Spaces:
Running
Running
Download index.html from danielrosehill/Hebrew-Datasets: direct link, hf CLI and curl.
- Browser
- Download file 49.8 kB
-
https://huggingface.co/spaces/danielrosehill/Hebrew-Datasets/resolve/main/index.html
- Command line
-
hf download hf://spaces/danielrosehill/Hebrew-Datasets/index.html
-
curl -L -o index.html https://huggingface.co/spaces/danielrosehill/Hebrew-Datasets/resolve/main/index.html
49.8 kB
| <!doctype html> | |
| <html lang="en"><head><meta charset="utf-8"><meta name="viewport" content="width=device-width,initial-scale=1"> | |
| <title>Hebrew Datasets</title> | |
| <style> | |
| body{font-family:system-ui,sans-serif;margin:0;color:#1d1d1f;background:#fafafa} | |
| header{padding:24px 32px;background:#fff;border-bottom:1px solid #e5e5e5} | |
| h1{margin:0 0 6px;font-size:1.6rem} header p{margin:4px 0;color:#555} | |
| .bar{position:sticky;top:0;background:#fafafa;padding:12px 32px;border-bottom:1px solid #e5e5e5;display:flex;gap:8px;flex-wrap:wrap;align-items:center} | |
| input{padding:8px 12px;font-size:1rem;border:1px solid #ccc;border-radius:8px;min-width:260px} | |
| button{padding:6px 12px;border:1px solid #ccc;border-radius:16px;background:#fff;cursor:pointer;font-size:.85rem} | |
| button.on{background:#1d1d1f;color:#fff;border-color:#1d1d1f} | |
| main{padding:8px 32px 48px} h2{margin-top:32px} h3{color:#444;font-size:1rem;margin:18px 0 6px} | |
| table{border-collapse:collapse;width:100%;background:#fff;font-size:.9rem} | |
| th,td{text-align:left;padding:6px 10px;border-bottom:1px solid #eee;vertical-align:top} th{background:#f3f3f3} | |
| a{color:#0b57d0;text-decoration:none} a:hover{text-decoration:underline} .hidden{display:none} | |
| footer{padding:24px 32px;color:#777;font-size:.85rem} | |
| </style></head><body> | |
| <header><h1>Hebrew Datasets</h1><p>Searchable catalogue of Hebrew-language datasets: speech and audio, sentence datasets, text corpora, translation and NLP tasks. Hebrew-specific datasets are kept apart from multilingual datasets that include Hebrew.</p><p><a href="https://github.com/danielrosehill/Hebrew-Datasets" target="_blank">Source list on GitHub</a> · <a href="https://huggingface.co/spaces/danielrosehill/Hebrew-AI-Models" target="_blank">Hebrew AI Models</a> · <a href="https://huggingface.co/danielrosehill/collections" target="_blank">Curated collections</a></p></header> | |
| <div class="bar"><input id="q" placeholder="Search names, authors, descriptions..." autofocus><span id="chips"></span></div> | |
| <main id="main"></main> | |
| <footer>Generated from README.md of <a href="https://github.com/danielrosehill/Hebrew-Datasets">danielrosehill/Hebrew-Datasets</a> on 2026-11-18.</footer> | |
| <script> | |
| const DATA=[{"name": "Audio and Speech", "tables": [{"subsection": "Hebrew-Specific Datasets", "columns": ["Name", "Description", "Details", "Links"], "rows": [{"cells": ["<a href=\"https://huggingface.co/datasets/shunyalabs/hebrew-speech-dataset\" target=\"_blank\" rel=\"noopener\">hebrew-speech-dataset</a>", "Hebrew speech with transcripts, 16 kHz.", "Author: shunyalabs · Size: 1K – 10K rows", "<a href=\"https://huggingface.co/datasets/shunyalabs/hebrew-speech-dataset\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[hebrew-speech-dataset](https://huggingface.co/datasets/shunyalabs/hebrew-speech-dataset) hebrew speech with transcripts, 16 khz. author: shunyalabs · size: 1k – 10k rows [dataset](https://huggingface.co/datasets/shunyalabs/hebrew-speech-dataset)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/sleeping-ai/Hebrew-talk\" target=\"_blank\" rel=\"noopener\">Hebrew-talk</a>", "Hebrew speech with transcripts (audio and text columns).", "Author: sleeping-ai · Size: 10K – 100K rows · License: mit", "<a href=\"https://huggingface.co/datasets/sleeping-ai/Hebrew-talk\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[hebrew-talk](https://huggingface.co/datasets/sleeping-ai/hebrew-talk) hebrew speech with transcripts (audio and text columns). author: sleeping-ai · size: 10k – 100k rows · license: mit [dataset](https://huggingface.co/datasets/sleeping-ai/hebrew-talk)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/verbit/hebrew_medical_audio\" target=\"_blank\" rel=\"noopener\">hebrew_medical_audio</a>", "Hebrew medical-domain audio (gated).", "Author: verbit · Size: 1K – 10K rows · License: cc-by-nc-4.0", "<a href=\"https://huggingface.co/datasets/verbit/hebrew_medical_audio\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[hebrew_medical_audio](https://huggingface.co/datasets/verbit/hebrew_medical_audio) hebrew medical-domain audio (gated). author: verbit · size: 1k – 10k rows · license: cc-by-nc-4.0 [dataset](https://huggingface.co/datasets/verbit/hebrew_medical_audio)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/imvladikon/hebrew_speech_campus\" target=\"_blank\" rel=\"noopener\">hebrew_speech_campus</a>", "Hebrew speech from Campus IL video lectures, with subtitles aligned to the audio.", "Author: imvladikon · Size: 10K – 100K rows", "<a href=\"https://huggingface.co/datasets/imvladikon/hebrew_speech_campus\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[hebrew_speech_campus](https://huggingface.co/datasets/imvladikon/hebrew_speech_campus) hebrew speech from campus