{
 "name": "LinZi open Chinese learning datasets",
 "url": "https://www.linzi.app/data/",
 "generated": "2026-11-02",
 "attribution": "Vocabulary data from LinZi - https://www.linzi.app/data/",
 "files": [
  {
   "path": "data/files/hsk30-words.csv",
   "url": "https://www.linzi.app/data/files/hsk30-words.csv",
   "bytes": 1058296,
   "sha256": "ed2004296efb3097b07870ef21d1e9dcb2f51cc1bf09b9dfa7bdda7713453f5d",
   "rows": 11036,
   "description": "HSK 3.0 word list - CSV",
   "license": "CC-BY-SA 4.0 - HSK 3.0 syllabus (PRC MoE, freely redistributable); definitions from CC-CEDICT (CC-BY-SA); compiled by LinZi"
  },
  {
   "path": "data/files/hsk30-words.json",
   "url": "https://www.linzi.app/data/files/hsk30-words.json",
   "bytes": 2249650,
   "sha256": "22d4308c32025cae498b0ac9d29d5dcae02036998960edca3b5218f0921d8a1f",
   "rows": 11036,
   "description": "HSK 3.0 word list - JSON",
   "license": "CC-BY-SA 4.0 - HSK 3.0 syllabus (PRC MoE, freely redistributable); definitions from CC-CEDICT (CC-BY-SA); compiled by LinZi"
  },
  {
   "path": "data/files/tocfl-words.csv",
   "url": "https://www.linzi.app/data/files/tocfl-words.csv",
   "bytes": 732762,
   "sha256": "1500a12f773875cde49a8070e6e19eac2c19ce0a919d2aeed052e754de15708e",
   "rows": 7187,
   "description": "TOCFL 華語八千詞 word list - CSV",
   "license": "CC-BY-SA 4.0 - TOCFL 華語八千詞 syllabus (Taiwan MOE / SC-TOP, freely redistributable); definitions from CC-CEDICT (CC-BY-SA); compiled by LinZi"
  },
  {
   "path": "data/files/tocfl-words.json",
   "url": "https://www.linzi.app/data/files/tocfl-words.json",
   "bytes": 1652651,
   "sha256": "519547a99a43815de5c983d3e278d6a6047f1b66ed37194bef5e42f88027a973",
   "rows": 7187,
   "description": "TOCFL 華語八千詞 word list - JSON",
   "license": "CC-BY-SA 4.0 - TOCFL 華語八千詞 syllabus (Taiwan MOE / SC-TOP, freely redistributable); definitions from CC-CEDICT (CC-BY-SA); compiled by LinZi"
  },
  {
   "path": "data/files/cross-strait-pairs.csv",
   "url": "https://www.linzi.app/data/files/cross-strait-pairs.csv",
   "bytes": 123167,
   "sha256": "7d623292e4b10909179eced21f072e1ffa057d92186558418b06fbbe73e273bc",
   "rows": 953,
   "description": "Taiwan vs Mainland word pairs - CSV",
   "license": "CC-BY-SA 4.0 - curated by LinZi (linzi.app)"
  },
  {
   "path": "data/files/cross-strait-pairs.json",
   "url": "https://www.linzi.app/data/files/cross-strait-pairs.json",
   "bytes": 303864,
   "sha256": "32dfab27143f7f186e91f1096f93c0b595cbe1ebf432ae136589f2d32455d90f",
   "rows": 953,
   "description": "Taiwan vs Mainland word pairs - JSON",
   "license": "CC-BY-SA 4.0 - curated by LinZi (linzi.app)"
  },
  {
   "path": "data/files/confusing-pairs.json",
   "url": "https://www.linzi.app/data/files/confusing-pairs.json",
   "bytes": 25143,
   "sha256": "882d72b37731738471d9e9f9ab7068e3f5b7624f4281c65c87b9b2a068a42fe4",
   "rows": 100,
   "description": "Easily-confused character & word pairs - JSON",
   "license": "CC-BY-SA 4.0 - curated by LinZi (linzi.app)"
  },
  {
   "path": "data/files/measure-words.csv",
   "url": "https://www.linzi.app/data/files/measure-words.csv",
   "bytes": 14612,
   "sha256": "f12ddbb9ef5d1f3059e392fcd1150f183381a52a056e5a2b6839d4d6ca0ec02f",
   "rows": 133,
   "description": "Measure words (classifiers) + nouns - CSV",
   "license": "CC-BY-SA 4.0 - curated by LinZi (linzi.app)"
  },
  {
   "path": "data/files/measure-words.json",
   "url": "https://www.linzi.app/data/files/measure-words.json",
   "bytes": 41523,
   "sha256": "92e33857dd5a5c4ba46140950505ef185e31ad8fbb8780c82839580bbe5680f1",
   "rows": 133,
   "description": "Measure words (classifiers) + nouns - JSON",
   "license": "CC-BY-SA 4.0 - curated by LinZi (linzi.app)"
  },
  {
   "path": "data/files/stories-catalog.csv",
   "url": "https://www.linzi.app/data/files/stories-catalog.csv",
   "bytes": 263713,
   "sha256": "04e2af21e3ffaf12547b923b9ec161ed4f1528cd8a2d8ab001ca73629e18826e",
   "rows": 1760,
   "description": "Graded-story catalog - CSV",
   "license": "CC-BY-SA 4.0 - curated by LinZi (linzi.app)"
  },
  {
   "path": "data/files/stories-catalog.json",
   "url": "https://www.linzi.app/data/files/stories-catalog.json",
   "bytes": 581179,
   "sha256": "691287f437fd8235ad70212ad4c0f716e741e6e5bab78d07a161ba608e17e22d",
   "rows": 1760,
   "description": "Graded-story catalog - JSON",
   "license": "CC-BY-SA 4.0 - curated by LinZi (linzi.app)"
  },
  {
   "path": "data/files/LICENSE.txt",
   "url": "https://www.linzi.app/data/files/LICENSE.txt",
   "bytes": 2025,
   "sha256": "d3ecf60f26ef68f71aca0dbdb78df131a04659ad605e58555b2ade7c683f415b",
   "rows": null,
   "description": "License terms for everything in this directory",
   "license": "see file"
  }
 ]
}
