tokenizer_64k / evaluation /language_fertility.json
ljcamargo's picture
Upload evaluation/language_fertility.json with huggingface_hub
1b41a75 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": 596,
"chars_per_token": 3.3808724832214767,
"tokens_per_char": 0.29578163771712157,
"bytes_per_token": 4.22986577181208,
"tokens_per_byte": 0.2364141213804046,
"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": 214,
"chars_per_token": 2.350467289719626,
"tokens_per_char": 0.4254473161033797,
"bytes_per_token": 2.8411214953271027,
"tokens_per_byte": 0.3519736842105263,
"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": 364,
"chars_per_token": 2.7664835164835164,
"tokens_per_char": 0.3614697120158888,
"bytes_per_token": 3.206043956043956,
"tokens_per_byte": 0.31191088260497,
"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": 251,
"chars_per_token": 4.01195219123506,
"tokens_per_char": 0.24925521350546176,
"bytes_per_token": 4.059760956175299,
"tokens_per_byte": 0.2463199214916585,
"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": 515,
"chars_per_token": 2.933980582524272,
"tokens_per_char": 0.34083388484447386,
"bytes_per_token": 3.349514563106796,
"tokens_per_byte": 0.2985507246376812,
"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": 676,
"chars_per_token": 2.235207100591716,
"tokens_per_char": 0.44738583719391134,
"bytes_per_token": 2.57396449704142,
"tokens_per_byte": 0.38850574712643676,
"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": 942,
"chars_per_token": 2.1390658174097665,
"tokens_per_char": 0.4674937965260546,
"bytes_per_token": 2.6762208067940554,
"tokens_per_byte": 0.37366124553748514,
"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": 200,
"chars_per_token": 2.515,
"tokens_per_char": 0.3976143141153082,
"bytes_per_token": 2.995,
"tokens_per_byte": 0.333889816360601,
"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": 521,
"chars_per_token": 2.9001919385796544,
"tokens_per_char": 0.3448047650562541,
"bytes_per_token": 3.053742802303263,
"tokens_per_byte": 0.3274670018856065,
"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": 471,
"chars_per_token": 3.208067940552017,
"tokens_per_char": 0.3117140966247518,
"bytes_per_token": 3.721868365180467,
"tokens_per_byte": 0.26868225898459785,
"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": 776,
"chars_per_token": 2.5966494845360826,
"tokens_per_char": 0.38511166253101736,
"bytes_per_token": 2.7899484536082473,
"tokens_per_byte": 0.3584295612009238,
"round_trip": true
},
{
"code": "cac",
"autonym": "Koti'",
"spanish_name": "Chuj",
"inali_name": "Chuj",
"english_name": "Chuj",
"samples": 3,
"chars": 1445,
"utf8_bytes": 1614,
"tokens": 536,
"chars_per_token": 2.6958955223880596,
"tokens_per_char": 0.37093425605536334,
"bytes_per_token": 3.0111940298507465,
"tokens_per_byte": 0.33209417596034696,
"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": 612,
"chars_per_token": 2.468954248366013,
"tokens_per_char": 0.40502978160158837,
"bytes_per_token": 2.718954248366013,
"tokens_per_byte": 0.36778846153846156,
"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": 210,
"chars_per_token": 2.395238095238095,
"tokens_per_char": 0.41749502982107356,
"bytes_per_token": 2.395238095238095,
"tokens_per_byte": 0.41749502982107356,
"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": 469,
"chars_per_token": 3.2217484008528783,
"tokens_per_char": 0.31039046988749175,
"bytes_per_token": 3.8976545842217485,
"tokens_per_byte": 0.2565645514223195,
"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": 577,
"chars_per_token": 2.6187175043327557,
"tokens_per_char": 0.3818663136995367,
"bytes_per_token": 2.856152512998267,
"tokens_per_byte": 0.35012135922330095,
"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": 473,
"chars_per_token": 3.06553911205074,
"tokens_per_char": 0.32620689655172413,
"bytes_per_token": 3.350951374207188,
"tokens_per_byte": 0.29842271293375394,