il video lectures, with subtitles aligned to the audio. author: imvladikon · size: 10k – 100k rows [dataset](https://huggingface.co/datasets/imvladikon/hebrew_speech_campus)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/imvladikon/hebrew_speech_coursera\" target=\"_blank\" rel=\"noopener\">hebrew_speech_coursera</a>", "Hebrew speech recognition dataset from Coursera course audio.", "Author: imvladikon · Size: 10K – 100K rows", "<a href=\"https://huggingface.co/datasets/imvladikon/hebrew_speech_coursera\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[hebrew_speech_coursera](https://huggingface.co/datasets/imvladikon/hebrew_speech_coursera) hebrew speech recognition dataset from coursera course audio. author: imvladikon · size: 10k – 100k rows [dataset](https://huggingface.co/datasets/imvladikon/hebrew_speech_coursera)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/imvladikon/hebrew_speech_kan\" target=\"_blank\" rel=\"noopener\">hebrew_speech_kan</a>", "Hebrew speech for ASR (Kan broadcast audio with transcripts).", "Author: imvladikon · Size: 10K – 100K rows", "<a href=\"https://huggingface.co/datasets/imvladikon/hebrew_speech_kan\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[hebrew_speech_kan](https://huggingface.co/datasets/imvladikon/hebrew_speech_kan) hebrew speech for asr (kan broadcast audio with transcripts). author: imvladikon · size: 10k – 100k rows [dataset](https://huggingface.co/datasets/imvladikon/hebrew_speech_kan)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/micsell/hebrew_speech_kan_nikud\" target=\"_blank\" rel=\"noopener\">hebrew_speech_kan_nikud</a>", "Kan Hebrew speech with vocalised (nikud) transcripts.", "Author: micsell · Size: 10K – 100K rows", "<a href=\"https://huggingface.co/datasets/micsell/hebrew_speech_kan_nikud\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[hebrew_speech_kan_nikud](https://huggingface.co/datasets/micsell/hebrew_speech_kan_nikud) kan hebrew speech with vocalised (nikud) transcripts. author: micsell · size: 10k – 100k rows [dataset](https://huggingface.co/datasets/micsell/hebrew_speech_kan_nikud)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/upai-inc/saspeech\" target=\"_blank\" rel=\"noopener\">saspeech</a>", "Single-speaker studio Hebrew speech (Shaul Amsterdamski), gold-standard subset of the OpenSLR 134 corpus; for TTS.", "Author: upai-inc · Size: ~4 hours · License: other", "<a href=\"https://huggingface.co/datasets/upai-inc/saspeech\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[saspeech](https://huggingface.co/datasets/upai-inc/saspeech) single-speaker studio hebrew speech (shaul amsterdamski), gold-standard subset of the openslr 134 corpus; for tts. author: upai-inc · size: ~4 hours · license: other [dataset](https://huggingface.co/datasets/upai-inc/saspeech)"}]}, {"subsection": "Hebrish / danielrosehill", "columns": ["Name", "Description", "Details", "Links"], "rows": [{"cells": ["<a href=\"https://huggingface.co/datasets/Hebrish/English-Hebrew-Codeswitching-ASR-Benchmark\" target=\"_blank\" rel=\"noopener\">English-Hebrew-Codeswitching-ASR-Benchmark</a>", "Benchmark test set for English-Hebrew code-switching ASR.", "Author: Hebrish · Size: <1K rows · License: cc-by-4.0", "<a href=\"https://huggingface.co/datasets/Hebrish/English-Hebrew-Codeswitching-ASR-Benchmark\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[english-hebrew-codeswitching-asr-benchmark](https://huggingface.co/datasets/hebrish/english-hebrew-codeswitching-asr-benchmark) benchmark test set for english-hebrew code-switching asr. author: hebrish · size: <1k rows · license: cc-by-4.0 [dataset](https://huggingface.co/datasets/hebrish/english-hebrew-codeswitching-asr-benchmark)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/danielrosehill/English-Hebrew-Codeswitching-Sentences\" target=\"_blank\" rel=\"noopener\">English-Hebrew-Codeswitching-Sentences</a>", "English-Hebrew code-switching sentences read aloud, for ASR training.", "Author: danielrosehill · Size: 10K – 100K rows · License: cc-by-4.0", "<a href=\"https://huggingface.co/datasets/danielrosehill/English-Hebrew-Codeswitching-Sentences\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[english-hebrew-codeswitching-sentences](https://huggingface.co/datasets/danielrosehill/english-hebrew-codeswitching-sentences) english-hebrew code-switching sentences read aloud, for asr training. author: danielrosehill · size: 10k – 100k rows · license: cc-by-4.0 [dataset](https://huggingface.co/datasets/danielrosehill/english-hebrew-codeswitching-sentences)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/Hebrish/English-Hebrew-Mixed-Sentences\" target=\"_blank\" rel=\"noopener\">English-Hebrew-Mixed-Sentences</a>", "\"Hebrish\": English sentences mixed with Hebrew, audio dataset.", "Author: Hebrish · Size: <1K rows · License: mit", "<a href=\"https://huggingface.co/datasets/Hebrish/English-Hebrew-Mixed-Sentences\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[english-hebrew-mixed-sentences](https://huggingface.co/datasets/hebrish/english-hebrew-mixed-sentences) \"hebrish\": english sentences mixed with hebrew, audio dataset. author: hebrish · size: <1k rows · license: mit [dataset](https://huggingface.co/datasets/hebrish/english-hebrew-mixed-sentences)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/Hebrish/Hebrish-TTS-Voice-Recordings\" target=\"_blank\" rel=\"noopener\">Hebrish-TTS-Voice-Recordings</a>", "English-Hebrew voice recordings for TTS.", "Author: Hebrish · Size: 10K – 100K rows · License: cc-by-nc-4.0", "<a href=\"https://huggingface.co/datasets/Hebrish/Hebrish-TTS-Voice-Recordings\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[hebrish-tts-voice-recordings](https://huggingface.co/datasets/hebrish/hebrish-tts-voice-recordings) english-hebrew voice recordings for tts. author: hebrish · size: 10k – 100k rows · license: cc-by-nc-4.0 [dataset](https://huggingface.co/datasets/hebrish/hebrish-tts-voice-recordings)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/Hebrish/Hebrish-Validation\" target=\"_blank\" rel=\"noopener\">Hebrish-Validation</a>", "Validation benchmark for English-Hebrew code-switching ASR: roughly one-minute reads of a fixed script.", "Author: Hebrish · Size: <1K rows · License: cc-by-4.0", "<a href=\"https://huggingface.co/datasets/Hebrish/Hebrish-Validation\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[hebrish-validation](https://huggingface.co/datasets/hebrish/hebrish-validation) validation benchmark for english-hebrew code-switching asr: roughly one-minute reads of a fixed script. author: hebrish · size: <1k rows · license: cc-by-4.0 [dataset](https://huggingface.co/datasets/hebrish/hebrish-validation)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/Hebrish/Israeli-Name-Sentences\" target=\"_blank\" rel=\"noopener\">Israeli-Name-Sentences</a>", "Sentences with Israeli names, English-Hebrew code-switching, for ASR.", "Author: Hebrish · Size: <1K rows · License: cc-by-4.0", "<a href=\"https://huggingface.co/datasets/Hebrish/Israeli-Name-Sentences\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[israeli-name-sentences](https://huggingface.co/datasets/hebrish/israeli-name-sentences) sentences with israeli names, english-hebrew code-switching, for asr. author: hebrish · size: <1k rows · license: cc-by-4.0 [dataset](https://huggingface.co/datasets/hebrish/israeli-name-sentences)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/Hebrish/Jewish-Religious-Terminology-Sentences\" target=\"_blank\" rel=\"noopener\">Jewish-Religious-Terminology-Sentences</a>", "Sentences with Jewish religious terminology, English-Hebrew code-switching, for ASR.", "Author: Hebrish · Size: 1K – 10K rows · License: cc-by-4.0", "<a href=\"https://huggingface.co/datasets/Hebrish/Jewish-Religious-Terminology-Sentences\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[jewish-religious-terminology-sentences](https://huggingface.co/datasets/hebrish/jewish-religious-terminology-sentences) sentences with jewish religious terminology, english-hebrew code-switching, for asr. author: hebrish · size: 1k – 10k rows · license: cc-by-4.0 [dataset](https://huggingface.co/datasets/hebrish/jewish-religious-terminology-sentences)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/Hebrish/Judaica-Sentences\" target=\"_blank\" rel=\"noopener\">Judaica-Sentences</a>", "English sentences from traditional Jewish works with Hebrew terms read in; code-switching ASR.", "Author: Hebrish · Size: 1K – 10K rows · License: cc-by-4.0", "<a href=\"https://huggingface.co/datasets/Hebrish/Judaica-Sentences\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[judaica-sentences](https://huggingface.co/datasets/hebrish/judaica-sentences) english sentences from traditional jewish works with hebrew terms read in; code-switching asr. author: hebrish · size: 1k – 10k rows · license: cc-by-4.0 [dataset](https://huggingface.co/datasets/hebrish/judaica-sentences)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/Hebrish/Noisy-Condition-Sentences\" target=\"_blank\" rel=\"noopener\">Noisy-Condition-Sentences</a>", "Code-switching sentences recorded under noisy conditions, for ASR robustness.", "Author: Hebrish · Size: 10K – 100K rows · License: cc-by-4.0", "<a href=\"https://huggingface.co/datasets/Hebrish/Noisy-Condition-Sentences\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[noisy-condition-sentences](https://huggingface.co/datasets/hebrish/noisy-condition-sentences) code-switching sentences recorded under noisy conditions, for asr robustness. author: hebrish · size: 10k – 100k rows · license: cc-by-4.0 [dataset](https://huggingface.co/datasets/hebrish/noisy-condition-sentences)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/Hebrish/Pronunciation-Variants\" target=\"_blank\" rel=\"noopener\">Pronunciation-Variants</a>", "Takes where a word is deliberately said one particular way (pronunciation variants), for ASR robustness.", "Author: Hebrish · Size: <1K rows · License: cc-by-4.0", "<a href=\"https://huggingface.co/datasets/Hebrish/Pronunciation-Variants\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[pronunciation-variants](https://huggingface.co/datasets/hebrish/pronunciation-variants) takes where a word is deliberately said one particular way (pronunciation variants), for asr robustness. author: hebrish · size: <1k rows · license: cc-by-4.0 [dataset](https://huggingface.co/datasets/hebrish/pronunciation-variants)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/danielrosehill/Read-Aloud-Voice-Sentences\" target=\"_blank\" rel=\"noopener\">Read-Aloud-Voice-Sentences</a>", "Master