tokenizer_test4 / evaluation /language_fertility.json
ljcamargo's picture
Upload evaluation/language_fertility.json with huggingface_hub
26c1184 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": 467,
"chars_per_token": 4.314775160599572,
"tokens_per_char": 0.2317617866004963,
"bytes_per_token": 5.398286937901499,
"tokens_per_byte": 0.18524395081316938,
"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": 191,
"chars_per_token": 2.6335078534031413,
"tokens_per_char": 0.3797216699801193,
"bytes_per_token": 3.183246073298429,
"tokens_per_byte": 0.31414473684210525,
"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": 323,
"chars_per_token": 3.1176470588235294,
"tokens_per_char": 0.32075471698113206,
"bytes_per_token": 3.613003095975232,
"tokens_per_byte": 0.27677806341045413,
"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": 187,
"chars_per_token": 5.385026737967914,
"tokens_per_char": 0.18570009930486595,
"bytes_per_token": 5.449197860962567,
"tokens_per_byte": 0.18351324828263002,
"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": 416,
"chars_per_token": 3.6322115384615383,
"tokens_per_char": 0.2753143613500993,
"bytes_per_token": 4.146634615384615,
"tokens_per_byte": 0.24115942028985507,
"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": 622,
"chars_per_token": 2.4292604501607715,
"tokens_per_char": 0.4116479152878888,
"bytes_per_token": 2.797427652733119,
"tokens_per_byte": 0.35747126436781607,
"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": 880,
"chars_per_token": 2.289772727272727,
"tokens_per_char": 0.43672456575682383,
"bytes_per_token": 2.8647727272727272,
"tokens_per_byte": 0.3490678302261008,
"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": 457,
"chars_per_token": 3.3063457330415753,
"tokens_per_char": 0.30244870946393115,
"bytes_per_token": 3.4814004376367613,
"tokens_per_byte": 0.2872407291011942,
"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": 360,
"chars_per_token": 4.197222222222222,
"tokens_per_char": 0.23825281270681667,
"bytes_per_token": 4.8694444444444445,
"tokens_per_byte": 0.2053622361665716,
"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": 695,
"chars_per_token": 2.8992805755395685,
"tokens_per_char": 0.34491315136476425,
"bytes_per_token": 3.115107913669065,
"tokens_per_byte": 0.3210161662817552,
"round_trip": true
},
{
"code": "cac",
"autonym": "Koti'",
"spanish_name": "Chuj",
"inali_name": "Chuj",
"english_name": "Chuj",
"samples": 3,
"chars": 1445,
"utf8_bytes": 1614,
"tokens": 457,
"chars_per_token": 3.1619256017505473,
"tokens_per_char": 0.31626297577854673,
"bytes_per_token": 3.5317286652078774,
"tokens_per_byte": 0.28314745972738536,
"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": 576,
"chars_per_token": 2.623263888888889,
"tokens_per_char": 0.3812045003309067,
"bytes_per_token": 2.888888888888889,
"tokens_per_byte": 0.34615384615384615,
"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": 176,
"chars_per_token": 2.8579545454545454,
"tokens_per_char": 0.3499005964214712,
"bytes_per_token": 2.8579545454545454,
"tokens_per_byte": 0.3499005964214712,
"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": 398,
"chars_per_token": 3.7964824120603016,
"tokens_per_char": 0.2634017207147584,
"bytes_per_token": 4.592964824120603,
"tokens_per_byte": 0.21772428884026257,
"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": 520,
"chars_per_token": 2.9057692307692307,
"tokens_per_char": 0.3441429516876241,
"bytes_per_token": 3.169230769230769,
"tokens_per_byte": 0.3155339805825243,
"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": 381,
"chars_per_token": 3.8057742782152233,
"tokens_per_char": 0.26275862068965516,
"bytes_per_token": 4.16010498687664,
"tokens_per_byte": 0.24037854889589905,
"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": 359,
"chars_per_token": 4.20891364902507,
"tokens_per_char": 0.23759099933818664,
