tokenizer_256K / evaluation /language_fertility.json
ljcamargo's picture
Upload evaluation/language_fertility.json with huggingface_hub
a4b2ef1 verified
Raw
History Blame Contribute Delete
48.7 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": 469,
"chars_per_token": 4.29637526652452,
"tokens_per_char": 0.2327543424317618,
"bytes_per_token": 5.3752665245202556,
"tokens_per_byte": 0.18603728679095596,
"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": 189,
"chars_per_token": 2.6613756613756614,
"tokens_per_char": 0.3757455268389662,
"bytes_per_token": 3.2169312169312168,
"tokens_per_byte": 0.31085526315789475,
"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": 330,
"chars_per_token": 3.0515151515151517,
"tokens_per_char": 0.32770605759682225,
"bytes_per_token": 3.536363636363636,
"tokens_per_byte": 0.2827763496143959,
"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": 188,
"chars_per_token": 5.3563829787234045,
"tokens_per_char": 0.18669314796425024,
"bytes_per_token": 5.420212765957447,
"tokens_per_byte": 0.1844946025515211,
"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": 424,
"chars_per_token": 3.563679245283019,
"tokens_per_char": 0.28060886829913967,
"bytes_per_token": 4.068396226415095,
"tokens_per_byte": 0.24579710144927536,
"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": 831,
"chars_per_token": 2.424789410348977,
"tokens_per_char": 0.41240694789081883,
"bytes_per_token": 3.033694344163658,
"tokens_per_byte": 0.32963109877032926,
"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": 184,
"chars_per_token": 2.733695652173913,
"tokens_per_char": 0.3658051689860835,
"bytes_per_token": 3.255434782608696,
"tokens_per_byte": 0.3071786310517529,
"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": 471,
"chars_per_token": 3.208067940552017,
"tokens_per_char": 0.3117140966247518,
"bytes_per_token": 3.3779193205944797,
"tokens_per_byte": 0.2960402262727844,
"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": 367,
"chars_per_token": 4.11716621253406,
"tokens_per_char": 0.242885506287227,
"bytes_per_token": 4.776566757493188,
"tokens_per_byte": 0.20935539075869938,
"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": 659,
"chars_per_token": 3.0576631259484066,
"tokens_per_char": 0.3270471464019851,
"bytes_per_token": 3.285280728376328,
"tokens_per_byte": 0.3043879907621247,
"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": 564,
"chars_per_token": 2.6790780141843973,
"tokens_per_char": 0.37326273990734615,
"bytes_per_token": 2.950354609929078,
"tokens_per_byte": 0.3389423076923077,
"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": 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": "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": 405,
"chars_per_token": 3.730864197530864,
"tokens_per_char": 0.2680344142951688,
"bytes_per_token": 4.51358024691358,
"tokens_per_byte": 0.2215536105032823,
"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": 501,
"chars_per_token": 3.0159680638722555,
"tokens_per_char": 0.3315684976836532,
"bytes_per_token": 3.2894211576846306,
"tokens_per_byte": 0.30400485436893204,
"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": 373,
"chars_per_token": 4.050938337801608,
"tokens_per_char": 0.2468563864990073,
"bytes_per_token": 4.289544235924933,
"tokens_per_byte": 0.233125,
"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": 843,
"chars_per_token": 2.9881376037959666,
"tokens_per_char": 0.33465660976578004,
"bytes_per_token": 3.264531435349941,
"tokens_per_byte": 0.30632267441860467,
"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": 522,
"chars_per_token": 2.8946360153256707,
"tokens_per_char": 0.3454665784248842,
"bytes_per_token": 3.235632183908046,
"tokens_per_byte": 0.30905861456483125,
"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": 467,
"chars_per_token": 3.235546038543897,
"tokens_per_char": 0.30906684315023164,
"bytes_per_token": 3.336188436830835,
"tokens_per_byte": 0.29974326059050066,
"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": 306,
"chars_per_token": 3.2908496732026142,
"tokens_per_char": 0.3038728897715988,
"bytes_per_token": 3.4248366013071894,
"tokens_per_byte": 0.2919847328244275,
"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": 670,
"chars_per_token": 3.7597014925373133,
"tokens_per_char": 0.26597856292179434,
"bytes_per_token": 4.208955223880597,
"tokens_per_byte": 0.2375886524822695,
"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": 600,
"chars_per_token": 3.3583333333333334,
"tokens_per_char": 0.2977667493796526,
"bytes_per_token": 3.4716666666666667,
"tokens_per_byte": 0.28804608737397985,
"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": 374,
"chars_per_token": 4.040106951871658,
"tokens_per_char": 0.24751819986763732,