set of read-aloud takes from the Hebrish capture app (English with Hebrew code-switching); the split-out datasets are copies of its rows.", "Author: danielrosehill · Size: 10K – 100K rows · License: cc-by-4.0", "<a href=\"https://huggingface.co/datasets/danielrosehill/Read-Aloud-Voice-Sentences\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[read-aloud-voice-sentences](https://huggingface.co/datasets/danielrosehill/read-aloud-voice-sentences) master set of read-aloud takes from the hebrish capture app (english with hebrew code-switching); the split-out datasets are copies of its rows. author: danielrosehill · size: 10k – 100k rows · license: cc-by-4.0 [dataset](https://huggingface.co/datasets/danielrosehill/read-aloud-voice-sentences)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/danielrosehill/Small-STT-Eval-Audio-Dataset\" target=\"_blank\" rel=\"noopener\">Small-STT-Eval-Audio-Dataset</a>", "Small STT evaluation set: 92 audio samples with ground truth, covering technical vocabulary and English/Hebrew code-switching.", "Author: danielrosehill · Size: 92 samples · License: cc-by-4.0", "<a href=\"https://huggingface.co/datasets/danielrosehill/Small-STT-Eval-Audio-Dataset\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[small-stt-eval-audio-dataset](https://huggingface.co/datasets/danielrosehill/small-stt-eval-audio-dataset) small stt evaluation set: 92 audio samples with ground truth, covering technical vocabulary and english/hebrew code-switching. author: danielrosehill · size: 92 samples · license: cc-by-4.0 [dataset](https://huggingface.co/datasets/danielrosehill/small-stt-eval-audio-dataset)"}]}, {"subsection": "Multilingual datasets with a Hebrew portion", "columns": ["Name", "Description", "Details", "Links"], "rows": [{"cells": ["<a href=\"https://huggingface.co/datasets/google/fleurs\" target=\"_blank\" rel=\"noopener\">fleurs</a>", "FLEURS speech benchmark; Hebrew is the `he_il` config.", "Author: google · Size: 100K – 1M rows · License: cc-by-4.0", "<a href=\"https://huggingface.co/datasets/google/fleurs\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[fleurs](https://huggingface.co/datasets/google/fleurs) fleurs speech benchmark; hebrew is the `he_il` config. author: google · size: 100k – 1m rows · license: cc-by-4.0 [dataset](https://huggingface.co/datasets/google/fleurs)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/espnet/yodas\" target=\"_blank\" rel=\"noopener\">yodas</a>", "YODAS multilingual YouTube speech; Hebrew is the `iw000` subset.", "Author: espnet · License: cc-by-3.0", "<a href=\"https://huggingface.co/datasets/espnet/yodas\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[yodas](https://huggingface.co/datasets/espnet/yodas) yodas multilingual youtube speech; hebrew is the `iw000` subset. author: espnet · license: cc-by-3.0 [dataset](https://huggingface.co/datasets/espnet/yodas)"}]}]}, {"name": "Instruction and Chat", "tables": [{"subsection": null, "columns": ["Name", "Description", "Details", "Links"], "rows": [{"cells": ["<a href=\"https://huggingface.co/datasets/ashercn97/hebrew_alpaca\" target=\"_blank\" rel=\"noopener\">hebrew_alpaca</a>", "Hebrew Alpaca-style instruction data (instruction, input, output).", "Author: ashercn97 · Size: 1K – 10K rows", "<a href=\"https://huggingface.co/datasets/ashercn97/hebrew_alpaca\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[hebrew_alpaca](https://huggingface.co/datasets/ashercn97/hebrew_alpaca) hebrew alpaca-style instruction data (instruction, input, output). author: ashercn97 · size: 1k – 10k rows [dataset](https://huggingface.co/datasets/ashercn97/hebrew_alpaca)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/jojo-ai-mst/Roleplay-Hebrew\" target=\"_blank\" rel=\"noopener\">Roleplay-Hebrew</a>", "Hebrew roleplay instruction data, translated from the GPTeacher roleplay set.", "Author: jojo-ai-mst · Size: 1K – 10K rows · License: mit", "<a href=\"https://huggingface.co/datasets/jojo-ai-mst/Roleplay-Hebrew\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[roleplay-hebrew](https://huggingface.co/datasets/jojo-ai-mst/roleplay-hebrew) hebrew roleplay instruction data, translated from the gpteacher roleplay set. author: jojo-ai-mst · size: 1k – 10k rows · license: mit [dataset](https://huggingface.co/datasets/jojo-ai-mst/roleplay-hebrew)"}]}]}, {"name": "NLP Task Datasets", "tables": [{"subsection": null, "columns": ["Name", "Description", "Details", "Links"], "rows": [{"cells": ["<a href=\"https://huggingface.co/datasets/HebArabNlpProject/Hebrew-Paraphrase-Dataset\" target=\"_blank\" rel=\"noopener\">Hebrew-Paraphrase-Dataset</a>", "9,785 LLM-generated paraphrase pairs (paragraph and sentence level); 300 manually validated gold.", "Author: HebArabNlpProject · Size: 9,785 instances · License: cc-by-sa-4.0", "<a href=\"https://huggingface.co/datasets/HebArabNlpProject/Hebrew-Paraphrase-Dataset\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[hebrew-paraphrase-dataset](https://huggingface.co/datasets/hebarabnlpproject/hebrew-paraphrase-dataset) 9,785 llm-generated paraphrase pairs (paragraph and sentence level); 300 manually validated gold. author: hebarabnlpproject · size: 9,785 instances · license: cc-by-sa-4.0 [dataset](https://huggingface.co/datasets/hebarabnlpproject/hebrew-paraphrase-dataset)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/TigreGotico/hebrew_diacritized_text\" target=\"_blank\" rel=\"noopener\">hebrew_diacritized_text</a>", "~5.3M Hebrew sentences with full nikud, from the phonikud knesset_nikud_v6 corpus; for diacritization.", "Author: TigreGotico · Size: ~5.3M sentences · License: cc-by-4.0", "<a href=\"https://huggingface.co/datasets/TigreGotico/hebrew_diacritized_text\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[hebrew_diacritized_text](https://huggingface.co/datasets/tigregotico/hebrew_diacritized_text) ~5.3m hebrew sentences with full nikud, from the phonikud knesset_nikud_v6 corpus; for diacritization. author: tigregotico · size: ~5.3m sentences · license: cc-by-4.0 [dataset](https://huggingface.co/datasets/tigregotico/hebrew_diacritized_text)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/omilab/hebrew_sentiment\" target=\"_blank\" rel=\"noopener\">hebrew_sentiment</a>", "Hebrew sentiment analysis (HebrewSentiment, positive/negative).", "Author: omilab · Size: 10K – 100K rows · License: mit", "<a href=\"https://huggingface.co/datasets/omilab/hebrew_sentiment\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[hebrew_sentiment](https://huggingface.co/datasets/omilab/hebrew_sentiment) hebrew sentiment analysis (hebrewsentiment, positive/negative). author: omilab · size: 10k – 100k rows · license: mit [dataset](https://huggingface.co/datasets/omilab/hebrew_sentiment)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/sepidmnorozy/Hebrew_sentiment\" target=\"_blank\" rel=\"noopener\">Hebrew_sentiment</a>", "Hebrew sentiment classification with binary labels.", "Author: sepidmnorozy · Size: 10K – 100K rows", "<a href=\"https://huggingface.co/datasets/sepidmnorozy/Hebrew_sentiment\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[hebrew_sentiment](https://huggingface.co/datasets/sepidmnorozy/hebrew_sentiment) hebrew sentiment classification with binary labels. author: sepidmnorozy · size: 10k – 100k rows [dataset](https://huggingface.co/datasets/sepidmnorozy/hebrew_sentiment)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/tdklab/HebrewMetaphors\" target=\"_blank\" rel=\"noopener\">HebrewMetaphors</a>", "Hebrew metaphor classification data.", "Author: tdklab · Size: 1K – 10K rows", "<a href=\"https://huggingface.co/datasets/tdklab/HebrewMetaphors\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[hebrewmetaphors](https://huggingface.co/datasets/tdklab/hebrewmetaphors) hebrew metaphor classification data. author: tdklab · size: 1k – 10k rows [dataset](https://huggingface.co/datasets/tdklab/hebrewmetaphors)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/HebArabNlpProject/HebrewSentiment\" target=\"_blank\" rel=\"noopener\">HebrewSentiment</a>", "Hebrew sentiment (positive/negative/neutral) from the Hebrew NLP benchmark collection.", "Author: HebArabNlpProject · Size: 10K – 100K rows · License: other", "<a href=\"https://huggingface.co/datasets/HebArabNlpProject/HebrewSentiment\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[hebrewsentiment](https://huggingface.co/datasets/hebarabnlpproject/hebrewsentiment) hebrew sentiment (positive/negative/neutral) from the hebrew nlp benchmark collection. author: hebarabnlpproject · size: 10k – 100k rows · license: other [dataset](https://huggingface.co/datasets/hebarabnlpproject/hebrewsentiment)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/imvladikon/wikianswers_hebrew\" target=\"_blank\" rel=\"noopener\">wikianswers_hebrew</a>", "Hebrew version of WikiAnswers paraphrase/question data.", "Author: imvladikon · Size: 1M – 10M rows", "<a href=\"https://huggingface.co/datasets/imvladikon/wikianswers_hebrew\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[wikianswers_hebrew](https://huggingface.co/datasets/imvladikon/wikianswers_hebrew) hebrew version of wikianswers paraphrase/question data. author: imvladikon · size: 1m – 10m rows [dataset](https://huggingface.co/datasets/imvladikon/wikianswers_hebrew)"}]}]}, {"name": "OCR and Handwriting", "tables": [{"subsection": null, "columns": ["Name", "Description", "Details", "Links"], "rows": [{"cells": ["<a href=\"https://huggingface.co/datasets/sivan22/hebrew-handwritten-dataset\" target=\"_blank\" rel=\"noopener\">hebrew-handwritten-dataset</a>", "HDD_v0: images of isolated handwritten Hebrew characters with train/test split.", "Author: sivan22 · Size: 1K – 10K rows · License: cc-by-3.0", "<a href=\"https://huggingface.co/datasets/sivan22/hebrew-handwritten-dataset\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[hebrew-handwritten-dataset](https://huggingface.co/datasets/sivan22/hebrew-handwritten-dataset) hdd_v0: images of isolated handwritten hebrew characters with train/test split. author: sivan22 · size: 1k – 10k rows · license: cc-by-3.0 [dataset](https://huggingface.co/datasets/sivan22/hebrew-handwritten-dataset)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/danielrosehill/Hebrew-Language-Signage\" target=\"_blank\" rel=\"noopener\">Hebrew-Language-Signage</a>", "68 photographs of Hebrew signage in Israel (street, commercial and public signs).", "Author: danielrosehill · Size: 68 images", "<a