{"licensedSources":[{"adaptation_notice":"Laowai selected and reviewed records, linked dictionary tokens, generated or corrected pinyin and Traditional forms, estimated difficulty, and may trim approved edge silence and transcode approved recordings to 32 kbps AAC-LC M4A.","author_credit":"FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech (2022), Alexis Conneau, Min Ma, Simran Khanuja, Yu Zhang, Vera Axelrod, Siddharth Dalmia, Jason Riesa, Clara Rivera, and Ankur Bapna","configuration":"cmn_hans_cn","dataset":"google/fleurs","license_name":"CC BY 4.0","license_url":"https://creativecommons.org/licenses/by/4.0/","source_id":"google-fleurs-cmn-hans-cn","source_revision":"70bb2e84b976b7e960aa89f1c648e09c59f894dd","source_url":"https://huggingface.co/datasets/google/fleurs"}],"metadata":{"character_reference_license":"Unicode License v3","character_reference_record_count":"102998","character_reference_source":"Unicode Unihan","character_reference_source_sha256":"f7a48b2b545acfaa77b2d607ae28747404ce02baefee16396c5d2d7a8ef34b5e","character_reference_source_url":"https://www.unicode.org/Public/UCD/latest/ucd/Unihan.zip","character_reference_version":"17.0.0","concept_relations_chinese_sha256":"7d07af60a6ced0cedc4ca114d0b60a796d3f138df0f3be21f6322e53d004e91c","concept_relations_count":"87118","concept_relations_english_sha256":"0e09dfb7f096bc3f10b9de68ffecf13839fa22ae46fd9b227cec890d204ca1dc","concept_relations_license":"WordNet licenses","concept_relations_source":"Chinese Open Wordnet 2.0 and WordNet 3.0","concept_relations_source_url":"https://github.com/omwn/omw-data/releases/tag/v2.0","corpus_collocation_count":"14003","corpus_usage_license":"CC BY","corpus_usage_source":"Leipzig Corpora Collection cmn-tw_web_2020_30K","corpus_usage_source_sha256":"4d1c20ec9b949ad338bb843ecc2be3189a419c0d5a3aafe71765b5ae0d5a6901","corpus_usage_source_url":"https://downloads.wortschatz-leipzig.de/corpora/cmn-tw_web_2020_30K.tar.gz","corpus_usage_word_count":"24486","dictionary":"CC-CEDICT","etymology_license":"LGPL-3.0-or-later","etymology_record_count":"9574","etymology_source":"Make Me a Hanzi dictionary.txt","etymology_source_commit":"618dbab8a8ddefb958763c8b4afbaa741a4460de","etymology_source_sha256":"744bb05d5b0742e9ee35c37791f94d56a173349b3367569e7ca11e510364d203","etymology_source_url":"https://github.com/skishore/makemeahanzi","license":"CC BY-SA 4.0","semantic_relations_count":"96273","semantic_relations_license":"CC BY-SA 4.0","semantic_relations_sha256":"adffa622f223b33b03e76fd1d8f7c57cd90f6491cd5e9cec69a984ec1b3bc1ad","semantic_relations_source":"FMLD","semantic_relations_source_url":"https://github.com/jiong3/fmld","source_release":"2026-07-23 06:20:41 GMT","source_sha256":"01336f9e51eab581342ef6a000a4c0afab7121647f07c1558955af41168b5021","source_url":"https://cc-cedict.org/editor/editor.php?handler=Download"},"modifications":"Laowai exported app tables into JSON shards and linked current CC-CEDICT IDs. Relations apply to headwords and can include other senses. No legacy unlicensed examples or third-party grammar bodies are exported. Character data retains LGPL 3.0-or-later; FMLD relations retain CC BY-SA 4.0; other components retain the licences listed in the bundled notices. Export transformation: https://github.com/MityaPolianskii/BKRSDB/blob/codex/ukrainian-search-matched-meaning/firebase/website/study_export.py"}