"bytes_per_token": 4.328877005347594,
"tokens_per_byte": 0.23100679431747992,
"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": 563,
"chars_per_token": 4.474245115452931,
"tokens_per_char": 0.22350138944025408,
"bytes_per_token": 5.230905861456483,
"tokens_per_byte": 0.19117147707979626,
"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": 467,
"chars_per_token": 3.235546038543897,
"tokens_per_char": 0.30906684315023164,
"bytes_per_token": 3.329764453961456,
"tokens_per_byte": 0.30032154340836015,
"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": 483,
"chars_per_token": 3.1283643892339543,
"tokens_per_char": 0.3196558570483124,
"bytes_per_token": 3.4389233954451344,
"tokens_per_byte": 0.29078868151715836,
"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": 459,
"chars_per_token": 3.291938997821351,
"tokens_per_char": 0.30377233620119126,
"bytes_per_token": 3.673202614379085,
"tokens_per_byte": 0.2722419928825623,
"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": 133,
"chars_per_token": 3.781954887218045,
"tokens_per_char": 0.2644135188866799,
"bytes_per_token": 3.81203007518797,
"tokens_per_byte": 0.26232741617357,
"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": 332,
"chars_per_token": 3.033132530120482,
"tokens_per_char": 0.32969215491559084,
"bytes_per_token": 3.3102409638554215,
"tokens_per_byte": 0.3020928116469518,
"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": 763,
"chars_per_token": 3.3014416775884667,
"tokens_per_char": 0.30289797538705837,
"bytes_per_token": 3.7195281782437744,
"tokens_per_byte": 0.26885130373502464,
"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": 402,
"chars_per_token": 2.5049751243781095,
"tokens_per_char": 0.39920556107249255,
"bytes_per_token": 2.8383084577114426,
"tokens_per_byte": 0.3523225241016652,
"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": 674,
"chars_per_token": 2.9896142433234423,
"tokens_per_char": 0.33449131513647645,
"bytes_per_token": 3.722551928783383,
"tokens_per_byte": 0.26863292148266243,
"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": 307,
"chars_per_token": 3.2801302931596092,
"tokens_per_char": 0.30486593843098314,
"bytes_per_token": 3.501628664495114,
"tokens_per_byte": 0.2855813953488372,
"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": 210,
"chars_per_token": 2.395238095238095,
"tokens_per_char": 0.41749502982107356,
"bytes_per_token": 2.704761904761905,
"tokens_per_byte": 0.36971830985915494,
"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": 614,
"chars_per_token": 3.281758957654723,
"tokens_per_char": 0.3047146401985112,
"bytes_per_token": 3.936482084690554,
"tokens_per_byte": 0.2540339263549855,
"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": 445,
"chars_per_token": 3.3955056179775283,
"tokens_per_char": 0.2945069490403706,
"bytes_per_token": 3.757303370786517,
"tokens_per_byte": 0.2661483253588517,
"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": 404,
"chars_per_token": 3.74009900990099,
"tokens_per_char": 0.2673726009265387,
"bytes_per_token": 3.8415841584158414,
"tokens_per_byte": 0.2603092783505155,
"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": 442,
"chars_per_token": 3.418552036199095,
"tokens_per_char": 0.2925215089344805,
"bytes_per_token": 3.776018099547511,
"tokens_per_byte": 0.2648292390653086,
"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": 169,
"chars_per_token": 2.9763313609467454,
"tokens_per_char": 0.3359840954274354,
"bytes_per_token": 3.2485207100591715,
"tokens_per_byte": 0.30783242258652094,
"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": 537,
"chars_per_token": 3.7523277467411544,
"tokens_per_char": 0.2665012406947891,
"bytes_per_token": 4.167597765363128,
"tokens_per_byte": 0.23994638069705093,
"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": 464,
"chars_per_token": 4.342672413793103,
"tokens_per_char": 0.23027295285359803,
"bytes_per_token": 4.711206896551724,
"tokens_per_byte": 0.21225983531564502,
"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": 140,
"chars_per_token": 3.592857142857143,
"tokens_per_char": 0.2783300198807157,
"bytes_per_token": 3.592857142857143,
"tokens_per_byte": 0.2783300198807157,
"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": 459,
"chars_per_token": 4.389978213507625,
"tokens_per_char": 0.22779156327543423,
"bytes_per_token": 4.538126361655773,
"tokens_per_byte": 0.22035525684109458,
"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": 455,
"chars_per_token": 4.428571428571429,
"tokens_per_char": 0.22580645161290322,
"bytes_per_token": 4.428571428571429,
"tokens_per_byte": 0.22580645161290322,
"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": 679,
"chars_per_token": 3.7098674521354935,