"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": 465,
"chars_per_token": 3.249462365591398,
"tokens_per_char": 0.30774321641297153,
"bytes_per_token": 3.4408602150537635,
"tokens_per_byte": 0.290625,
"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": 994,
"chars_per_token": 2.53420523138833,
"tokens_per_char": 0.3946010321556173,
"bytes_per_token": 2.7686116700201207,
"tokens_per_byte": 0.36119186046511625,
"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": 605,
"chars_per_token": 2.497520661157025,
"tokens_per_char": 0.400397088021178,
"bytes_per_token": 2.7917355371900827,
"tokens_per_byte": 0.35820011841326227,
"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": 536,
"chars_per_token": 2.8190298507462686,
"tokens_per_char": 0.35473196558570486,
"bytes_per_token": 2.906716417910448,
"tokens_per_byte": 0.34403080872913994,
"round_trip": true
},
{
"code": "klb",
"autonym": "Kiliwa",
"spanish_name": "Kiliwa",
"inali_name": "kiliwa",
"english_name": "Kiliwa",
"samples": 1,
"chars": 503,
"utf8_bytes": 528,
"tokens": 191,
"chars_per_token": 2.6335078534031413,
"tokens_per_char": 0.3797216699801193,
"bytes_per_token": 2.764397905759162,
"tokens_per_byte": 0.36174242424242425,
"round_trip": true
},
{
"code": "dih",
"autonym": "Kumiai",
"spanish_name": "Kumiai",
"inali_name": "kumiai",
"english_name": "Kumiai",
"samples": 2,
"chars": 1007,
"utf8_bytes": 1048,
"tokens": 359,
"chars_per_token": 2.8050139275766015,
"tokens_per_char": 0.35650446871896724,
"bytes_per_token": 2.9192200557103063,
"tokens_per_byte": 0.3425572519083969,
"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": 803,
"chars_per_token": 3.136986301369863,
"tokens_per_char": 0.31877729257641924,
"bytes_per_token": 3.511830635118306,
"tokens_per_byte": 0.2847517730496454,
"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": 699,
"chars_per_token": 2.882689556509299,
"tokens_per_char": 0.34689826302729526,
"bytes_per_token": 2.9799713876967098,
"tokens_per_byte": 0.3355736917906865,
"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": 478,
"chars_per_token": 3.1610878661087867,
"tokens_per_char": 0.31634679020516215,
"bytes_per_token": 3.3870292887029287,
"tokens_per_byte": 0.29524397776405187,
"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": 700,
"chars_per_token": 3.5985714285714288,
"tokens_per_char": 0.277888050813815,
"bytes_per_token": 4.207142857142857,
"tokens_per_byte": 0.23769100169779286,
"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": 548,
"chars_per_token": 2.7572992700729926,
"tokens_per_char": 0.3626737260092654,
"bytes_per_token": 2.8375912408759123,
"tokens_per_byte": 0.352411575562701,
"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": 484,
"chars_per_token": 3.121900826446281,
"tokens_per_char": 0.3203176704169424,
"bytes_per_token": 3.5165289256198347,
"tokens_per_byte": 0.28437132784958874,
"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": 381,
"chars_per_token": 2.643044619422572,
"tokens_per_char": 0.37835153922542203,
"bytes_per_token": 2.8057742782152233,
"tokens_per_byte": 0.35640785781103834,
"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": 540,
"chars_per_token": 2.7981481481481483,
"tokens_per_char": 0.357379219060225,
"bytes_per_token": 3.075925925925926,
"tokens_per_byte": 0.325105358217941,
"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": 527,
"chars_per_token": 2.8671726755218216,
"tokens_per_char": 0.3487756452680344,
"bytes_per_token": 3.1992409867172675,
"tokens_per_byte": 0.3125741399762752,
"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": 156,
"chars_per_token": 3.2243589743589745,
"tokens_per_char": 0.3101391650099404,
"bytes_per_token": 3.25,
"tokens_per_byte": 0.3076923076923077,
"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": 372,
"chars_per_token": 2.706989247311828,
"tokens_per_char": 0.36941410129096325,
"bytes_per_token": 2.954301075268817,