"bytes_per_token": 4.456824512534819,
"tokens_per_byte": 0.224375,
"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": 821,
"chars_per_token": 3.0682095006090133,
"tokens_per_char": 0.3259229853116316,
"bytes_per_token": 3.3520097442143726,
"tokens_per_byte": 0.298328488372093,
"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": 521,
"chars_per_token": 2.9001919385796544,
"tokens_per_char": 0.3448047650562541,
"bytes_per_token": 3.2418426103646834,
"tokens_per_byte": 0.30846654825340436,
"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": 463,
"chars_per_token": 3.263498920086393,
"tokens_per_char": 0.3064195896757114,
"bytes_per_token": 3.365010799136069,
"tokens_per_byte": 0.29717586649550704,
"round_trip": true
},
{
"code": "klb",
"autonym": "Kiliwa",
"spanish_name": "Kiliwa",
"inali_name": "kiliwa",
"english_name": "Kiliwa",
"samples": 1,
"chars": 503,
"utf8_bytes": 528,
"tokens": 173,
"chars_per_token": 2.907514450867052,
"tokens_per_char": 0.34393638170974156,
"bytes_per_token": 3.052023121387283,
"tokens_per_byte": 0.32765151515151514,
"round_trip": true
},
{
"code": "dih",
"autonym": "Kumiai",
"spanish_name": "Kumiai",
"inali_name": "kumiai",
"english_name": "Kumiai",
"samples": 2,
"chars": 1007,
"utf8_bytes": 1048,
"tokens": 305,
"chars_per_token": 3.301639344262295,
"tokens_per_char": 0.3028798411122145,
"bytes_per_token": 3.4360655737704917,
"tokens_per_byte": 0.29103053435114506,
"round_trip": true
},
{
"code": "lac",
"autonym": "Jach-t'aan",
"spanish_name": "Lacandón",
"inali_name": "lacandón",
"english_name": "Lacandon",
"samples": 5,
"chars": 2519,
"utf8_bytes": 2820,
"tokens": 659,
"chars_per_token": 3.8224582701062215,
"tokens_per_char": 0.26161175069472015,
"bytes_per_token": 4.279210925644916,
"tokens_per_byte": 0.23368794326241135,
"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": 583,
"chars_per_token": 3.456260720411664,
"tokens_per_char": 0.2893300248138958,
"bytes_per_token": 3.5728987993138936,
"tokens_per_byte": 0.2798847815650504,
"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": 353,
"chars_per_token": 4.280453257790368,
"tokens_per_char": 0.23362011912640634,
"bytes_per_token": 4.586402266288951,
"tokens_per_byte": 0.21803582458307597,
"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": 564,
"chars_per_token": 4.466312056737588,
"tokens_per_char": 0.22389837236998808,
"bytes_per_token": 5.221631205673759,
"tokens_per_byte": 0.19151103565365024,
"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": 474,
"chars_per_token": 3.1877637130801686,
"tokens_per_char": 0.31369953673064194,
"bytes_per_token": 3.280590717299578,
"tokens_per_byte": 0.3048231511254019,
"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": 375,
"chars_per_token": 4.029333333333334,
"tokens_per_char": 0.24818001323626737,
"bytes_per_token": 4.538666666666667,
"tokens_per_byte": 0.22032902467685075,
"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": 339,
"chars_per_token": 2.9705014749262535,
"tokens_per_char": 0.33664349553128103,
"bytes_per_token": 3.1533923303834808,
"tokens_per_byte": 0.31711880261927033,
"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": 491,
"chars_per_token": 3.0773930753564156,
"tokens_per_char": 0.3249503639973527,
"bytes_per_token": 3.3828920570264764,
"tokens_per_byte": 0.2956050571944612,
"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": 469,
"chars_per_token": 3.2217484008528783,
"tokens_per_char": 0.31039046988749175,
"bytes_per_token": 3.594882729211087,
"tokens_per_byte": 0.2781731909845789,
"round_trip": true
},
{
"code": "maj",
"autonym": "Kinꞌekꞌatiya, Ntaxjo̱",
"spanish_name": "Mazateco de Jalapa de Díaz",
"inali_name": "mazateco del este bajo",
"english_name": "Jalapa de Díaz Mazatec",
"samples": 1,
"chars": 503,
"utf8_bytes": 507,
"tokens": 134,
"chars_per_token": 3.753731343283582,
"tokens_per_char": 0.2664015904572565,
"bytes_per_token": 3.783582089552239,
