136653895274,
"tokens_per_char": 0.3108376339817388,
"bytes_per_token": 3.5427841634738186,
"tokens_per_byte": 0.2822638788752704,
"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": 207,
"chars_per_token": 4.8647342995169085,
"tokens_per_char": 0.20556107249255212,
"bytes_per_token": 5.323671497584541,
"tokens_per_byte": 0.18784029038112524,
"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": 355,
"chars_per_token": 5.676056338028169,
"tokens_per_char": 0.1761786600496278,
"bytes_per_token": 6.194366197183099,
"tokens_per_byte": 0.16143701682582992,
"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": 504,
"chars_per_token": 3.998015873015873,
"tokens_per_char": 0.2501240694789082,
"bytes_per_token": 4.186507936507937,
"tokens_per_byte": 0.23886255924170616,
"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": 471,
"chars_per_token": 3.208067940552017,
"tokens_per_char": 0.3117140966247518,
"bytes_per_token": 3.5562632696390657,
"tokens_per_byte": 0.28119402985074626,
"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": 504,
"chars_per_token": 2.998015873015873,
"tokens_per_char": 0.33355393778954334,
"bytes_per_token": 3.2142857142857144,
"tokens_per_byte": 0.3111111111111111,
"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": 530,
"chars_per_token": 2.8509433962264152,
"tokens_per_char": 0.35076108537392453,
"bytes_per_token": 2.9981132075471697,
"tokens_per_byte": 0.33354310887350536,
"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": 472,
"chars_per_token": 4.2690677966101696,
"tokens_per_char": 0.23424317617866006,
"bytes_per_token": 4.733050847457627,
"tokens_per_byte": 0.21128021486123547,
"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": 717,
"chars_per_token": 2.810320781032078,
"tokens_per_char": 0.3558312655086849,
"bytes_per_token": 3.1171548117154813,
"tokens_per_byte": 0.3208053691275168,
"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": 375,
"chars_per_token": 4.029333333333334,
"tokens_per_char": 0.24818001323626737,
"bytes_per_token": 4.28,
"tokens_per_byte": 0.2336448598130841,
"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": 568,
"chars_per_token": 2.660211267605634,
"tokens_per_char": 0.3759099933818663,
"bytes_per_token": 3.0140845070422535,
"tokens_per_byte": 0.3317757009345794,
"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": 541,
"chars_per_token": 2.7929759704251387,
"tokens_per_char": 0.35804103242885504,
"bytes_per_token": 2.9390018484288354,
"tokens_per_byte": 0.340251572327044,
"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": 788,
"chars_per_token": 2.5571065989847717,
"tokens_per_char": 0.3910669975186104,
"bytes_per_token": 2.8236040609137056,
"tokens_per_byte": 0.3541573033707865,
"round_trip": true
}
]