"tokens_per_char": 0.2695514092894006,
"bytes_per_token": 3.8100147275405005,
"tokens_per_byte": 0.26246617703904135,
"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": 445,
"chars_per_token": 3.3955056179775283,
"tokens_per_char": 0.2945069490403706,
"bytes_per_token": 3.4786516853932583,
"tokens_per_byte": 0.2874677002583979,
"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": 577,
"chars_per_token": 3.4783362218370883,
"tokens_per_char": 0.28749377179870456,
"bytes_per_token": 3.511265164644714,
"tokens_per_byte": 0.28479763079960513,
"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": 587,
"chars_per_token": 3.4327086882453153,
"tokens_per_char": 0.2913151364764268,
"bytes_per_token": 3.4412265758091993,
"tokens_per_byte": 0.2905940594059406,
"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": 450,
"chars_per_token": 3.3577777777777778,
"tokens_per_char": 0.29781601588352086,
"bytes_per_token": 3.3577777777777778,
"tokens_per_byte": 0.29781601588352086,
"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": 176,
"chars_per_token": 2.835227272727273,
"tokens_per_char": 0.3527054108216433,
"bytes_per_token": 3.0681818181818183,
"tokens_per_byte": 0.32592592592592595,
"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": 519,
"chars_per_token": 2.9113680154142583,
"tokens_per_char": 0.343481138318994,
"bytes_per_token": 3.3622350674373798,
"tokens_per_byte": 0.2974212034383954,
"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": 522,
"chars_per_token": 2.8946360153256707,
"tokens_per_char": 0.3454665784248842,
"bytes_per_token": 3.5134099616858236,
"tokens_per_byte": 0.2846237731733915,
"round_trip": true
},
{
"code": "ppi",
"autonym": "Paipai",
"spanish_name": "Paipai",
"inali_name": "paipai",
"english_name": "Paipai",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1554,
"tokens": 528,
"chars_per_token": 2.8617424242424243,
"tokens_per_char": 0.3494374586366645,
"bytes_per_token": 2.9431818181818183,
"tokens_per_byte": 0.33976833976833976,
"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": 491,
"chars_per_token": 3.0773930753564156,
"tokens_per_char": 0.3249503639973527,
"bytes_per_token": 3.134419551934827,
"tokens_per_byte": 0.3190383365821962,
"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": 551,
"chars_per_token": 3.6569872958257714,
"tokens_per_char": 0.27344913151364764,
"bytes_per_token": 3.972776769509982,
"tokens_per_byte": 0.2517131110095934,
"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": 155,
"chars_per_token": 3.2451612903225806,
"tokens_per_char": 0.3081510934393638,
"bytes_per_token": 3.3096774193548386,
"tokens_per_byte": 0.30214424951267055,
"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": 438,
"chars_per_token": 3.449771689497717,
"tokens_per_char": 0.2898742554599603,
"bytes_per_token": 4.027397260273973,
"tokens_per_byte": 0.24829931972789115,
"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": 477,
"chars_per_token": 3.1677148846960166,
"tokens_per_char": 0.31568497683653207,
"bytes_per_token": 3.4276729559748427,
"tokens_per_byte": 0.29174311926605506,
"round_trip": true
},
{
"code": "mhc",
"autonym": "Mocho'",
"spanish_name": "Motozintleco",
"inali_name": "mocho’",
"english_name": "Mocho",
"samples": 4,
"chars": 2015,
"utf8_bytes": 2021,
"tokens": 469,
"chars_per_token": 4.29637526652452,
"tokens_per_char": 0.2327543424317618,
"bytes_per_token": 4.309168443496802,
"tokens_per_byte": 0.23206333498268183,
"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": 517,
"chars_per_token": 2.9226305609284333,
"tokens_per_char": 0.34215751158173396,
"bytes_per_token": 3.357833655705996,
"tokens_per_byte": 0.2978110599078341,
"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": 297,
"chars_per_token": 5.087542087542087,
"tokens_per_char": 0.19655857048312375,
"bytes_per_token": 5.154882154882155,
"tokens_per_byte": 0.19399085564990204,
"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": 469,
"chars_per_token": 3.2217484008528783,
"tokens_per_char": 0.31039046988749175,
"bytes_per_token": 3.5735607675906182,
"tokens_per_byte": 0.2798329355608592,
"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": 508,
"chars_per_token": 2.9744094488188977,
"tokens_per_char": 0.33620119126406356,
"bytes_per_token": 3.12007874015748,
"tokens_per_byte": 0.3205047318611987,
"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": 411,
"chars_per_token": 3.67639902676399,
"tokens_per_char": 0.27200529450694905,
"bytes_per_token": 3.8686131386861313,
"tokens_per_byte": 0.25849056603773585,
"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": 520,
"chars_per_token": 3.875,
"tokens_per_char": 0.25806451612903225,
"bytes_per_token": 3.9461538461538463,
"tokens_per_byte": 0.253411306042885,
"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": 489,