"tokens_per_byte": 0.33848953594176523,
"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": 198,
"chars_per_token": 2.54040404040404,
"tokens_per_char": 0.39363817097415504,
"bytes_per_token": 2.808080808080808,
"tokens_per_byte": 0.35611510791366907,
"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": 899,
"chars_per_token": 2.8020022246941045,
"tokens_per_char": 0.3568876538308853,
"bytes_per_token": 3.156840934371524,
"tokens_per_byte": 0.3167723749119098,
"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": 808,
"chars_per_token": 2.493811881188119,
"tokens_per_char": 0.40099255583126553,
"bytes_per_token": 2.88490099009901,
"tokens_per_byte": 0.34663234663234666,
"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": 448,
"chars_per_token": 2.247767857142857,
"tokens_per_char": 0.4448857994041708,
"bytes_per_token": 2.546875,
"tokens_per_byte": 0.39263803680981596,
"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": 814,
"chars_per_token": 2.4754299754299756,
"tokens_per_char": 0.40397022332506205,
"bytes_per_token": 3.0823095823095823,
"tokens_per_byte": 0.32443204463929853,
"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": 368,
"chars_per_token": 2.7364130434782608,
"tokens_per_char": 0.365441906653426,
"bytes_per_token": 2.921195652173913,
"tokens_per_byte": 0.34232558139534885,
"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": 232,
"chars_per_token": 2.168103448275862,
"tokens_per_char": 0.46123260437375746,
"bytes_per_token": 2.4482758620689653,
"tokens_per_byte": 0.4084507042253521,
"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": 707,
"chars_per_token": 2.85007072135785,
"tokens_per_char": 0.35086848635235734,
"bytes_per_token": 3.4186704384724185,
"tokens_per_byte": 0.2925113777410012,
"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": 519,
"chars_per_token": 2.9113680154142583,
"tokens_per_char": 0.343481138318994,
"bytes_per_token": 3.2215799614643545,
"tokens_per_byte": 0.3104066985645933,
"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": 520,
"chars_per_token": 2.9057692307692307,
"tokens_per_char": 0.3441429516876241,
"bytes_per_token": 3.423076923076923,
"tokens_per_byte": 0.29213483146067415,
"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": 470,
"chars_per_token": 3.2148936170212767,
"tokens_per_char": 0.3110522832561218,
"bytes_per_token": 3.302127659574468,
"tokens_per_byte": 0.30283505154639173,
"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": 512,
"chars_per_token": 2.951171875,
"tokens_per_char": 0.3388484447385837,
"bytes_per_token": 3.259765625,
"tokens_per_byte": 0.3067705212702217,
"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": 701,
"chars_per_token": 2.8744650499286735,
"tokens_per_char": 0.34789081885856077,
"bytes_per_token": 3.101283880171184,
"tokens_per_byte": 0.3224471021159154,
"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": 185,
"chars_per_token": 2.718918918918919,
"tokens_per_char": 0.36779324055666,
"bytes_per_token": 2.9675675675675675,
"tokens_per_byte": 0.33697632058287796,
"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": 648,
"chars_per_token": 3.109567901234568,
"tokens_per_char": 0.3215880893300248,
"bytes_per_token": 3.4537037037037037,
"tokens_per_byte": 0.289544235924933,
"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": 557,
"chars_per_token": 3.6175942549371634,
"tokens_per_char": 0.27642679900744416,
"bytes_per_token": 3.9245960502693,
"tokens_per_byte": 0.25480329368709975,
"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": 174,
"chars_per_token": 2.8908045977011496,
"tokens_per_char": 0.34592445328031807,
"bytes_per_token": 2.8908045977011496,
"tokens_per_byte": 0.34592445328031807,
"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": 579,
"chars_per_token": 3.4801381692573403,
"tokens_per_char": 0.2873449131513648,
"bytes_per_token": 3.597582037996546,
"tokens_per_byte": 0.27796447431589055,