"tokens_per_byte": 0.26429980276134124,
"round_trip": true
},
{
"code": "maq",
"autonym": "Hne naja, Nne nangui ngaxni",
"spanish_name": "Mazateco de Chiquihuitlán",
"inali_name": "mazateco del sur",
"english_name": "Chiquihuitlán Mazatec",
"samples": 2,
"chars": 1007,
"utf8_bytes": 1099,
"tokens": 329,
"chars_per_token": 3.060790273556231,
"tokens_per_char": 0.32671300893743793,
"bytes_per_token": 3.3404255319148937,
"tokens_per_byte": 0.29936305732484075,
"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": 178,
"chars_per_token": 2.8258426966292136,
"tokens_per_char": 0.3538767395626243,
"bytes_per_token": 3.1235955056179776,
"tokens_per_byte": 0.32014388489208634,
"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": 768,
"chars_per_token": 3.2799479166666665,
"tokens_per_char": 0.30488289003572844,
"bytes_per_token": 3.6953125,
"tokens_per_byte": 0.27061310782241016,
"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": 721,
"chars_per_token": 2.794729542302358,
"tokens_per_char": 0.3578163771712159,
"bytes_per_token": 3.233009708737864,
"tokens_per_byte": 0.30930930930930933,
"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": 391,
"chars_per_token": 2.575447570332481,
"tokens_per_char": 0.38828202581926513,
"bytes_per_token": 2.918158567774936,
"tokens_per_byte": 0.3426818580192813,
"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": 646,
"chars_per_token": 3.1191950464396285,
"tokens_per_char": 0.3205955334987593,
"bytes_per_token": 3.8839009287925697,
"tokens_per_byte": 0.2574730968513352,
"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": 310,
"chars_per_token": 3.2483870967741937,
"tokens_per_char": 0.30784508440913605,
"bytes_per_token": 3.467741935483871,
"tokens_per_byte": 0.28837209302325584,
"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": 216,
"chars_per_token": 2.3287037037037037,
"tokens_per_char": 0.4294234592445328,
"bytes_per_token": 2.6296296296296298,
"tokens_per_byte": 0.38028169014084506,
"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": 610,
"chars_per_token": 3.30327868852459,
"tokens_per_char": 0.3027295285359802,
"bytes_per_token": 3.962295081967213,
"tokens_per_byte": 0.25237898220935046,
"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": 452,
"chars_per_token": 3.3429203539823007,
"tokens_per_char": 0.29913964262078097,
"bytes_per_token": 3.6991150442477876,
"tokens_per_byte": 0.2703349282296651,
"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": 432,
"chars_per_token": 3.497685185185185,
"tokens_per_char": 0.28590337524818,
"bytes_per_token": 4.12037037037037,
"tokens_per_byte": 0.24269662921348314,
"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": 411,
"chars_per_token": 3.67639902676399,
"tokens_per_char": 0.27200529450694905,
"bytes_per_token": 3.776155717761557,
"tokens_per_byte": 0.264819587628866,
"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": 445,
"chars_per_token": 3.3955056179775283,
"tokens_per_char": 0.2945069490403706,
"bytes_per_token": 3.750561797752809,
"tokens_per_byte": 0.2666267225883763,
"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": 624,
"chars_per_token": 3.2291666666666665,
"tokens_per_char": 0.3096774193548387,
"bytes_per_token": 3.483974358974359,
"tokens_per_byte": 0.28702851885924563,
"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": 165,
"chars_per_token": 3.0484848484848484,
"tokens_per_char": 0.32803180914512925,
"bytes_per_token": 3.327272727272727,
"tokens_per_byte": 0.3005464480874317,
"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": 543,
"chars_per_token": 3.710865561694291,
"tokens_per_char": 0.2694789081885856,
"bytes_per_token": 4.121546961325967,
"tokens_per_byte": 0.24262734584450402,
"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": 453,
"chars_per_token": 4.448123620309051,
"tokens_per_char": 0.2248138957816377,
"bytes_per_token": 4.82560706401766,