href=\"https://huggingface.co/datasets/danielrosehill/Hebrew-Language-Signage\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[hebrew-language-signage](https://huggingface.co/datasets/danielrosehill/hebrew-language-signage) 68 photographs of hebrew signage in israel (street, commercial and public signs). author: danielrosehill · size: 68 images [dataset](https://huggingface.co/datasets/danielrosehill/hebrew-language-signage)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/mbole/hebrew-ocr-dataset\" target=\"_blank\" rel=\"noopener\">hebrew-ocr-dataset</a>", "Hebrew text with label and source columns for OCR work.", "Author: mbole · Size: <1K rows", "<a href=\"https://huggingface.co/datasets/mbole/hebrew-ocr-dataset\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[hebrew-ocr-dataset](https://huggingface.co/datasets/mbole/hebrew-ocr-dataset) hebrew text with label and source columns for ocr work. author: mbole · size: <1k rows [dataset](https://huggingface.co/datasets/mbole/hebrew-ocr-dataset)"}]}]}, {"name": "Related", "tables": [{"subsection": null, "columns": ["Name", "Description", "Details", "Links"], "rows": [{"cells": ["<a href=\"https://github.com/danielrosehill/Hebrew-AI-Models\" target=\"_blank\" rel=\"noopener\">danielrosehill/Hebrew-AI-Models</a>", "Companion list: Hebrew LLMs, ASR, TTS, OCR, NLP models.", "", "<a href=\"https://github.com/danielrosehill/Hebrew-AI-Models\" target=\"_blank\" rel=\"noopener\">View Repo</a>"], "text": "[danielrosehill/hebrew-ai-models](https://github.com/danielrosehill/hebrew-ai-models) companion list: hebrew llms, asr, tts, ocr, nlp models. [view repo](https://github.com/danielrosehill/hebrew-ai-models)"}, {"cells": ["<a href=\"https://github.com/NNLP-IL/Hebrew-Resources\" target=\"_blank\" rel=\"noopener\">NNLP-IL/Hebrew-Resources</a>", "Comprehensive list of Hebrew NLP resources, including corpora.", "", "<a href=\"https://github.com/NNLP-IL/Hebrew-Resources\" target=\"_blank\" rel=\"noopener\">View Repo</a>"], "text": "[nnlp-il/hebrew-resources](https://github.com/nnlp-il/hebrew-resources) comprehensive list of hebrew nlp resources, including corpora. [view repo](https://github.com/nnlp-il/hebrew-resources)"}]}]}, {"name": "Sentence Datasets", "tables": [{"subsection": null, "columns": ["Name", "Description", "Details", "Links"], "rows": [{"cells": ["<a href=\"https://huggingface.co/datasets/tomron87/hebrew-wikipedia-sentences-corpus\" target=\"_blank\" rel=\"noopener\">hebrew-wikipedia-sentences-corpus</a>", "Cleaned, deduplicated Hebrew sentences from 366,610 Hebrew Wikipedia articles (crawled 2026-02).", "Author: tomron87 · Size: 10,999,257 sentences · License: cc-by-sa-3.0", "<a href=\"https://huggingface.co/datasets/tomron87/hebrew-wikipedia-sentences-corpus\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[hebrew-wikipedia-sentences-corpus](https://huggingface.co/datasets/tomron87/hebrew-wikipedia-sentences-corpus) cleaned, deduplicated hebrew sentences from 366,610 hebrew wikipedia articles (crawled 2026-02). author: tomron87 · size: 10,999,257 sentences · license: cc-by-sa-3.0 [dataset](https://huggingface.co/datasets/tomron87/hebrew-wikipedia-sentences-corpus)"}]}]}, {"name": "Text Corpora", "tables": [{"subsection": "Hebrew-Specific Datasets", "columns": ["Name", "Description", "Details", "Links"], "rows": [{"cells": ["<a href=\"https://huggingface.co/datasets/AvishayDev/hebrew-BenIshHai\" target=\"_blank\" rel=\"noopener\">hebrew-BenIshHai</a>", "Halachot from the book Ben Ish Hai, from Hebrew Wikisource.", "Author: AvishayDev · Size: 1K – 10K rows", "<a href=\"https://huggingface.co/datasets/AvishayDev/hebrew-BenIshHai\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[hebrew-benishhai](https://huggingface.co/datasets/avishaydev/hebrew-benishhai) halachot from the book ben ish hai, from hebrew wikisource. author: avishaydev · size: 1k – 10k rows [dataset](https://huggingface.co/datasets/avishaydev/hebrew-benishhai)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/MetroCat/Hebrew-Mil\" target=\"_blank\" rel=\"noopener\">Hebrew-Mil</a>", "Hebrew-only PDFs on military and defence topics.", "Author: MetroCat · Size: 1K – 10K rows · License: gpl", "<a href=\"https://huggingface.co/datasets/MetroCat/Hebrew-Mil\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[hebrew-mil](https://huggingface.co/datasets/metrocat/hebrew-mil) hebrew-only pdfs on military and defence topics. author: metrocat · size: 1k – 10k rows · license: gpl [dataset](https://huggingface.co/datasets/metrocat/hebrew-mil)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/imvladikon/hebrew_news\" target=\"_blank\" rel=\"noopener\">hebrew_news</a>", "Hebrew news articles.", "Author: imvladikon · Size: 100K – 1M rows · License: other", "<a href=\"https://huggingface.co/datasets/imvladikon/hebrew_news\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[hebrew_news](https://huggingface.co/datasets/imvladikon/hebrew_news) hebrew news articles. author: imvladikon · size: 100k – 1m rows · license: other [dataset](https://huggingface.co/datasets/imvladikon/hebrew_news)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/simsim314/Hebrew_Noam30B_Tokenized\" target=\"_blank\" rel=\"noopener\">Hebrew_Noam30B_Tokenized</a>", "Tokenized Hebrew