"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": 573,
"chars_per_token": 3.5165794066317626,
"tokens_per_char": 0.2843672456575682,
"bytes_per_token": 3.5165794066317626,
"tokens_per_byte": 0.2843672456575682,
"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": 820,
"chars_per_token": 3.071951219512195,
"tokens_per_char": 0.3255260023818976,
"bytes_per_token": 3.1548780487804877,
"tokens_per_byte": 0.31696946269810594,
"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": 509,
"chars_per_token": 2.968565815324165,
"tokens_per_char": 0.3368630046326936,
"bytes_per_token": 3.0412573673870336,
"tokens_per_byte": 0.32881136950904394,
"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": 640,
"chars_per_token": 3.1484375,
"tokens_per_char": 0.3176178660049628,
"bytes_per_token": 3.1796875,
"tokens_per_byte": 0.3144963144963145,
"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": 742,
"chars_per_token": 3.394878706199461,
"tokens_per_char": 0.2945613338626439,
"bytes_per_token": 3.442048517520216,
"tokens_per_byte": 0.29052466718872355,
"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": 652,
"chars_per_token": 3.0782208588957056,
"tokens_per_char": 0.32486297957149973,
"bytes_per_token": 3.107361963190184,
"tokens_per_byte": 0.32181638696939785,
"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": 691,
"chars_per_token": 2.9160636758321274,
"tokens_per_char": 0.34292803970223323,
"bytes_per_token": 2.923299565846599,
"tokens_per_byte": 0.3420792079207921,
"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": 439,
"chars_per_token": 3.441913439635535,
"tokens_per_char": 0.29053606882859034,
"bytes_per_token": 3.441913439635535,
"tokens_per_byte": 0.29053606882859034,
"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": 515,
"chars_per_token": 2.933980582524272,
"tokens_per_char": 0.34083388484447386,
"bytes_per_token": 2.933980582524272,
"tokens_per_byte": 0.34083388484447386,
"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": 210,
"chars_per_token": 2.376190476190476,
"tokens_per_char": 0.42084168336673344,
"bytes_per_token": 2.5714285714285716,
"tokens_per_byte": 0.3888888888888889,
"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": 592,
"chars_per_token": 2.552364864864865,
"tokens_per_char": 0.39179351422898745,
"bytes_per_token": 2.947635135135135,
"tokens_per_byte": 0.33925501432664756,
"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": 590,
"chars_per_token": 2.5610169491525423,
"tokens_per_char": 0.39046988749172734,
"bytes_per_token": 3.1084745762711865,
"tokens_per_byte": 0.321701199563795,
"round_trip": true
},
{
"code": "ppi",
"autonym": "Paipai",
"spanish_name": "Paipai",
"inali_name": "paipai",
"english_name": "Paipai",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1554,
"tokens": 602,
"chars_per_token": 2.509966777408638,
"tokens_per_char": 0.3984116479152879,
"bytes_per_token": 2.5813953488372094,
"tokens_per_byte": 0.38738738738738737,
"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": 540,
"chars_per_token": 2.7981481481481483,
"tokens_per_char": 0.357379219060225,
"bytes_per_token": 3.2185185185185183,
"tokens_per_byte": 0.31070195627157654,
"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": 576,
"chars_per_token": 2.623263888888889,
"tokens_per_char": 0.3812045003309067,
"bytes_per_token": 2.9010416666666665,
"tokens_per_byte": 0.34470377019748655,
"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": 556,
"chars_per_token": 2.7176258992805757,
"tokens_per_char": 0.3679682329583058,
"bytes_per_token": 2.7679856115107913,
"tokens_per_byte": 0.3612735542560104,
"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": 676,
"chars_per_token": 2.980769230769231,
"tokens_per_char": 0.33548387096774196,
"bytes_per_token": 3.2381656804733727,
"tokens_per_byte": 0.30881681132937416,
"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": 168,
"chars_per_token": 2.994047619047619,
"tokens_per_char": 0.33399602385685884,
