Spaces:
Running
Running
Download data.js from Bayanat-Labs/arabic-data-index: direct link, hf CLI and curl.
- Browser
- Download file 49.4 kB
-
https://huggingface.co/spaces/Bayanat-Labs/arabic-data-index/resolve/main/data.js
- Command line
-
hf download hf://spaces/Bayanat-Labs/arabic-data-index/data.js
-
curl -L -o data.js https://huggingface.co/spaces/Bayanat-Labs/arabic-data-index/resolve/main/data.js
49.4 kB
| /* Arabic Data Index, snapshot 2026-11. Generated by scripts/build_space.py from the released files. */ | |
| window.ADI = {"checks":{"candidates":296,"candidates_by_rule":{"multi-masader":{"different":2,"pairs":17,"same":15},"name":{"different":50,"pairs":61,"same":11},"same-size-copy":{"different":0,"pairs":188,"same":188},"shared-link":{"different":28,"pairs":30,"same":2}},"candidates_merged":201,"candidates_same":216,"codes":32,"links_undone":3,"pairs":406,"rule_confirmed":111,"rule_copy":32,"rule_link":80,"rule_sample":112,"rule_undone":1,"sample_also_candidates":3,"source":"qa/dedup_check_2026-11.csv","spot_checks":1,"spot_undone":1},"citation":"Bayanat Labs Arabic Data Index, snapshot 2026-11, CC BY 4.0. https://huggingface.co/datasets/Bayanat-Labs/arabic-data-index","defs":{"ADI-CNT-01":{"ar":"مجموعات البيانات العربية بعد إزالة التكرار (المجموعات الرئيسية؛ دون المجموعات الضخمة متعددة اللغات)","basis":"n/a","en":"De-duplicated Arabic datasets (headline datasets; massive multilingual datasets excluded)","method":"sql/metrics.sql#ADI-CNT-01","notes":"Hugging Face repositories tagged with an Arabic language code, joined with Masader; copies count once (copy groups of the Arabic Dataset Rights Index, and same-size copies checked by Bayanat Labs).","notes_ar":"مستودعات Hugging Face الموسومة برمز لغة عربية مع مدخلات Masader؛ وتُعدّ النسخ مرة واحدة (مجموعات النسخ في فهرس حقوق مجموعات البيانات العربية، والنسخ ذات الحجم المتطابق التي راجعتها بيانات لابز)."},"ADI-CNT-02":{"ar":"مستودعات بيانات في Hugging Face موسومة برمز لغة عربية (كلها، بما فيها النسخ والمجموعات الضخمة متعددة اللغات)","basis":"n/a","en":"Hugging Face dataset repositories tagged with an Arabic language code (all, copies and massive multilingual datasets included)","method":"sql/metrics.sql#ADI-CNT-02","notes":"Repositories counted, not datasets; see ADI-CNT-01 for de-duplicated datasets.","notes_ar":"تُعدّ المستودعات لا مجموعات البيانات؛ انظر ADI-CNT-01 لمجموعات البيانات بعد إزالة التكرار."},"ADI-CNT-03":{"ar":"مجموعات البيانات حسب حصة العربية (عربية فقط، ثنائية اللغة، متعددة اللغات، ضخمة)","basis":"n/a","en":"De-duplicated datasets by Arabic share (only, bilingual, multilingual, massive)","method":"sql/metrics.sql#ADI-CNT-03","notes":"only: every declared language is an Arabic variety; bilingual: Arabic and one other; multilingual: 3 to 9 languages; massive: 10 or more. Arabic varieties count as one language. Masader entries marked multilingual are counted as multilingual because Masader gives no number of languages; entries known to cover 10 or more languages are counted as massive.","notes_ar":"عربية فقط: كل اللغات المعلنة من أنواع العربية؛ ثنائية اللغة: العربية ولغة أخرى؛ متعددة اللغات: من 3 إلى 9 لغات؛ ضخمة: 10 لغات أو أكثر. وتُعدّ أنواع العربية لغة واحدة. وتُعدّ مدخلات Masader الموصوفة بأنها متعددة اللغات ضمن متعددة اللغات لأن Masader لا يذكر عدد اللغات؛ أما المدخلات المعروف أنها تغطي 10 لغات أو أكثر فتُعدّ ضخمة."},"ADI-CNT-04":{"ar":"المجموعات الرئيسية حسب مكان إدراجها (Hugging Face فقط، كلاهما، Masader فقط)","basis":"n/a","en":"Headline datasets by where they are listed (Hugging Face only, both, Masader only)","method":"sql/metrics.sql#ADI-CNT-04","notes":"A Masader entry is joined to a Hugging Face repository through its Hub link, or by a name match checked by Bayanat Labs.","notes_ar":"يُضمّ مدخل Masader إلى مستودع في Hugging Face عبر رابطه في المنصة، أو بتطابق في الاسم راجعته بيانات لابز."},"ADI-CNT-05":{"ar":"مستودعات في Hugging Face تُعدّ مرة واحدة مع مستودع آخر لأنها نسخ من المجموعة نفسها","basis":"n/a","en":"Hugging Face repositories counted once with another repository as copies of the same dataset","method":"sql/metrics.sql#ADI-CNT-05","notes":"Copy groups from the Arabic Dataset Rights Index at a pinned revision, and same-size copies checked by Bayanat Labs: repositories with an identical complete dataset-viewer size whose names match, or a group of 3 or more repositories with one size and at least 10 MB of Parquet files.","notes_ar":"مجموعات النسخ من فهرس حقوق مجموعات البيانات العربية عند مراجعة مثبّتة، والنسخ ذات الحجم المتطابق التي راجعتها بيانات لابز: مستودعات لها الحجم الكامل نفسه في عارض البيانات وتتطابق أسماؤها، أو مجموعة من 3 مستودعات أو أكثر بالحجم نفسه وبملفات Parquet لا تقل عن 10 ميغابايت."},"ADI-CNT-06":{"ar":"المجموعات الرئيسية المدرجة في Masader حسب وضعها في Hugging Face","basis":"n/a","en":"Headline datasets listed in Masader, by their Hugging Face status","method":"sql/metrics.sql#ADI-CNT-06","notes":"on-hub-tagged-arabic: joined to a repository tagged Arabic; on-hub-not-tagged-arabic: the Hub link names a repository without an Arabic language tag; hub-link-not-found: the Hub link does not resolve; hub-link-other-dataset: a checked pair showed that the link names a different dataset; no-hub-link: Masader gives no Hub link.","notes_ar":"on-hub-tagged-arabic: مضمومة إلى مستودع موسوم بالعربية؛ on-hub-not-tagged-arabic: رابط المنصة يشير إلى مستودع دون وسم لغة عربية؛ hub-link-not-found: رابط المنصة لا يعمل؛ hub-link-other-dataset: أظهرت مراجعة الزوج أن الرابط يشير إلى مجموعة أخرى؛ no-hub-link: لا يذكر Masader رابطًا في المنصة."