"tokens_per_byte": 0.20722781335773102,
"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": 146,
"chars_per_token": 3.4452054794520546,
"tokens_per_char": 0.29025844930417494,
"bytes_per_token": 3.4452054794520546,
"tokens_per_byte": 0.29025844930417494,
"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": 464,
"chars_per_token": 4.342672413793103,
"tokens_per_char": 0.23027295285359803,
"bytes_per_token": 4.489224137931035,
"tokens_per_byte": 0.2227556409025444,
"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": 458,
"chars_per_token": 4.399563318777292,
"tokens_per_char": 0.22729528535980148,
"bytes_per_token": 4.399563318777292,
"tokens_per_byte": 0.22729528535980148,
"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": 689,
"chars_per_token": 3.656023222060958,
"tokens_per_char": 0.27352123858674077,
"bytes_per_token": 3.7547169811320753,
"tokens_per_byte": 0.2663316582914573,
"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": 562,
"chars_per_token": 3.5854092526690393,
"tokens_per_char": 0.27890818858560795,
"bytes_per_token": 3.6209964412811386,
"tokens_per_byte": 0.27616707616707614,
"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": 623,
"chars_per_token": 4.043338683788122,
"tokens_per_char": 0.24732036522429535,
"bytes_per_token": 4.099518459069021,
"tokens_per_byte": 0.24393108848864525,
"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": 566,
"chars_per_token": 3.545936395759717,
"tokens_per_char": 0.2820129546586946,
"bytes_per_token": 3.579505300353357,
"tokens_per_byte": 0.2793682132280355,
"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": 586,
"chars_per_token": 3.438566552901024,
"tokens_per_char": 0.29081885856079404,
"bytes_per_token": 3.4470989761092152,
"tokens_per_byte": 0.2900990099009901,
"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": 357,
"chars_per_token": 4.23249299719888,
"tokens_per_char": 0.23626737260092653,
"bytes_per_token": 4.23249299719888,
"tokens_per_byte": 0.23626737260092653,
"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": 443,
"chars_per_token": 3.4108352144469527,
"tokens_per_char": 0.2931833223031105,
"bytes_per_token": 3.4108352144469527,
"tokens_per_byte": 0.2931833223031105,
"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": 197,
"chars_per_token": 2.532994923857868,
"tokens_per_char": 0.39478957915831664,
"bytes_per_token": 2.7411167512690353,
"tokens_per_byte": 0.3648148148148148,
"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": 522,
"chars_per_token": 2.8946360153256707,
"tokens_per_char": 0.3454665784248842,
"bytes_per_token": 3.342911877394636,
"tokens_per_byte": 0.29914040114613183,
"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": 527,
"chars_per_token": 2.8671726755218216,
"tokens_per_char": 0.3487756452680344,
"bytes_per_token": 3.480075901328273,
"tokens_per_byte": 0.28735005452562706,
"round_trip": true
},
{
"code": "ppi",
"autonym": "Paipai",
"spanish_name": "Paipai",
"inali_name": "paipai",
"english_name": "Paipai",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1554,
"tokens": 529,
"chars_per_token": 2.8563327032136105,
"tokens_per_char": 0.3500992720052945,
"bytes_per_token": 2.937618147448015,
"tokens_per_byte": 0.3404118404118404,
"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": 455,
"chars_per_token": 3.320879120879121,
"tokens_per_char": 0.3011250827266711,
"bytes_per_token": 3.81978021978022,
"tokens_per_byte": 0.261795166858458,
"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": 480,
"chars_per_token": 3.1479166666666667,
"tokens_per_char": 0.31767041694242226,
"bytes_per_token": 3.48125,
"tokens_per_byte": 0.2872531418312388,
"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": 507,
"chars_per_token": 2.980276134122288,
"tokens_per_char": 0.3355393778954335,
"bytes_per_token": 3.035502958579882,
"tokens_per_byte": 0.32943469785575047,
"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": 566,