"bytes_per_token": 3.0535714285714284,
"tokens_per_byte": 0.32748538011695905,
"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": 550,
"chars_per_token": 2.747272727272727,
"tokens_per_char": 0.3639973527465255,
"bytes_per_token": 3.207272727272727,
"tokens_per_byte": 0.31179138321995464,
"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": 565,
"chars_per_token": 2.674336283185841,
"tokens_per_char": 0.3739245532759762,
"bytes_per_token": 2.893805309734513,
"tokens_per_byte": 0.345565749235474,
"round_trip": true
},
{
"code": "mhc",
"autonym": "Mocho'",
"spanish_name": "Motozintleco",
"inali_name": "mocho’",
"english_name": "Mocho",
"samples": 4,
"chars": 2015,
"utf8_bytes": 2021,
"tokens": 596,
"chars_per_token": 3.3808724832214767,
"tokens_per_char": 0.29578163771712157,
"bytes_per_token": 3.390939597315436,
"tokens_per_byte": 0.29490351311232066,
"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": 608,
"chars_per_token": 2.4851973684210527,
"tokens_per_char": 0.40238252812706815,
"bytes_per_token": 2.8552631578947367,
"tokens_per_byte": 0.35023041474654376,
"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": 413,
"chars_per_token": 3.6585956416464893,
"tokens_per_char": 0.27332892124420916,
"bytes_per_token": 3.7070217917675543,
"tokens_per_byte": 0.2697583278902678,
"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": 548,
"chars_per_token": 2.7572992700729926,
"tokens_per_char": 0.3626737260092654,
"bytes_per_token": 3.0583941605839415,
"tokens_per_byte": 0.3269689737470167,
"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": 587,
"chars_per_token": 2.574105621805792,
"tokens_per_char": 0.3884844473858372,
"bytes_per_token": 2.700170357751278,
"tokens_per_byte": 0.37034700315457414,
"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": 513,
"chars_per_token": 2.94541910331384,
"tokens_per_char": 0.33951025810721375,
"bytes_per_token": 3.0994152046783627,
"tokens_per_byte": 0.32264150943396225,
"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": 603,
"chars_per_token": 3.341625207296849,
"tokens_per_char": 0.2992555831265509,
"bytes_per_token": 3.4029850746268657,
"tokens_per_byte": 0.29385964912280704,
"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": 598,
"chars_per_token": 3.369565217391304,
"tokens_per_char": 0.2967741935483871,
"bytes_per_token": 3.5100334448160537,
"tokens_per_byte": 0.2848975702715579,
"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": 509,
"chars_per_token": 2.968565815324165,
"tokens_per_char": 0.3368630046326936,
"bytes_per_token": 3.218074656188605,
"tokens_per_byte": 0.31074481074481075,
"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": 656,
"chars_per_token": 2.3033536585365852,
"tokens_per_char": 0.43414956982131037,
"bytes_per_token": 2.393292682926829,
"tokens_per_byte": 0.4178343949044586,
"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": 491,
"chars_per_token": 3.0773930753564156,
"tokens_per_char": 0.3249503639973527,
"bytes_per_token": 3.3482688391038695,
"tokens_per_byte": 0.298661800486618,
"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": 485,
"chars_per_token": 2.0762886597938146,
"tokens_per_char": 0.4816285998013903,
"bytes_per_token": 2.57319587628866,
"tokens_per_byte": 0.3886217948717949,
"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": 690,
"chars_per_token": 2.189855072463768,
"tokens_per_char": 0.456651224354732,
"bytes_per_token": 2.4565217391304346,
"tokens_per_byte": 0.40707964601769914,
"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": 709,
"chars_per_token": 2.1311706629055007,
"tokens_per_char": 0.4692256783587028,
"bytes_per_token": 2.7475317348378,
"tokens_per_byte": 0.3639630390143737,
"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": 647,
"chars_per_token": 3.114374034003091,
"tokens_per_char": 0.3210918114143921,
"bytes_per_token": 3.394126738794436,
"tokens_per_byte": 0.2946265938069217,