},"ADI-CNT-07":{"ar":"مدخلات Masader المقروءة","basis":"n/a","en":"Masader entries read","method":"sql/metrics.sql#ADI-CNT-07","notes":"Every entry file in the Masader repository at the recorded commit.","notes_ar":"كل ملفات المدخلات في مستودع Masader عند الإيداع المسجّل."},"ADI-CON-01":{"ar":"نسبة المجموعات الرئيسية في Hugging Face لدى الحسابات العشرة الأكثر رفعًا","basis":"n/a","en":"Share of headline Hugging Face datasets held by the 10 accounts with the most","method":"sql/metrics.sql#ADI-CON-01","notes":"Accounts are not named.","notes_ar":"لا تُذكر أسماء الحسابات."},"ADI-CON-02":{"ar":"نسبة تنزيلات آخر 30 يومًا للمجموعات الرئيسية في Hugging Face التي تذهب إلى أكثر 20 مجموعة تنزيلًا","basis":"n/a","en":"Share of 30-day downloads of headline Hugging Face datasets that goes to the 20 most downloaded","method":"sql/metrics.sql#ADI-CON-02","notes":"Downloads as the Hub reports them for the last 30 days.","notes_ar":"التنزيلات كما تذكرها المنصة لآخر 30 يومًا."},"ADI-CON-03":{"ar":"أكثر 20 مجموعة رئيسية تنزيلًا في Hugging Face (تنزيلات آخر 30 يومًا)","basis":"n/a","en":"The 20 most downloaded headline Hugging Face datasets (30-day downloads)","method":"sql/metrics.sql#ADI-CON-03","notes":"Repository ids as published on the Hub; ids include account names.","notes_ar":"معرّفات المستودعات كما تنشرها المنصة؛ وتتضمن المعرّفات أسماء الحسابات."},"ADI-DIA-01":{"ar":"المجموعات الرئيسية حسب نوع العربية أو اللهجة المعلنة","basis":"n/a","en":"Headline datasets by declared Arabic variety or dialect","method":"sql/metrics.sql#ADI-DIA-01","notes":"From Hub language codes and Masader's dialect fields only. A dataset can carry several labels, so shares add up to more than 100%. A Hub tag of plain Arabic (ar) is unspecified. Country labels map to regions. Coverage is the share that declares a variety beyond Arabic.","notes_ar":"من رموز اللغات في المنصة وحقول اللهجة في Masader فقط. قد تحمل المجموعة أكثر من تسمية، فمجموع النسب يتجاوز 100%. ووسم العربية العامة (ar) في المنصة يعني «غير محدد». وتُنسب تسميات البلدان إلى أقاليمها. التغطية نسبة المجموعات التي تعلن نوعًا من العربية غير العربية العامة."},"ADI-DIA-02":{"ar":"المجموعات الرئيسية التي تعلن نوعًا من العربية أو لهجة غير العربية العامة","basis":"n/a","en":"Headline datasets that declare an Arabic variety or dialect beyond Arabic","method":"sql/metrics.sql#ADI-DIA-02","notes":"Modern Standard Arabic, Classical Arabic, mixed and every regional label count.","notes_ar":"تُعدّ العربية الفصحى المعاصرة والعربية الكلاسيكية والمختلطة وكل تسمية إقليمية."},"ADI-DIA-03":{"ar":"المجموعات الرئيسية التي تعلن لهجة إقليمية واحدة على الأقل","basis":"n/a","en":"Headline datasets that declare at least one regional dialect","method":"sql/metrics.sql#ADI-DIA-03","notes":"Regional labels are Gulf, Najdi, Hijazi, Egyptian, Levantine, Iraqi, Maghrebi, Moroccan (Darija), Sudanese, Yemeni and other varieties; Modern Standard Arabic, Classical Arabic and mixed are not counted.","notes_ar":"التسميات الإقليمية: الخليجية والنجدية والحجازية والمصرية والشامية والعراقية والمغاربية والمغربية (الدارجة) والسودانية واليمنية وأنواع أخرى؛ ولا تُعدّ الفصحى المعاصرة والكلاسيكية والمختلطة."},"ADI-GRW-01":{"ar":"المجموعات الرئيسية الموجودة حاليًا في Hugging Face حسب شهر الإنشاء","basis":"n/a","en":"Headline Hugging Face datasets still on the Hub, by creation month","method":"sql/metrics.sql#ADI-GRW-01","notes":"Only datasets that still exist are counted, so earlier months are undercounted (deleted datasets are absent). The Hub gives repositories created before March 2022 a migration date of 2 March 2022; they are counted in the before-2022-03 bucket.","notes_ar":"لا تُعدّ إلا المجموعات الموجودة حاليًا، فالأشهر الأقدم أقل من حقيقتها (المجموعات المحذوفة غائبة). وتعطي المنصة المستودعات المنشأة قبل مارس 2022 تاريخ نقل هو 2 مارس 2022؛ وتُعدّ في خانة before-2022-03."},"ADI-GRW-02":{"ar":"المجموعات الرئيسية في Hugging Face التي أُنشئت في آخر شهر كامل قبل اللقطة","basis":"n/a","en":"Headline Hugging Face datasets created in the last full month before the snapshot","method":"sql/metrics.sql#ADI-GRW-02","notes":"Datasets still on the Hub when the snapshot was read.","notes_ar":"المجموعات الموجودة في المنصة وقت قراءة اللقطة."},"ADI-GRW-03":{"ar":"المجموعات الرئيسية في Hugging Face التي أُنشئت في سنة اللقطة حتى تاريخها","basis":"n/a","en":"Headline Hugging Face datasets created in the snapshot year, up to the snapshot","method":"sql/metrics.sql#ADI-GRW-03","notes":"Datasets still on the Hub when the snapshot was read.","notes_ar":"المجموعات الموجودة في المنصة وقت قراءة اللقطة."},"ADI-GRW-04":{"ar":"المجموعات الرئيسية المدرجة في Masader حسب السنة التي يذكرها","basis":"n/a","en":"Headline datasets listed in Masader, by the year Masader gives","method":"sql/metrics.sql#ADI-GRW-04","notes":"Masader's year is usually the year of the paper or release.","notes_ar":"سنة Masader عادة سنة الورقة أو الإصدار."},"ADI-HLT-01":{"ar":"المجموعات الرئيسية في Hugging Face التي تتطلب الموافقة على شروط للوصول","basis":"n/a","en":"Headline Hugging Face datasets that are gated","method":"sql/metrics.sql#ADI-HLT-01","notes":"Gated repositories ask users to accept conditions before access; they were not opened.","notes_ar":"تطلب المستودعات المقيّدة من المستخدمين قبول شروط قبل الوصول؛ ولم تُفتح."