{"id":303,"date":"2025-10-31T21:15:45","date_gmt":"2025-10-31T21:15:45","guid":{"rendered":"https:\/\/tonallicorpus.com\/?page_id=303"},"modified":"2026-10-29T22:24:39","modified_gmt":"2026-10-30T04:24:39","slug":"download-datasets","status":"publish","type":"page","link":"https:\/\/tonallicorpus.com\/?page_id=303","title":{"rendered":"Download the Datasets"},"content":{"rendered":"\n<p class=\"wp-block-paragraph\">Here you can download the datasets, so as the transcriptions and translatios to Spanish and English.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>N\u00e1huatl<\/strong><\/p>\n\n\n\n<div class=\"wp-block-group is-layout-constrained wp-block-group-is-layout-constrained\">\n<p class=\"wp-block-paragraph\"><a href=\"https:\/\/tonallicorpus.com\/?page_id=308\">Cuetzalan Town Interviews (<em>Date:<\/em> July 9th, 2025)<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><a href=\"https:\/\/tonallicorpus.com\/?page_id=316\" data-type=\"page\" data-id=\"316\">Cuautempan Town Interviews (<em>Date:<\/em> July 10th, 2025)<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><a href=\"https:\/\/tonallicorpus.com\/?page_id=497\" data-type=\"page\" data-id=\"497\">San Jos\u00e9 Miahuatl\u00e1n Town Interviews (Date: December 1st, 2025)<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><a href=\"https:\/\/tonallicorpus.com\/?page_id=499\" data-type=\"page\" data-id=\"499\">Teteles de \u00c1vila Castillo Town Interviews (Date: December 3rd, 2025)<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><a href=\"https:\/\/tonallicorpus.com\/?page_id=490\" data-type=\"page\" data-id=\"490\">San Miguel Canoa Town Interviews (Date: December 11th, 2025)<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><a href=\"https:\/\/tonallicorpus.com\/?page_id=507\" data-type=\"page\" data-id=\"507\">Ocotlamanic, Coxcatl\u00e1n Town Interviews (Date: December 29th, 2025)<\/a><\/p>\n<\/div>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Totonaco<\/strong><\/p>\n\n\n\n<div class=\"wp-block-group is-layout-constrained wp-block-group-is-layout-constrained\">\n<p class=\"wp-block-paragraph\"><a href=\"https:\/\/tonallicorpus.com\/?page_id=325\" data-type=\"page\" data-id=\"325\">Ixtepec Town Interviews (<em>Date:<\/em> August 7th, 2025)<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><a href=\"https:\/\/tonallicorpus.com\/?page_id=503\" data-type=\"page\" data-id=\"503\">Nanacatl\u00e1n Town Interviews (Date: December 4rd, 2025)<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><a href=\"https:\/\/tonallicorpus.com\/?page_id=509\" data-type=\"page\" data-id=\"509\">Zihuateutla Town Interviews (Date: December 31st, 2025)<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><a href=\"https:\/\/tonallicorpus.com\/?page_id=564\" data-type=\"page\" data-id=\"564\">Huehuetla Town Interviews (Date: May 21st, 2026)<\/a><\/p>\n<\/div>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Please <\/strong>use the <em>corresponding credits <\/em>when you publish some paper in which you have used this dataset.<\/p>\n\n\n\n<h1 class=\"wp-block-heading\"><strong>Transcriptions \/ Translations of the Dataset<\/strong><\/h1>\n\n\n\n<div class=\"lacuna-downloads\">\n\n  <style>\n    .lacuna-downloads {\n      max-width: 1000px;\n      margin: 30px auto;\n      font-family: inherit;\n    }\n\n    .lacuna-downloads h2 {\n      margin-bottom: 8px;\n    }\n\n    .lacuna-downloads .intro {\n      margin-bottom: 25px;\n      color: #555;\n      line-height: 1.6;\n    }\n\n    .lacuna-language {\n      border: 1px solid #e1e1e1;\n      border-radius: 12px;\n      padding: 24px;\n      margin-bottom: 25px;\n      background: #fff;\n    }\n\n    .lacuna-language h3 {\n      margin-top: 0;\n      margin-bottom: 8px;\n      font-size: 1.5rem;\n    }\n\n    .lacuna-language p {\n      margin-top: 0;\n      margin-bottom: 20px;\n      color: #555;\n      line-height: 1.6;\n    }\n\n    .lacuna-buttons {\n      display: flex;\n      flex-wrap: wrap;\n      gap: 12px;\n    }\n\n    .lacuna-button {\n      display: inline-block;\n      padding: 11px 20px;\n      border-radius: 6px;\n      background: #1f4e78;\n      color: #ffffff !important;\n      text-decoration: none !important;\n      font-weight: 600;\n      transition: opacity 0.2s ease;\n    }\n\n    .lacuna-button:hover {\n      opacity: 0.85;\n      color: #ffffff !important;\n    }\n\n    .lacuna-format {\n      font-size: 0.85em;\n      opacity: 0.85;\n      margin-left: 5px;\n    }\n\n    .lacuna-info {\n      margin-top: 18px;\n      font-size: 0.9rem;\n      color: #777;\n    }\n  <\/style>\n\n\n  <h2>Corpus Download<\/h2>\n\n  <p class=\"intro\">\n    The datasets are available in XLSX, XML, and JSON formats.