"chars_per_token": 3.560070671378092,
"tokens_per_char": 0.28089330024813897,
"bytes_per_token": 3.8674911660777385,
"tokens_per_byte": 0.25856555504796713,
"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": 154,
"chars_per_token": 3.2662337662337664,
"tokens_per_char": 0.3061630218687873,
"bytes_per_token": 3.331168831168831,
"tokens_per_byte": 0.3001949317738791,
"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": 415,
"chars_per_token": 3.6409638554216865,
"tokens_per_char": 0.2746525479814692,
"bytes_per_token": 4.250602409638554,
"tokens_per_byte": 0.23526077097505668,
"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": 490,
"chars_per_token": 3.083673469387755,
"tokens_per_char": 0.3242885506287227,
"bytes_per_token": 3.336734693877551,
"tokens_per_byte": 0.2996941896024465,
"round_trip": true
},
{
"code": "mhc",
"autonym": "Mocho'",
"spanish_name": "Motozintleco",
"inali_name": "mocho’",
"english_name": "Mocho",
"samples": 4,
"chars": 2015,
"utf8_bytes": 2021,
"tokens": 460,
"chars_per_token": 4.380434782608695,
"tokens_per_char": 0.228287841191067,
"bytes_per_token": 4.393478260869565,
"tokens_per_byte": 0.22761009401286492,
"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": 534,
"chars_per_token": 2.8295880149812733,
"tokens_per_char": 0.35340833884844475,
"bytes_per_token": 3.250936329588015,
"tokens_per_byte": 0.3076036866359447,
"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": 305,
"chars_per_token": 4.954098360655737,
"tokens_per_char": 0.20185307743216413,
"bytes_per_token": 5.019672131147541,
"tokens_per_byte": 0.1992161985630307,
"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": 465,
"chars_per_token": 3.249462365591398,
"tokens_per_char": 0.30774321641297153,
"bytes_per_token": 3.6043010752688174,
"tokens_per_byte": 0.27744630071599047,
"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": 516,
"chars_per_token": 2.9282945736434107,
"tokens_per_char": 0.3414956982131039,
"bytes_per_token": 3.0717054263565893,
"tokens_per_byte": 0.32555205047318614,
"round_trip": true
},
{
"code": "tsz",
"autonym": "P’urhe, P’urhépecha",
"spanish_name": "Purépecha",
"inali_name": "purépecha",
"english_name": "Purepecha",
"samples": 3,
"chars": 1511,
"utf8_bytes": 1590,
"tokens": 413,
"chars_per_token": 3.6585956416464893,
"tokens_per_char": 0.27332892124420916,
"bytes_per_token": 3.8498789346246975,
"tokens_per_byte": 0.259748427672956,
"round_trip": true
},
{
"code": "tee",
"autonym": "Lhima'alh'ama'",
"spanish_name": "Tepehua de Huehuetla",
"inali_name": "tepehua del sur",
"english_name": "Huehuetla Tepehua",
"samples": 4,
"chars": 2015,
"utf8_bytes": 2052,
"tokens": 516,
"chars_per_token": 3.9050387596899223,
"tokens_per_char": 0.25607940446650124,
"bytes_per_token": 3.9767441860465116,
"tokens_per_byte": 0.25146198830409355,
"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": 487,
"chars_per_token": 4.137577002053388,
"tokens_per_char": 0.24168734491315136,
"bytes_per_token": 4.310061601642711,
"tokens_per_byte": 0.23201524535493093,
"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": 408,
"chars_per_token": 3.7034313725490198,
"tokens_per_char": 0.2700198544010589,
"bytes_per_token": 4.014705882352941,
"tokens_per_byte": 0.2490842490842491,
"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": 331,
"chars_per_token": 3.0422960725075527,
"tokens_per_char": 0.3286991062562066,
"bytes_per_token": 3.673716012084592,
"tokens_per_byte": 0.2722039473684211,
"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": 580,
"chars_per_token": 2.6051724137931034,
"tokens_per_char": 0.38385175380542685,
"bytes_per_token": 2.706896551724138,
"tokens_per_byte": 0.36942675159235666,
"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": 429,
"chars_per_token": 2.347319347319347,
"tokens_per_char": 0.4260178748758689,
"bytes_per_token": 2.909090909090909,
"tokens_per_byte": 0.34375,