},"ADI-HLT-02":{"ar":"المجموعات الرئيسية في Hugging Face التي يعمل فيها عارض البيانات","basis":"n/a","en":"Headline Hugging Face datasets whose dataset viewer works","method":"sql/metrics.sql#ADI-HLT-02","notes":"Of the repositories asked (gated ones were not); coverage is the share asked. Viewer requests that failed were requested once more, and a reply that then succeeded is used.","notes_ar":"من المستودعات التي طُلبت (لم تُطلب المقيّدة)؛ والتغطية نسبة ما طُلب. وطُلبت طلبات العارض الفاشلة مرة أخرى، ويُستخدم الرد إن نجح."},"ADI-HLT-03":{"ar":"المجموعات الرئيسية في Hugging Face حسب حالة الحجم في عارض البيانات","basis":"n/a","en":"Headline Hugging Face datasets by dataset-viewer size status","method":"sql/metrics.sql#ADI-HLT-03","notes":"ok: complete size; partial: size of part of the data; gated: not asked; unsupported-script: the dataset runs its own loading code; viewer-unsupported: the viewer is off or not supported; empty: no data files; error: another error. A failed request was requested once more; one that failed again keeps the status of its original reply.","notes_ar":"ok: حجم كامل؛ partial: حجم جزء من البيانات؛ gated: لم تُطلب؛ unsupported-script: تعتمد المجموعة على شيفرة تحميل خاصة؛ viewer-unsupported: العارض متوقف أو غير مدعوم؛ empty: دون ملفات بيانات؛ error: خطأ آخر. وطُلب كل طلب فاشل مرة أخرى؛ وما فشل ثانيةً يبقى على حالة رده الأصلي."},"ADI-LIC-01":{"ar":"المجموعات الرئيسية حسب فئة الترخيص المعلن","basis":"declared","en":"Headline datasets by declared licence class","method":"sql/metrics.sql#ADI-LIC-01","notes":"Classes are never added together. open-commercial: permissive, share-alike or software licences; open-noncommercial: CC BY-NC variants; restricted: no-derivatives, research or agreement-based; unclear: other, custom or unknown terms; none: no licence declared. The Hub licence tag is used, or Masader's licence when the Hub has none. Not legal advice.","notes_ar":"لا تُجمع الفئات. مفتوح تجاريًا: تراخيص متساهلة أو تراخيص المشاركة بالمثل أو تراخيص برمجيات؛ مفتوح لغير الأغراض التجارية: صيغ CC BY-NC؛ مقيّد: منع الاشتقاق أو للبحث فقط أو بموجب اتفاقية؛ غير واضح: شروط أخرى أو خاصة أو غير معروفة؛ بلا ترخيص: لا يُعلن أي ترخيص. يُستخدم وسم الترخيص في المنصة، أو ترخيص Masader حين لا يوجد وسم. ليست استشارة قانونية."},"ADI-LIC-02":{"ar":"المجموعات الرئيسية حسب الفئة التفصيلية للترخيص المعلن","basis":"declared","en":"Headline datasets by declared fine licence class","method":"sql/metrics.sql#ADI-LIC-02","notes":"several: licences in different fine classes are declared together.","notes_ar":"several: تُعلن معًا تراخيص من فئات تفصيلية مختلفة."},"ADI-LIC-03":{"ar":"المجموعات الرئيسية التي تعلن ترخيص برمجيات (MIT وApache وBSD وGPL وما يشبهها) لبياناتها","basis":"declared","en":"Headline datasets that declare a software licence (MIT, Apache, BSD, GPL and similar) for their data","method":"sql/metrics.sql#ADI-LIC-03","notes":"Software licences are written for code; they are counted in the open-commercial class.","notes_ar":"تراخيص البرمجيات مكتوبة للشيفرة؛ وتُعدّ ضمن فئة المفتوح تجاريًا."},"ADI-LIC-04":{"ar":"نسبة المجموعات الرئيسية ذات الترخيص المعلن المفتوح للاستخدام التجاري، حسب نوع البيانات","basis":"declared","en":"Share of headline datasets with a declared open-commercial licence, by modality","method":"sql/metrics.sql#ADI-LIC-04","notes":"Denominator is the number of headline datasets of that modality.","notes_ar":"المقام عدد المجموعات الرئيسية من نوع البيانات ذاك."},"ADI-LIC-05":{"ar":"المجموعات الرئيسية في Hugging Face التي لا تحمل وسم ترخيص في المنصة","basis":"declared","en":"Headline Hugging Face datasets without a licence tag on the Hub","method":"sql/metrics.sql#ADI-LIC-05","notes":"Counts the Hub tag only; ADI-LIC-01 also uses Masader's licence when the Hub has none.","notes_ar":"يعدّ وسم المنصة فقط؛ ويستخدم ADI-LIC-01 أيضًا ترخيص Masader حين لا يوجد وسم في المنصة."},"ADI-MOD-01":{"ar":"المجموعات الرئيسية حسب نوع البيانات","basis":"n/a","en":"Headline datasets by modality","method":"sql/metrics.sql#ADI-MOD-01","notes":"From the Hub modality tags, then the Hub task categories, then Masader's form. Coverage is the share with a declared modality.","notes_ar":"من وسوم نوع البيانات في المنصة، ثم فئات المهام في المنصة، ثم شكل البيانات في Masader. التغطية نسبة المجموعات التي تعلن نوع بياناتها."},"ADI-SIZE-01":{"ar":"عدد الصفوف في المجموعات الرئيسية في Hugging Face التي يعطي عارض البيانات حجمها كاملًا","basis":"n/a","en":"Rows in headline Hugging Face datasets with a complete size from the dataset viewer","method":"sql/metrics.sql#ADI-SIZE-01","notes":"Rows mean different things in text, speech and image datasets; the figure is a row count, not a measure of data. Coverage is the share of headline Hub datasets with a complete size. Copies count once. One dataset holds 29.56% of these rows, more than any other.","notes_ar":"تعني الصفوف أشياء مختلفة في مجموعات النص والكلام والصور؛ فالرقم عدد صفوف وليس مقياسًا لكمية البيانات. التغطية نسبة المجموعات الرئيسية في المنصة التي لها حجم كامل. وتُعدّ النسخ مرة واحدة. وتضم مجموعة واحدة 29.56% من هذه الصفوف، أكثر من أي مجموعة أخرى."},"ADI-SIZE-02":{"ar":"حجم ملفات Parquet بالبايت للمجموعات الرئيسية في Hugging Face التي يعطي عارض البيانات حجمها كاملًا","basis":"n/a","en":"Parquet bytes of headline Hugging Face datasets with a complete size from the dataset viewer","method":"sql/metrics.sql#ADI-SIZE-02","notes":"Same population as ADI-SIZE-01. Copies count once.","notes_ar":"المجموعات نفسها في ADI-SIZE-01. وتُعدّ النسخ مرة واحدة."},"ADI-SIZE-03":{"ar":"المجموعات الرئيسية في Hugging Face حسب فئة الحجم في المنصة","basis":"n/a","en":"Headline Hugging Face datasets by Hub size category","method":"sql/metrics.sql#ADI-SIZE-03","notes":"The size category the uploader or the Hub declares (number of rows). Coverage is the share with a category.","notes_ar":"فئة الحجم التي يعلنها الرافع أو المنصة (عدد الصفوف). التغطية نسبة المجموعات التي لها فئة."