\n    Each record includes the transcription in the Indigenous language,\n    together with Spanish and English translations of both questions\n    and answers.\n  <\/p>\n\n\n  <!-- NAHUATL CORPUS -->\n  <div class=\"lacuna-language\">\n\n    <h3>Nahuatl Corpus<\/h3>\n\n    <p>\n      2,964 segments with Nahuatl transcriptions and parallel\n      Spanish and English translations.\n    <\/p>\n\n    <div class=\"lacuna-buttons\">\n\n      <a class=\"lacuna-button\" href=\"\/wp-content\/uploads\/lacuna\/datasets\/nahuatl\/nahuatl_master.xlsx\" download=\"\">\n        Download <span class=\"lacuna-format\">XLSX<\/span>\n      <\/a>\n\n      <a class=\"lacuna-button\" href=\"\/wp-content\/uploads\/lacuna\/datasets\/nahuatl\/nahuatl_master.xml\" download=\"\">\n        Download <span class=\"lacuna-format\">XML<\/span>\n      <\/a>\n\n      <a class=\"lacuna-button\" href=\"\/wp-content\/uploads\/lacuna\/datasets\/nahuatl\/nahuatl_master.json\" download=\"\">\n        Download <span class=\"lacuna-format\">JSON<\/span>\n      <\/a>\n\n    <\/div>\n\n    <div class=\"lacuna-info\">\n      Languages: Nahuatl (original transcription), Spanish and English.\n    <\/div>\n\n  <\/div>\n\n\n  <!-- TOTONAC CORPUS -->\n  <div class=\"lacuna-language\">\n\n    <h3>Totonac Corpus<\/h3>\n\n    <p>\n      2,563 segments with Totonac transcriptions and parallel\n      Spanish and English translations.\n    <\/p>\n\n    <div class=\"lacuna-buttons\">\n\n      <a class=\"lacuna-button\" href=\"\/wp-content\/uploads\/lacuna\/datasets\/totonac\/totonaco_master.xlsx\" download=\"\">\n        Download <span class=\"lacuna-format\">XLSX<\/span>\n      <\/a>\n\n      <a class=\"lacuna-button\" href=\"\/wp-content\/uploads\/lacuna\/datasets\/totonac\/totonaco_master.xml\" download=\"\">\n        Download <span class=\"lacuna-format\">XML<\/span>\n      <\/a>\n\n      <a class=\"lacuna-button\" href=\"\/wp-content\/uploads\/lacuna\/datasets\/totonac\/totonaco_master.json\" download=\"\">\n        Download <span class=\"lacuna-format\">JSON<\/span>\n      <\/a>\n\n    <\/div>\n\n    <div class=\"lacuna-info\">\n      Languages: Totonac (original transcription), Spanish and English.\n    <\/div>\n\n  <\/div>\n\n <!-- TAGGED CORPUS -->\n  <div class=\"lacuna-language\">\n\n    <h3>Tagged Corpus<\/h3>\n\n    <p>\n      Here you can download the complete tagged corpus, including Nahuatl and Totonac transcriptions and parallel Spanish and English translations.\n    <\/p>\n\n    <div class=\"lacuna-buttons\">\n\n      <a class=\"lacuna-button\" href=\"\/wp-content\/uploads\/lacuna\/datasets\/Tonalli_Corpus_AI_Institutional_v1_3.zip\" download=\"\">\n        Download <span class=\"lacuna-format\">ZIP<\/span>\n      <\/a>\n\n    <\/div>\n\n    <div class=\"lacuna-info\">\n      Languages: Nahuatl and Totonac (original transcription), Spanish and English.\n    <\/div>\n\n  <\/div>\n\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>Here you can download the datasets, so as the transcriptions and translatios to Spanish and English. N\u00e1huatl Cuetzalan Town Interviews [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"default","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"default","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"footnotes":""},"class_list":["post-303","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/tonallicorpus.com\/index.php?rest_route=\/wp\/v2\/pages\/303","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/tonallicorpus.com\/index.php?rest_route=\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/tonallicorpus.com\/index.php?rest_route=\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/tonallicorpus.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/tonallicorpus.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=303"}],"version-history":[{"count":22,"href":"https:\/\/tonallicorpus.com\/index.php?rest_route=\/wp\/v2\/pages\/303\/revisions"}],"predecessor-version":[{"id":590,"href":"https:\/\/tonallicorpus.com\/index.php?rest_route=\/wp\/v2\/pages\/303\/revisions\/590"}],"wp:attachment":[{"href":"https:\/\/tonallicorpus.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=303"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}