"chars_per_token": 4.120654396728017,
"tokens_per_char": 0.24267990074441687,
"bytes_per_token": 4.292433537832311,
"tokens_per_byte": 0.2329680800381134,
"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": 418,
"chars_per_token": 3.6148325358851676,
"tokens_per_char": 0.27663798808735934,
"bytes_per_token": 3.9186602870813396,
"tokens_per_byte": 0.25518925518925517,
"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": 295,
"chars_per_token": 3.4135593220338984,
"tokens_per_char": 0.2929493545183714,
"bytes_per_token": 4.122033898305085,
"tokens_per_byte": 0.24259868421052633,
"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": 579,
"chars_per_token": 2.609671848013817,
"tokens_per_char": 0.3831899404367968,
"bytes_per_token": 2.7115716753022454,
"tokens_per_byte": 0.3687898089171974,
"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": 396,
"chars_per_token": 3.8156565656565657,
"tokens_per_char": 0.26207809397749837,
"bytes_per_token": 4.151515151515151,
"tokens_per_byte": 0.24087591240875914,
"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": 591,
"chars_per_token": 2.55668358714044,
"tokens_per_char": 0.39113170086035737,
"bytes_per_token": 2.8680203045685277,
"tokens_per_byte": 0.3486725663716814,
"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": 629,
"chars_per_token": 2.4022257551669317,
"tokens_per_char": 0.41628060886829915,
"bytes_per_token": 3.09697933227345,
"tokens_per_byte": 0.3228952772073922,
"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": 207,
"chars_per_token": 2.429951690821256,
"tokens_per_char": 0.4115308151093439,
"bytes_per_token": 2.4396135265700485,
"tokens_per_byte": 0.4099009900990099,
"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": 573,
"chars_per_token": 4.396160558464223,
"tokens_per_char": 0.2274712187375943,
"bytes_per_token": 4.506108202443281,
"tokens_per_byte": 0.22192099147947328,
"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": 574,
"chars_per_token": 3.510452961672474,
"tokens_per_char": 0.284863523573201,
"bytes_per_token": 3.637630662020906,
"tokens_per_byte": 0.27490421455938696,
"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": 296,
"chars_per_token": 5.10472972972973,
"tokens_per_char": 0.19589675711449372,
"bytes_per_token": 6.050675675675675,
"tokens_per_byte": 0.1652707984366276,
"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": 234,
"chars_per_token": 4.303418803418803,
"tokens_per_char": 0.2323733862959285,
"bytes_per_token": 4.7094017094017095,
"tokens_per_byte": 0.21234119782214156,
"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": 414,
"chars_per_token": 4.867149758454106,
"tokens_per_char": 0.2054590570719603,
"bytes_per_token": 5.311594202898551,
"tokens_per_byte": 0.1882673942701228,
"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": 528,
"chars_per_token": 3.816287878787879,
"tokens_per_char": 0.2620347394540943,
"bytes_per_token": 3.996212121212121,
"tokens_per_byte": 0.2502369668246445,
"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": 444,
"chars_per_token": 3.4031531531531534,
"tokens_per_char": 0.2938451356717406,
"bytes_per_token": 3.7725225225225225,
"tokens_per_byte": 0.2650746268656716,
"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": 463,
"chars_per_token": 3.263498920086393,
"tokens_per_char": 0.3064195896757114,
"bytes_per_token": 3.4989200863930887,
"tokens_per_byte": 0.2858024691358025,
"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": 504,
"chars_per_token": 2.998015873015873,
"tokens_per_char": 0.33355393778954334,
"bytes_per_token": 3.1527777777777777,
"tokens_per_byte": 0.31718061674008813,
"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": 487,
"chars_per_token": 4.137577002053388,
"tokens_per_char": 0.24168734491315136,
"bytes_per_token": 4.587268993839836,
"tokens_per_byte": 0.2179946284691137,
"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": 662,
"chars_per_token": 3.0438066465256797,
"tokens_per_char": 0.32853598014888336,
"bytes_per_token": 3.376132930513595,
"tokens_per_byte": 0.29619686800894857,
"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": 422,
"chars_per_token": 3.580568720379147,
"tokens_per_char": 0.27928524156187956,
"bytes_per_token": 3.8033175355450237,
"tokens_per_byte": 0.26292834890965733,
"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": 524,
"chars_per_token": 2.883587786259542,
"tokens_per_char": 0.34679020516214426,
"bytes_per_token": 3.267175572519084,
"tokens_per_byte": 0.3060747663551402,
"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": 655,
"chars_per_token": 3.0763358778625953,
"tokens_per_char": 0.3250620347394541,
"bytes_per_token": 3.3969465648854964,
"tokens_per_byte": 0.2943820224719101,
"round_trip": true
}
]