},"ADI-SIZE-04":{"ar":"ساعات الكلام العربي المفتوح والقابل للاستخدام التجاري، ساعات الصوت المنشور بعد خصم التداخل (منقولة)","basis":"declared","en":"Open, commercially usable Arabic speech, released audio hours, overlap-adjusted (quoted)","method":"quoted: Bayanat-Labs/arabic-speech-hours feed/latest.json @ 696cc8e, as of 2026-10-30","notes":"Quoted from the Open Arabic Speech Hours Counter with its as-of date; not recomputed here.","notes_ar":"منقولة عن عدّاد ساعات الكلام العربي المفتوح مع تاريخ سريانها؛ ولا يُعاد حسابها هنا."},"ADI-TSK-01":{"ar":"المجموعات الرئيسية حسب عائلة المهمة","basis":"n/a","en":"Headline datasets by task family","method":"sql/metrics.sql#ADI-TSK-01","notes":"From Hub task categories, task ids and uploader tags, and Masader's tasks. A dataset can carry several families, so shares add up to more than 100%. Coverage is the share with any task declared.","notes_ar":"من فئات المهام ومعرّفاتها في المنصة ووسوم الرافع ومهام Masader. قد تحمل المجموعة أكثر من عائلة، فمجموع النسب يتجاوز 100%. التغطية نسبة المجموعات التي تعلن أي مهمة."},"ADI-TSK-02":{"ar":"المجموعات الرئيسية التي لا تعلن مهمة","basis":"n/a","en":"Headline datasets with no task declared","method":"sql/metrics.sql#ADI-TSK-02","notes":"","notes_ar":""}},"facts":{"largest_rows_share_pct":"29.56"},"files":{"aggregates":"arabic-data-index_2026-11.csv","entities":"entities_2026-11.csv.gz"},"groups":{"CNT":{"ar":"الأعداد","en":"Counts"},"CON":{"ar":"التركّز","en":"Concentration"},"DIA":{"ar":"اللهجات وأنواع العربية","en":"Varieties and dialects"},"GRW":{"ar":"النمو","en":"Growth"},"HLT":{"ar":"الوصول وحالة العارض","en":"Access and viewer health"},"LIC":{"ar":"التراخيص (المعلنة)","en":"Licences (declared)"},"MOD":{"ar":"نوع البيانات","en":"Modality"},"SIZE":{"ar":"الحجم","en":"Size"},"TSK":{"ar":"المهام","en":"Tasks"}},"labels":{"arabic_share":{"bilingual":{"ar":"العربية ولغة أخرى","en":"Arabic and one other language"},"massive":{"ar":"10 لغات أو أكثر (تُعدّ وحدها)","en":"10 or more languages (counted apart)"},"multilingual":{"ar":"من 3 إلى 9 لغات","en":"3 to 9 languages"},"only":{"ar":"العربية فقط","en":"Arabic only"}},"dialect":{"Classical":{"ar":"العربية الكلاسيكية","en":"Classical Arabic"},"Darija":{"ar":"المغربية (الدارجة)","en":"Moroccan (Darija)"},"Egyptian":{"ar":"المصرية","en":"Egyptian"},"Gulf":{"ar":"الخليجية","en":"Gulf"},"Hijazi":{"ar":"الحجازية","en":"Hijazi"},"Iraqi":{"ar":"العراقية","en":"Iraqi"},"Levantine":{"ar":"الشامية","en":"Levantine"},"MSA":{"ar":"الفصحى المعاصرة","en":"Modern Standard Arabic"},"Maghrebi":{"ar":"المغاربية (غير المغربية)","en":"Maghrebi (other than Moroccan)"},"Najdi":{"ar":"النجدية","en":"Najdi"},"Sudanese":{"ar":"السودانية","en":"Sudanese"},"Yemeni":{"ar":"اليمنية","en":"Yemeni"},"mixed":{"ar":"مختلطة (كما يذكر المصدر)","en":"Mixed (as the source states)"},"other":{"ar":"لهجات أخرى","en":"Other varieties"},"unspecified":{"ar":"غير محددة","en":"Not specified"}},"licence_class":{"none":{"ar":"لا ترخيص معلن","en":"No licence declared"},"open-commercial":{"ar":"مفتوح ويسمح بالاستخدام التجاري","en":"Open, commercial use allowed"},"open-noncommercial":{"ar":"مفتوح لغير الأغراض التجارية فقط","en":"Open, non-commercial only"},"restricted":{"ar":"مقيّد (بلا اشتقاق أو للبحث أو باتفاقية)","en":"Restricted (no derivatives, research or agreement)"},"unclear":{"ar":"شروط أخرى أو خاصة أو غير معروفة","en":"Other, custom or unknown terms"}},"licence_fine_class":{"nc":{"ar":"غير تجاري (CC BY-NC وCC BY-NC-SA)","en":"Non-commercial (CC BY-NC, CC BY-NC-SA)"},"nd":{"ar":"بلا أعمال مشتقة (CC BY-ND وCC BY-NC-ND)","en":"No derivatives (CC BY-ND, CC BY-NC-ND)"},"none":{"ar":"لا ترخيص معلن","en":"No licence declared"},"other":{"ar":"شروط أخرى أو خاصة (other وcustom وتراخيص RAIL والنماذج وcc دون إصدار)","en":"Other or custom terms (other, custom, RAIL and model licences, unversioned cc)"},"permissive":{"ar":"متساهل (CC0 وCC BY وODC-By وPDDL وCDLA-Permissive)","en":"Permissive (CC0, CC BY, ODC-By, PDDL, CDLA-Permissive)"},"research-only":{"ar":"للبحث أو بموجب اتفاقية (LDC وELRA)","en":"Research or agreement-based (LDC, ELRA end-user)"},"several":{"ar":"عدة تراخيص من فئات مختلفة","en":"Several licences in different classes"},"share-alike":{"ar":"المشاركة بالمثل (CC BY-SA وODbL وCDLA-Sharing وGFDL)","en":"Share-alike (CC BY-SA, ODbL, CDLA-Sharing, GFDL)"},"software-licence-on-data":{"ar":"ترخيص برمجيات معلن للبيانات (MIT وApache وBSD وGPL وما يشبهها)","en":"Software licence declared for data (MIT, Apache, BSD, GPL and similar)"},"unknown":{"ar":"معلن بأنه غير معروف","en":"Declared as unknown"}},"masader_hub_status":{"hub-link-not-found":{"ar":"رابط المنصة لا يعمل","en":"Hub link does not resolve"},"hub-link-other-dataset":{"ar":"رابط المنصة يشير إلى مجموعة أخرى","en":"Hub link names another dataset"},"no-hub-link":{"ar":"دون رابط في Hugging Face","en":"No Hugging Face link"},"on-hub-not-tagged-arabic":{"ar":"في Hugging Face دون وسم العربية","en":"On Hugging Face, no Arabic tag"},"on-hub-tagged-arabic":{"ar":"في Hugging Face وموسومة بالعربية","en":"On Hugging Face, tagged Arabic"}},"modality":{"document":{"ar":"مستندات","en":"Document"},"image":{"ar":"صور","en":"Image"},"multimodal":{"ar":"متعدد الوسائط","en":"Multimodal"},"speech":{"ar":"كلام وصوت","en":"Speech and audio"},"structured":{"ar":"جداول وبيانات مهيكلة","en":"Tabular or