"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": 233,
"chars_per_token": 2.1587982832618025,
"tokens_per_char": 0.46322067594433397,
"bytes_per_token": 2.167381974248927,
"tokens_per_byte": 0.4613861386138614,
"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": 683,
"chars_per_token": 2.950219619326501,
"tokens_per_char": 0.3389578163771712,
"bytes_per_token": 3.0117130307467055,
"tokens_per_byte": 0.332036947010209,
"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": 717,
"chars_per_token": 3.513249651324965,
"tokens_per_char": 0.2846367606192934,
"bytes_per_token": 3.601115760111576,
"tokens_per_byte": 0.27769171185127806,
"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": 651,
"chars_per_token": 3.0952380952380953,
"tokens_per_char": 0.3230769230769231,
"bytes_per_token": 3.207373271889401,
"tokens_per_byte": 0.3117816091954023,
"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": 421,
"chars_per_token": 3.5890736342042757,
"tokens_per_char": 0.2786234281932495,
"bytes_per_token": 4.254156769596199,
"tokens_per_byte": 0.2350642099385818,
"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": 901,
"chars_per_token": 2.7957824639289677,
"tokens_per_char": 0.35768161969035334,
"bytes_per_token": 3.078801331853496,
"tokens_per_byte": 0.32480173035328047,
"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": 282,
"chars_per_token": 3.5709219858156027,
"tokens_per_char": 0.2800397219463754,
"bytes_per_token": 3.9078014184397163,
"tokens_per_byte": 0.2558983666061706,
"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": 531,
"chars_per_token": 3.7947269303201505,
"tokens_per_char": 0.26352357320099257,
"bytes_per_token": 4.141242937853107,
"tokens_per_byte": 0.24147339699863574,
"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": 642,
"chars_per_token": 3.1386292834890965,
"tokens_per_char": 0.3186104218362283,
"bytes_per_token": 3.2866043613707165,
"tokens_per_byte": 0.3042654028436019,
"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": 503,
"chars_per_token": 3.003976143141153,
"tokens_per_char": 0.3328921244209133,
"bytes_per_token": 3.3300198807157058,
"tokens_per_byte": 0.30029850746268655,
"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": 521,
"chars_per_token": 2.9001919385796544,
"tokens_per_char": 0.3448047650562541,
"bytes_per_token": 3.109404990403071,
"tokens_per_byte": 0.3216049382716049,
"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": 558,
"chars_per_token": 2.707885304659498,
"tokens_per_char": 0.3692918596955658,
"bytes_per_token": 2.847670250896057,
"tokens_per_byte": 0.35116425424795467,
"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": 583,
"chars_per_token": 3.456260720411664,
"tokens_per_char": 0.2893300248138958,
"bytes_per_token": 3.8319039451114922,
"tokens_per_byte": 0.26096687555953446,
"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": 773,
"chars_per_token": 2.606727037516171,
"tokens_per_char": 0.38362282878411913,
"bytes_per_token": 2.891332470892626,
"tokens_per_byte": 0.3458612975391499,
"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": 514,
"chars_per_token": 2.9396887159533076,
"tokens_per_char": 0.34017207147584383,
"bytes_per_token": 3.122568093385214,
"tokens_per_byte": 0.3202492211838006,
"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": 600,
"chars_per_token": 2.5183333333333335,
"tokens_per_char": 0.3970880211780278,
"bytes_per_token": 2.8533333333333335,
"tokens_per_byte": 0.35046728971962615,
"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": 553,
"chars_per_token": 2.732368896925859,
"tokens_per_char": 0.36598279285241564,
"bytes_per_token": 2.875226039783002,
"tokens_per_byte": 0.34779874213836476,
"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": 784,
"chars_per_token": 2.57015306122449,
"tokens_per_char": 0.3890818858560794,
"bytes_per_token": 2.8380102040816326,
"tokens_per_byte": 0.35235955056179774,
"round_trip": true
}
]