"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": 585,
"chars_per_token": 2.582905982905983,
"tokens_per_char": 0.3871608206485771,
"bytes_per_token": 2.8974358974358974,
"tokens_per_byte": 0.34513274336283184,
"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": 626,
"chars_per_token": 2.413738019169329,
"tokens_per_char": 0.414295168762409,
"bytes_per_token": 3.1118210862619806,
"tokens_per_byte": 0.3213552361396304,
"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": 508,
"chars_per_token": 3.966535433070866,
"tokens_per_char": 0.2521091811414392,
"bytes_per_token": 4.322834645669292,
"tokens_per_byte": 0.23132969034608378,
"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": 590,
"chars_per_token": 3.4152542372881354,
"tokens_per_char": 0.29280397022332505,
"bytes_per_token": 3.486440677966102,
"tokens_per_byte": 0.2868254739912494,
"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": 578,
"chars_per_token": 4.358131487889273,
"tokens_per_char": 0.2294561333862644,
"bytes_per_token": 4.467128027681661,
"tokens_per_byte": 0.2238574748257165,
"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": 570,
"chars_per_token": 3.5350877192982457,
"tokens_per_char": 0.28287841191067,
"bytes_per_token": 3.663157894736842,
"tokens_per_byte": 0.27298850574712646,
"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": 289,
"chars_per_token": 5.228373702422146,
"tokens_per_char": 0.1912640635340834,
"bytes_per_token": 6.197231833910035,
"tokens_per_byte": 0.16136236739251814,
"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": 231,
"chars_per_token": 4.359307359307359,
"tokens_per_char": 0.22939424031777558,
"bytes_per_token": 4.770562770562771,
"tokens_per_byte": 0.20961887477313976,
"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": 395,
"chars_per_token": 5.10126582278481,
"tokens_per_char": 0.19602977667493796,
"bytes_per_token": 5.567088607594937,
"tokens_per_byte": 0.17962710322874034,
"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": 527,
"chars_per_token": 3.823529411764706,
"tokens_per_char": 0.26153846153846155,
"bytes_per_token": 4.003795066413662,
"tokens_per_byte": 0.24976303317535545,
"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": 440,
"chars_per_token": 3.434090909090909,
"tokens_per_char": 0.29119788219722037,
"bytes_per_token": 3.8068181818181817,
"tokens_per_byte": 0.2626865671641791,
"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": 454,
"chars_per_token": 3.328193832599119,
"tokens_per_char": 0.300463269358041,
"bytes_per_token": 3.5682819383259914,
"tokens_per_byte": 0.2802469135802469,
"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": 512,
"chars_per_token": 2.951171875,
"tokens_per_char": 0.3388484447385837,
"bytes_per_token": 3.103515625,
"tokens_per_byte": 0.3222152297042165,
"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": 475,
"chars_per_token": 4.242105263157895,
"tokens_per_char": 0.23573200992555832,
"bytes_per_token": 4.703157894736842,
"tokens_per_byte": 0.2126230975828111,
"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": 673,
"chars_per_token": 2.9940564635958395,
"tokens_per_char": 0.33399503722084367,
"bytes_per_token": 3.320950965824666,
"tokens_per_byte": 0.3011185682326622,
"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": 529,
"chars_per_token": 2.8563327032136105,
"tokens_per_char": 0.3500992720052945,
"bytes_per_token": 3.2362948960302456,
"tokens_per_byte": 0.30899532710280375,
"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": 505,
"chars_per_token": 2.992079207920792,
"tokens_per_char": 0.33421575115817337,
"bytes_per_token": 3.1485148514851486,
"tokens_per_byte": 0.31761006289308175,
"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": 645,
"chars_per_token": 3.124031007751938,
"tokens_per_char": 0.3200992555831266,
"bytes_per_token": 3.449612403100775,
"tokens_per_byte": 0.2898876404494382,
"round_trip": true
}
]