structured"},"text":{"ar":"نص","en":"Text"},"unknown":{"ar":"غير معلن","en":"Not declared"},"video":{"ar":"فيديو","en":"Video"}},"platform":{"hf":{"ar":"Hugging Face فقط","en":"Hugging Face only"},"hf+masader":{"ar":"كلاهما","en":"Both"},"masader":{"ar":"Masader فقط","en":"Masader only"}},"size_status":{"empty":{"ar":"دون ملفات بيانات","en":"No data files"},"error":{"ar":"خطأ آخر","en":"Other error"},"gated":{"ar":"مقيّدة بشروط (لم تُطلب)","en":"Gated (not asked)"},"ok":{"ar":"حجم كامل","en":"Complete size"},"partial":{"ar":"حجم جزئي","en":"Partial size"},"unsupported-script":{"ar":"تعتمد على شيفرة تحميل خاصة","en":"Runs its own loading code"},"viewer-unsupported":{"ar":"العارض متوقف أو غير مدعوم","en":"Viewer off or not supported"}},"task":{"ASR":{"ar":"التعرف على الكلام","en":"Speech recognition"},"MT":{"ar":"الترجمة","en":"Translation"},"NER":{"ar":"الكيانات المسماة","en":"Named entities"},"OCR":{"ar":"التعرف الضوئي والخط اليدوي","en":"OCR and handwriting"},"QA":{"ar":"الإجابة عن الأسئلة","en":"Question answering"},"TTS":{"ar":"تحويل النص إلى كلام","en":"Speech synthesis"},"classification":{"ar":"التصنيف","en":"Classification"},"dialect-ID":{"ar":"تحديد اللهجة","en":"Dialect identification"},"instruction":{"ar":"ضبط التعليمات","en":"Instruction tuning"},"other":{"ar":"مهام أخرى","en":"Other tasks"},"preference":{"ar":"التفضيلات والتقييم","en":"Preference and feedback"},"retrieval":{"ar":"الاسترجاع والتشابه","en":"Retrieval and similarity"},"sentiment":{"ar":"تحليل المشاعر","en":"Sentiment"}}},"mode":"declared-only","read":{"hub_pages_first":"2026-11-01T06:05:32.537Z","hub_pages_last":"2026-11-01T06:06:07.211Z","masader_clone":"2026-11-01T06:07:22Z","viewer_first":"2026-11-01T06:07:08.203Z","viewer_last":"2026-11-01T08:35:24.845Z","viewer_requery_first":"2026-11-01T09:31:02.522Z","viewer_requery_last":"2026-11-01T09:41:17.753Z"},"requery":{"calls":609,"first":"2026-11-01T09:31:02.522Z","gap_hours_max":3.4,"gap_hours_median":2.48,"gap_hours_min":1.1,"last":"2026-11-01T09:41:17.753Z","now_ok":1,"still_failed":608},"revisions":{"masader_commit":"ce2c342","rights_index":"a422db2"},"rows":{"ADI-CNT-01":[{"c":null,"d":null,"den":null,"n":3564,"u":"datasets","v":3564.0}],"ADI-CNT-02":[{"c":null,"d":null,"den":null,"n":4333,"u":"repos","v":4333.0}],"ADI-CNT-03":[{"c":null,"d":"only","den":4888,"n":2210,"u":"percent","v":45.21},{"c":null,"d":"bilingual","den":4888,"n":546,"u":"percent","v":11.17},{"c":null,"d":"multilingual","den":4888,"n":808,"u":"percent","v":16.53},{"c":null,"d":"massive","den":4888,"n":1324,"u":"percent","v":27.09}],"ADI-CNT-04":[{"c":null,"d":"hf","den":3564,"n":2589,"u":"percent","v":72.64},{"c":null,"d":"hf+masader","den":3564,"n":213,"u":"percent","v":5.98},{"c":null,"d":"masader","den":3564,"n":762,"u":"percent","v":21.38}],"ADI-CNT-05":[{"c":null,"d":null,"den":null,"n":224,"u":"repos","v":224.0}],"ADI-CNT-06":[{"c":null,"d":"on-hub-tagged-arabic","den":975,"n":213,"u":"percent","v":21.85},{"c":null,"d":"on-hub-not-tagged-arabic","den":975,"n":249,"u":"percent","v":25.54},{"c":null,"d":"hub-link-not-found","den":975,"n":6,"u":"percent","v":0.62},{"c":null,"d":"hub-link-other-dataset","den":975,"n":2,"u":"percent","v":0.21},{"c":null,"d":"no-hub-link","den":975,"n":505,"u":"percent","v":51.79}],"ADI-CNT-07":[{"c":null,"d":null,"den":null,"n":1163,"u":"entries","v":1163.0}],"ADI-CON-01":[{"c":null,"d":null,"den":2802,"n":392,"u":"percent","v":13.99}],"ADI-CON-02":[{"c":null,"d":null,"den":1414715,"n":868390,"u":"percent","v":61.38}],"ADI-CON-03":[{"c":null,"d":"ieasybooks-org/prophet-mosque-library","den":null,"n":376883,"u":"downloads","v":376883.0},{"c":null,"d":"ieasybooks-org/shamela-waqfeya-library","den":null,"n":125382,"u":"downloads","v":125382.0},{"c":null,"d":"ieasybooks-org/waqfeya-library","den":null,"n":122571,"u":"downloads","v":122571.0},{"c":null,"d":"AuthenticIlm/Shamela4_Full_DB","den":null,"n":47297,"u":"downloads","v":47297.0},{"c":null,"d":"zaibihassan/Quranic-Recitation-Data","den":null,"n":36221,"u":"downloads","v":36221.0},{"c":null,"d":"MohamedRashad/arabic-books","den":null,"n":18315,"u":"downloads","v":18315.0},{"c":null,"d":"lightonai/multilingual-embeddings-pre-training-curated","den":null,"n":16805,"u":"downloads","v":16805.0},{"c":null,"d":"philippesaade/Wikidata_Vectors_0.2","den":null,"n":15397,"u":"downloads","v":15397.0},{"c":null,"d":"HeshamHaroon/tahqiq-results","den":null,"n":13218,"u":"downloads","v":13218.0},{"c":null,"d":"D2I-CUHK-Shenzhen/FormStruct-Bench","den":null,"n":11406,"u":"downloads","v":11406.0},{"c":null,"d":"Helsinki-NLP/multiun","den":null,"n":9837,"u":"downloads","v":9837.0},{"c":null,"d":"CALM/arwiki","den":null,"n":9658,"u":"downloads","v":9658.0},{"c":null,"d":"ieasybooks-org/prophet-mosque-library-compressed","den":null,"n":9623,"u":"downloads","v":9623.0},{"c":null,"d":"gijl/agentic-thinker-v1","den":null,"n":8924,"u":"downloads","v":8924.0},{"c":null,"d":"ieasybooks-org/waqfeya-library-compressed","den":null,"n":8660,"u":"downloads","v":8660.0},{"c":null,"d":"riotu-lab/SARD","den":null,"n":8508,"u":"downloads","v":8508.0},{"c":null,"d":"Djebbi/UltraData-Math","den":null,"n":8085,"u":"downloads","v":8085.0},{"c":null,"d":"khursanirevo/dialogue-episodes","den":null,"n":7596,"u":"downloads","v":7596.0},{"c":null,"d":"M-A-D/Mixed-Arabic-Datasets-Repo","den":null,"n":7044,"u":"downloads","v":7044.0},{"c":null,"d":"oddadmix/dialectal-arabic-lahgtna-v2","den":null,"n":6960,"u":"downloads","v":6960.0}],"ADI-DIA-01":[{"c":30.72,"d":"MSA","den":3564,"n":528,"u":"percent","v":14.81},{"c":30.72,"d":"Classical","den":3564,"n":47,"u":"percent","v":1.32},{"c":30.72,"d":"Gulf","den":3564,"n":78,"u":"percent","v":2.19},{"c":30.72,"d":"Najdi","den":3564,"n":6,"u":"percent","v":0.17},{"c":30.72,"d":"Hijazi","den":3564,"n":2,"u":"percent","v":0.06},{"c":30.72,"d":"Egyptian","den":3564,"n":146,"u":"percent","v":4.1},{"c":30.72,"d":"Levantine","den":3564,"n":108,"u":"percent","v":3.03},{"c":30.72,"d":"Iraqi","den":3564,"n":28,"u":"percent","v":0.79},{"c":30.72,"d":"Maghrebi","den":3564,"n":98,"u":"percent","v":2.75},{"c":30.72,"d":"Darija","den":3564,"n":106,"u":"percent","v":2.97},{"c":30.72,"d":"Sudanese","den":3564,"n":25,"u":"percent","v":0.7},{"c":30.72,"d":"Yemeni","den":3564,"n":20,"u":"percent","v":0.56},{"c":30.72,"d":"other","den":3564,"n":5,"u":"percent","v":0.14},{"c":30.72,"d":"mixed","den":3564,"n":282,"u":"percent","v":7.91},{"c":30.72,"d":"unspecified","den":3564,"n":2469,"u":"percent","v":69.28}],"ADI-DIA-02":[{"c":null,"d":null,"den":3564,"n":1095,"u":"percent","v":30.72}],"ADI-DIA-03":[{"c":null,"d":null,"den":3564,"n":361,"u":"percent","v":10.13}],"ADI-GRW-01":[{"c":null,"d":"before-2022-03","den":null,"n":32,"u":"datasets","v":32.0},{"c":null,"d":"2019-01","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2019-02","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2019-03","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2019-04","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2019-05","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2019-06","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2019-07","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2019-08","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2019-09","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2019-10","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2019-11","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2019-12","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2020-01","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2020-02","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2020-03","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2020-04","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2020-05","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2020-06","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2020-07","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2020-08","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2020-09","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2020-10","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2020-11","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2020-12","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2021-01","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2021-02","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2021-03","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2021-04","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2021-05","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2021-06","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2021-07","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2021-08","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2021-09","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2021-10","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2021-11","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2021-12","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2022-01","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2022-02","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2022-03","den":null,"n":3,"u":"datasets","v":3.0},{"c":null,"d":"2022-04","den":null,"n":2,"u":"datasets","v":2.0},{"c":null,"d":"2022-05","den":null,"n":19,"u":"datasets","v":19.0},{"c":null,"d":"2022-06","den":null,"n":2,"u":"datasets","v":2.0},{"c":null,"d":"2022-07","den":null,"n":3,"u":"datasets","v":3.0},{"c":null,"d":"2022-08","den":null,"n":1,"u":"datasets","v":1.0},{"c":null,"d":"2022-09","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2022-10","den":null,"n":0,"u":"datasets","v":0.0},{"c":null,"d":"2022-11","den":null,"n":4,"u":"datasets","v":4.0},{"c":null,"d":"2022-12","den":null,"n":4,"u":"datasets","v":4.0},{"c":null,"d":"2023-01","den":null,"n":3,"u":"datasets","v":3.0},{"c":null,"d":"2023-02","den":null,"n":2,"u":"datasets","v":2.0},{"c":null,"d":"2023-03","den":null,"n":9,"u":"datasets","v":9.0},{"c":null,"d":"2023-04","den":null,"n":11,"u":"datasets","v":11.0},{"c":null,"d":"2023-05","den":null,"n":6,"u":"datasets","v":6.0},{"c":null,"d":"2023-06","den":null,"n":9,"u":"datasets","v":9.0},{"c":null,"d":"2023-07","den":null,"n":14,"u":"datasets","v":14.0},{"c":null,"d":"2023-08","den":null,"n":11,"u":"datasets","v":11.0},{"c":null,"d":"2023-09","den":null,"n":18,"u":"datasets","v":18.0},{"c":null,"d":"2023-10","den":null,"n":12,"u":"datasets","v":12.0},{"c":null,"d":"2023-11","den":null,"n":6,"u":"datasets","v":6.0},{"c":null,"d":"2023-12","den":null,"n":12,"u":"datasets","v":12.0},{"c":null,"d":"2024-01","den":null,"n":13,"u":"datasets","v":13.0},{"c":null,"d":"2024-02","den":null,"n":32,"u":"datasets","v":32.0},{"c":null,"d":"2024-03","den":null,"n":26,"u":"datasets","v":26.0},{"c":null,"d":"2024-04","den":null,"n":37,"u":"datasets","v":37.0},{"c":null,"d":"2024-05","den":null,"n":62,"u":"datasets","v":62.0},{"c":null,"d":"2024-06","den":null,"n":29,"u":"datasets","v":29.0},{"c":null,"d":"2024-07","den":null,"n":37,"u":"datasets","v":37.0},{"c":null,"d":"2024-08","den":null,"n":28,"u":"datasets","v":28.0},{"c":null,"d":"2024-09","den":null,"n":36,"u":"datasets","v":36.0},{"c":null,"d":"2024-10","den":null,"n":24,"u":"datasets","v":24.0},{"c":null,"d":"2024-11","den":null,"n":43,"u":"datasets","v":43.0},{"c":null,"d":"2024-12","den":null,"n":31,"u":"datasets","v":31.0},{"c":null,"d":"2025-01","den":null,"n":40,"u":"datasets","v":40.0},{"c":null,"d":"2025-02","den":null,"n":53,"u":"datasets","v":53.0},{"c":null,"d":"2025-03","den":null,"n":35,"u":"datasets","v":35.0},{"c":null,"d":"2025-04","den":null,"n":38,"u":"datasets","v":38.0},{"c":null,"d":"2025-05","den":null,"n":71,"u":"datasets","v":71.0},{"c":null,"d":"2025-06","den":null,"n":30,"u":"datasets","v":30.0},{"c":null,"d":"2025-07","den":null,"n":70,"u":"datasets","v":70.0},{"c":null,"d":"2025-08","den":null,"n":32,"u":"datasets","v":32.0},{"c":null,"d":"2025-09","den":null,"n":63,"u":"datasets","v":63.0},{"c":null,"d":"2025-10","den":null,"n":54,"u":"datasets","v":54.0},{"c":null,"d":"2025-11","den":null,"n":37,"u":"datasets","v":37.0},{"c":null,"d":"2025-12","den":null,"n":72,"u":"datasets","v":72.0},{"c":null,"d":"2026-01","den":null,"n":83,"u":"datasets","v":83.0},{"c":null,"d":"2026-02","den":null,"n":95,"u":"datasets","v":95.0},{"c":null,"d":"2026-03","den":null,"n":87,"u":"datasets","v":87.0},{"c":null,"d":"2026-04","den":null,"n":156,"u":"datasets","v":156.0},{"c":null,"d":"2026-05","den":null,"n":131,"u":"datasets","v":131.0},{"c":null,"d":"2026-06","den":null,"n":136,"u":"datasets","v":136.0},{"c":null,"d":"2026-07","den":null,"n":115,"u":"datasets","v":115.0},{"c":null,"d":"2026-08","den":null,"n":223,"u":"datasets","v":223.0},{"c":null,"d":"2026-09","den":null,"n":194,"u":"datasets","v":194.0},{"c":null,"d":"2026-10","den":null,"n":404,"u":"datasets","v":404.0},{"c":null,"d":"2026-11","den":null,"n":2,"u":"datasets","v":2.0}],"ADI-GRW-02":[{"c":null,"d":"2026-10","den":null,"n":404,"u":"datasets","v":404.0}],"ADI-GRW-03":[{"c":null,"d":"2026","den":null,"n":1626,"u":"datasets","v":1626.0}],"ADI-GRW-04":[{"c":null,"d":"2001","den":null,"n":2,"u":"datasets","v":2.0},{"c":null,"d":"2002","den":null,"n":11,"u":"datasets","v":11.0},{"c":null,"d":"2003","den":null,"n":4,"u":"datasets","v":4.0},{"c":null,"d":"2004","den":null,"n":9,"u":"datasets","v":9.0},{"c":null,"d":"2005","den":null,"n":11,"u":"datasets","v":11.0},{"c":null,"d":"2006","den":null,"n":19,"u":"datasets","v":19.0},{"c":null,"d":"2007","den":null,"n":12,"u":"datasets","v":12.0},{"c":null,"d":"2008","den":null,"n":3,"u":"datasets","v":3.0},{"c":null,"d":"2009","den":null,"n":13,"u":"datasets","v":13.0},{"c":null,"d":"2010","den":null,"n":21,"u":"datasets","v":21.0},{"c":null,"d":"2011","den":null,"n":16,"u":"datasets","v":16.0},{"c":null,"d":"2012","den":null,"n":11,"u":"datasets","v":11.0},{"c":null,"d":"2013","den":null,"n":23,"u":"datasets","v":23.0},{"c":null,"d":"2014","den":null,"n":23,"u":"datasets","v":23.0},{"c":null,"d":"2015","den":null,"n":25,"u":"datasets","v":25.0},{"c":null,"d":"2016","den":null,"n":48,"u":"datasets","v":48.0},{"c":null,"d":"2017","den":null,"n":36,"u":"datasets","v":36.0},{"c":null,"d":"2018","den":null,"n":53,"u":"datasets","v":53.0},{"c":null,"d":"2019","den":null,"n":55,"u":"datasets","v":55.0},{"c":null,"d":"2020","den":null,"n":77,"u":"datasets","v":77.0},{"c":null,"d":"2021","den":null,"n":67,"u":"datasets","v":67.0},{"c":null,"d":"2022","den":null,"n":65,"u":"datasets","v":65.0},{"c":null,"d":"2023","den":null,"n":62,"u":"datasets","v":62.0},{"c":null,"d":"2024","den":null,"n":120,"u":"datasets","v":120.0},{"c":null,"d":"2025","den":null,"n":133,"u":"datasets","v":133.0},{"c":null,"d":"2026","den":null,"n":56,"u":"datasets","v":56.0}],"ADI-HLT-01":[{"c":null,"d":null,"den":2802,"n":254,"u":"percent","v":9.06}],"ADI-HLT-02":[{"c":90.94,"d":null,"den":2548,"n":2089,"u":"percent","v":81.99}],"ADI-HLT-03":[{"c":null,"d":"ok","den":2802,"n":2010,"u":"percent","v":71.73},{"c":null,"d":"partial","den":2802,"n":308,"u":"percent","v":10.99},{"c":null,"d":"gated","den":2802,"n":254,"u":"percent","v":9.06},{"c":null,"d":"unsupported-script","den":2802,"n":29,"u":"percent","v":1.03},{"c":null,"d":"viewer-unsupported","den":2802,"n":80,"u":"percent","v":2.86},{"c":null,"d":"empty","den":2802,"n":53,"u":"percent","v":1.89},{"c":null,"d":"error","den":2802,"n":68,"u":"percent","v":2.43}],"ADI-LIC-01":[{"c":null,"d":"open-commercial","den":3564,"n":1673,"u":"percent","v":46.94},{"c":null,"d":"open-noncommercial","den":3564,"n":330,"u":"percent","v":9.26},{"c":null,"d":"restricted","den":3564,"n":264,"u":"percent","v":7.41},{"c":null,"d":"unclear","den":3564,"n":844,"u":"percent","v":23.68},{"c":null,"d":"none","den":3564,"n":453,"u":"percent","v":12.71}],"ADI-LIC-02":[{"c":null,"d":"permissive","den":3564,"n":635,"u":"percent","v":17.82},{"c":null,"d":"share-alike","den":3564,"n":142,"u":"percent","v":3.98},{"c":null,"d":"software-licence-on-data","den":3564,"n":890,"u":"percent","v":24.97},{"c":null,"d":"nc","den":3564,"n":330,"u":"percent","v":9.26},{"c":null,"d":"nd","den":3564,"n":50,"u":"percent","v":1.4},{"c":null,"d":"research-only","den":3564,"n":214,"u":"percent","v":6.0},{"c":null,"d":"other","den":3564,"n":526,"u":"percent","v":14.76},{"c":null,"d":"unknown","den":3564,"n":318,"u":"percent","v":8.92},{"c":null,"d":"several","den":3564,"n":6,"u":"percent","v":0.17},{"c":null,"d":"none","den":3564,"n":453,"u":"percent","v":12.71}],"ADI-LIC-03":[{"c":null,"d":null,"den":3564,"n":893,"u":"percent","v":25.06}],"ADI-LIC-04":[{"c":null,"d":"text","den":2503,"n":1265,"u":"percent","v":50.54},{"c":null,"d":"speech","den":614,"n":157,"u":"percent","v":25.57},{"c":null,"d":"image","den":239,"n":129,"u":"percent","v":53.97},{"c":null,"d":"video","den":18,"n":6,"u":"percent","v":33.33},{"c":null,"d":"document","den":35,"n":24,"u":"percent","v":68.57},{"c":null,"d":"multimodal","den":25,"n":10,"u":"percent","v":40.0},{"c":null,"d":"structured","den":5,"n":5,"u":"percent","v":100.0},{"c":null,"d":"unknown","den":125,"n":77,"u":"percent","v":61.6}],"ADI-LIC-05":[{"c":null,"d":null,"den":2802,"n":472,"u":"percent","v":16.85}],"ADI-MOD-01":[{"c":96.49,"d":"text","den":3564,"n":2503,"u":"percent","v":70.23},{"c":96.49,"d":"speech","den":3564,"n":614,"u":"percent","v":17.23},{"c":96.49,"d":"image","den":3564,"n":239,"u":"percent","v":6.71},{"c":96.49,"d":"video","den":3564,"n":18,"u":"percent","v":0.51},{"c":96.49,"d":"document","den":3564,"n":35,"u":"percent","v":0.98},{"c":96.49,"d":"multimodal","den":3564,"n":25,"u":"percent","v":0.7},{"c":96.49,"d":"structured","den":3564,"n":5,"u":"percent","v":0.14},{"c":96.49,"d":"unknown","den":3564,"n":125,"u":"percent","v":3.51}],"ADI-SIZE-01":[{"c":71.73,"d":null,"den":null,"n":15228639299,"u":"rows","v":15228639299.0}],"ADI-SIZE-02":[{"c":71.73,"d":null,"den":null,"n":16208502476821,"u":"bytes","v":16208502476821.0}],"ADI-SIZE-03":[{"c":91.61,"d":"n<1K","den":2802,"n":568,"u":"percent","v":20.27},{"c":91.61,"d":"1K<n<10K","den":2802,"n":807,"u":"percent","v":28.8},{"c":91.61,"d":"10K<n<100K","den":2802,"n":627,"u":"percent","v":22.38},{"c":91.61,"d":"100K<n<1M","den":2802,"n":328,"u":"percent","v":11.71},{"c":91.61,"d":"1M<n<10M","den":2802,"n":128,"u":"percent","v":4.57},{"c":91.61,"d":"10M<n<100M","den":2802,"n":63,"u":"percent","v":2.25},{"c":91.61,"d":"100M<n<1B","den":2802,"n":29,"u":"percent","v":1.03},{"c":91.61,"d":"1B<n<10B","den":2802,"n":8,"u":"percent","v":0.29},{"c":91.61,"d":"10B<n<100B","den":2802,"n":3,"u":"percent","v":0.11},{"c":91.61,"d":"100B<n<1T","den":2802,"n":1,"u":"percent","v":0.04},{"c":91.61,"d":"n>1T","den":2802,"n":5,"u":"percent","v":0.18}],"ADI-SIZE-04":[{"c":null,"d":"open-commercial","den":null,"n":36220.98,"u":"hours","v":36220.98}],"ADI-TSK-01":[{"c":80.67,"d":"ASR","den":3564,"n":406,"u":"percent","v":11.39},{"c":80.67,"d":"TTS","den":3564,"n":160,"u":"percent","v":4.49},{"c":80.67,"d":"MT","den":3564,"n":435,"u":"percent","v":12.21},{"c":80.67,"d":"QA","den":3564,"n":518,"u":"percent","v":14.53},{"c":80.67,"d":"NER","den":3564,"n":80,"u":"percent","v":2.24},{"c":80.67,"d":"sentiment","den":3564,"n":146,"u":"percent","v":4.1},{"c":80.67,"d":"dialect-ID","den":3564,"n":61,"u":"percent","v":1.71},{"c":80.67,"d":"instruction","den":3564,"n":91,"u":"percent","v":2.55},{"c":80.67,"d":"preference","den":3564,"n":37,"u":"percent","v":1.04},{"c":80.67,"d":"retrieval","den":3564,"n":296,"u":"percent","v":8.31},{"c":80.67,"d":"OCR","den":3564,"n":112,"u":"percent","v":3.14},{"c":80.67,"d":"classification","den":3564,"n":701,"u":"percent","v":19.67},{"c":80.67,"d":"other","den":3564,"n":1127,"u":"percent","v":31.62}],"ADI-TSK-02":[{"c":null,"d":null,"den":3564,"n":689,"u":"percent","v":19.33}]},"snapshot_id":"2026-11","speech":{"as_of":"2026-10-30","hours":36220.98,"revision":"696cc8e"},"top":[{"dl":376883,"id":"ieasybooks-org/prophet-mosque-library","lic":"open-commercial","mod":"text"},{"dl":125382,"id":"ieasybooks-org/shamela-waqfeya-library","lic":"open-commercial","mod":"text"},{"dl":122571,"id":"ieasybooks-org/waqfeya-library","lic":"open-commercial","mod":"image"},{"dl":47297,"id":"AuthenticIlm/Shamela4_Full_DB","lic":"open-commercial","mod":"text"},{"dl":36221,"id":"zaibihassan/Quranic-Recitation-Data","lic":"open-commercial","mod":"speech"},{"dl":18315,"id":"MohamedRashad/arabic-books","lic":"open-commercial","mod":"text"},{"dl":16805,"id":"lightonai/multilingual-embeddings-pre-training-curated","lic":"none","mod":"text"},{"dl":15397,"id":"philippesaade/Wikidata_Vectors_0.2","lic":"open-commercial","mod":"text"},{"dl":13218,"id":"HeshamHaroon/tahqiq-results","lic":"open-commercial","mod":"speech"},{"dl":11406,"id":"D2I-CUHK-Shenzhen/FormStruct-Bench","lic":"unclear","mod":"image"},{"dl":9837,"id":"Helsinki-NLP/multiun","lic":"unclear","mod":"text"},{"dl":9658,"id":"CALM/arwiki","lic":"unclear","mod":"text"},{"dl":9623,"id":"ieasybooks-org/prophet-mosque-library-compressed","lic":"open-commercial","mod":"text"},{"dl":8924,"id":"gijl/agentic-thinker-v1","lic":"unclear","mod":"text"},{"dl":8660,"id":"ieasybooks-org/waqfeya-library-compressed","lic":"open-commercial","mod":"text"},{"dl":8508,"id":"riotu-lab/SARD","lic":"restricted","mod":"image"},{"dl":8085,"id":"Djebbi/UltraData-Math","lic":"open-commercial","mod":"text"},{"dl":7596,"id":"khursanirevo/dialogue-episodes","lic":"open-noncommercial","mod":"speech"},{"dl":7044,"id":"M-A-D/Mixed-Arabic-Datasets-Repo","lic":"none","mod":"text"},{"dl":6960,"id":"oddadmix/dialectal-arabic-lahgtna-v2","lic":"none","mod":"speech"}],"urls":{"dataset":"https://huggingface.co/datasets/Bayanat-Labs/arabic-data-index","github":"https://github.com/Bayanat-Labs/arabic-data-index","masader":"https://github.com/ARBML/masader","page_ar":"https://www.bayanatlabs.com/ar/open/arabic-data-index","page_en":"https://www.bayanatlabs.com/open/arabic-data-index","speech":"https://huggingface.co/datasets/Bayanat-Labs/arabic-speech-hours"}}; | |