text (input_ids and attention masks) for pretraining.", "Author: simsim314 · License: mit", "<a href=\"https://huggingface.co/datasets/simsim314/Hebrew_Noam30B_Tokenized\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[hebrew_noam30b_tokenized](https://huggingface.co/datasets/simsim314/hebrew_noam30b_tokenized) tokenized hebrew text (input_ids and attention masks) for pretraining. author: simsim314 · license: mit [dataset](https://huggingface.co/datasets/simsim314/hebrew_noam30b_tokenized)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/YanFren/Hebrew_wikipedia\" target=\"_blank\" rel=\"noopener\">Hebrew_wikipedia</a>", "Most of Hebrew Wikipedia as JSON, crawled breadth-first.", "Author: YanFren · Size: 100K – 1M rows · License: mit", "<a href=\"https://huggingface.co/datasets/YanFren/Hebrew_wikipedia\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[hebrew_wikipedia](https://huggingface.co/datasets/yanfren/hebrew_wikipedia) most of hebrew wikipedia as json, crawled breadth-first. author: yanfren · size: 100k – 1m rows · license: mit [dataset](https://huggingface.co/datasets/yanfren/hebrew_wikipedia)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/Norod78/HebrewLyricsDataet\" target=\"_blank\" rel=\"noopener\">HebrewLyricsDataet</a>", "Hebrew song lyrics with title and singer.", "Author: Norod78 · Size: 10K – 100K rows", "<a href=\"https://huggingface.co/datasets/Norod78/HebrewLyricsDataet\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[hebrewlyricsdataet](https://huggingface.co/datasets/norod78/hebrewlyricsdataet) hebrew song lyrics with title and singer. author: norod78 · size: 10k – 100k rows [dataset](https://huggingface.co/datasets/norod78/hebrewlyricsdataet)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/guyhadad01/Judaism-Hebrew\" target=\"_blank\" rel=\"noopener\">Judaism-Hebrew</a>", "Hebrew Judaism texts (responsa and related).", "Author: guyhadad01 · Size: 1K – 10K rows", "<a href=\"https://huggingface.co/datasets/guyhadad01/Judaism-Hebrew\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[judaism-hebrew](https://huggingface.co/datasets/guyhadad01/judaism-hebrew) hebrew judaism texts (responsa and related). author: guyhadad01 · size: 1k – 10k rows [dataset](https://huggingface.co/datasets/guyhadad01/judaism-hebrew)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/sivan22/sefaria-hebrew\" target=\"_blank\" rel=\"noopener\">sefaria-hebrew</a>", "Jewish texts in Hebrew from the Sefaria project.", "Author: sivan22 · Size: 1M – 10M rows", "<a href=\"https://huggingface.co/datasets/sivan22/sefaria-hebrew\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[sefaria-hebrew](https://huggingface.co/datasets/sivan22/sefaria-hebrew) jewish texts in hebrew from the sefaria project. author: sivan22 · size: 1m – 10m rows [dataset](https://huggingface.co/datasets/sivan22/sefaria-hebrew)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/cp500/synthetic_hebrew_medical_text\" target=\"_blank\" rel=\"noopener\">synthetic_hebrew_medical_text</a>", "Synthetic Hebrew medical text.", "Author: cp500 · Size: 1K – 10K rows", "<a href=\"https://huggingface.co/datasets/cp500/synthetic_hebrew_medical_text\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[synthetic_hebrew_medical_text](https://huggingface.co/datasets/cp500/synthetic_hebrew_medical_text) synthetic hebrew medical text. author: cp500 · size: 1k – 10k rows [dataset](https://huggingface.co/datasets/cp500/synthetic_hebrew_medical_text)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/guyhadad01/Talmud-Hebrew\" target=\"_blank\" rel=\"noopener\">Talmud-Hebrew</a>", "Talmud Bavli text in Hebrew from Wikisource.", "Author: guyhadad01 · Size: <1K rows", "<a href=\"https://huggingface.co/datasets/guyhadad01/Talmud-Hebrew\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[talmud-hebrew](https://huggingface.co/datasets/guyhadad01/talmud-hebrew) talmud bavli text in hebrew from wikisource. author: guyhadad01 · size: <1k rows [dataset](https://huggingface.co/datasets/guyhadad01/talmud-hebrew)"}]}, {"subsection": "Multilingual datasets with a Hebrew portion", "columns": ["Name", "Description", "Details", "Links"], "rows": [{"cells": ["<a href=\"https://huggingface.co/datasets/ksolovev/fine-news\" target=\"_blank\" rel=\"noopener\">fine-news</a>", "Multilingual news corpus from Common Crawl News; Hebrew is the `heb_Hebr` partition.", "Author: ksolovev · Size: 100M – 1B rows", "<a href=\"https://huggingface.co/datasets/ksolovev/fine-news\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[fine-news](https://huggingface.co/datasets/ksolovev/fine-news) multilingual news corpus from common crawl news; hebrew is the `heb_hebr` partition. author: ksolovev · size: 100m – 1b rows [dataset](https://huggingface.co/datasets/ksolovev/fine-news)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/wikimedia/wikipedia\" target=\"_blank\" rel=\"noopener\">wikipedia</a>", "Wikipedia dumps; Hebrew is the `20231101.he` config.", "Author: wikimedia · Size: 10M – 100M rows · License: cc-by-sa-3.0", "<a href=\"https://huggingface.co/datasets/wikimedia/wikipedia\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[wikipedia](https://huggingface.co/datasets/wikimedia/wikipedia) wikipedia dumps; hebrew is the `20231101.he` config. author: wikimedia · size: 10m – 100m rows · license: cc-by-sa-3.0 [dataset](https://huggingface.co/datasets/wikimedia/wikipedia)"}]}]}, {"name": "Translation and Parallel Text", "tables": [{"subsection": "Multilingual datasets with a Hebrew portion", "columns": ["Name", "Description", "Details", "Links"], "rows": [{"cells": ["<a href=\"https://huggingface.co/datasets/openlanguagedata/flores_plus\" target=\"_blank\" rel=\"noopener\">flores_plus</a>", "FLORES+ translation benchmark; Hebrew is `heb_Hebr` (also Yiddish `ydd_Hebr`).", "Author: openlanguagedata · Size: 100K – 1M rows · License: cc-by-sa-4.0", "<a href=\"https://huggingface.co/datasets/openlanguagedata/flores_plus\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[flores_plus](https://huggingface.co/datasets/openlanguagedata/flores_plus) flores+ translation benchmark; hebrew is `heb_hebr` (also yiddish `ydd_hebr`). author: openlanguagedata · size: 100k – 1m rows · license: cc-by-sa-4.0 [dataset](https://huggingface.co/datasets/openlanguagedata/flores_plus)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/sentence-transformers/parallel-sentences-global-voices\" target=\"_blank\" rel=\"noopener\">parallel-sentences-global-voices</a>", "Global Voices news pairs; Hebrew is the `en-he` subset.", "Author: sentence-transformers · Size: 1M – 10M rows", "<a href=\"https://huggingface.co/datasets/sentence-transformers/parallel-sentences-global-voices\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[parallel-sentences-global-voices](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-global-voices) global voices news pairs; hebrew is the `en-he` subset. author: sentence-transformers · size: 1m – 10m rows [dataset](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-global-voices)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks\" target=\"_blank\" rel=\"noopener\">parallel-sentences-talks</a>", "TED-style talk pairs; Hebrew is the `en-he` subset.", "Author: sentence-transformers · Size: 10M – 100M rows", "<a href=\"https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[parallel-sentences-talks](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks) ted-style talk pairs; hebrew is the `en-he` subset. author: sentence-transformers · size: 10m – 100m rows [dataset](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks)"}, {"cells": ["<a href=\"https://huggingface.co/datasets/sentence-transformers/parallel-sentences-tatoeba\" target=\"_blank\" rel=\"noopener\">parallel-sentences-tatoeba</a>", "Tatoeba sentence pairs; Hebrew is the `en-he` subset.", "Author: sentence-transformers · Size: 1M – 10M rows", "<a href=\"https://huggingface.co/datasets/sentence-transformers/parallel-sentences-tatoeba\" target=\"_blank\" rel=\"noopener\">Dataset</a>"], "text": "[parallel-sentences-tatoeba](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-tatoeba) tatoeba sentence pairs; hebrew is the `en-he` subset. author: sentence-transformers · size: 1m – 10m rows [dataset](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-tatoeba)"}]}]}, {"name": "Curated HF Collections", "tables": [{"subsection": null, "columns": ["Name", "Description", "Details", "Links"], "rows": [{"cells": ["<a href=\"https://huggingface.co/collections/danielrosehill/audio-datasets-mine-6aee9e80cb04e786c3fdbeaa\" target=\"_blank\" rel=\"noopener\">Audio Datasets - Mine</a>", "The maintainer's own audio datasets.", "", "<a href=\"https://huggingface.co/collections/danielrosehill/audio-datasets-mine-6aee9e80cb04e786c3fdbeaa\" target=\"_blank\" rel=\"noopener\">Collection</a>"], "text": "[audio datasets - mine](https://huggingface.co/collections/danielrosehill/audio-datasets-mine-6aee9e80cb04e786c3fdbeaa) the maintainer's own audio datasets. [collection](https://huggingface.co/collections/danielrosehill/audio-datasets-mine-6aee9e80cb04e786c3fdbeaa)"}, {"cells": ["<a href=\"https://huggingface.co/collections/danielrosehill/audio-datasets-third-party-classics-6aeea2c2b9ec48969f48e054\" target=\"_blank\" rel=\"noopener\">Audio Datasets - Third Party Classics</a>", "Well-known third-party audio datasets.", "", "<a href=\"https://huggingface.co/collections/danielrosehill/audio-datasets-third-party-classics-6aeea2c2b9ec48969f48e054\" target=\"_blank\" rel=\"noopener\">Collection</a>"], "text": "[audio datasets - third party classics](https://huggingface.co/collections/danielrosehill/audio-datasets-third-party-classics-6aeea2c2b9ec48969f48e054) well-known third-party audio datasets. [collection](https://huggingface.co/collections/danielrosehill/audio-datasets-third-party-classics-6aeea2c2b9ec48969f48e054)"}, {"cells": ["<a href=\"https://huggingface.co/collections/danielrosehill/code-switching-english-and-hebrew-all-resources-6acfdcb1e11911797af4c3b3\" target=\"_blank\" rel=\"noopener\">Code Switching (English And Hebrew) - All Resources</a>", "English-Hebrew code-switching models and datasets.", "", "<a href=\"https://huggingface.co/collections/danielrosehill/code-switching-english-and-hebrew-all-resources-6acfdcb1e11911797af4c3b3\" target=\"_blank\" rel=\"noopener\">Collection</a>"], "text": "[code switching (english and hebrew) - all resources](https://huggingface.co/collections/danielrosehill/code-switching-english-and-hebrew-all-resources-6acfdcb1e11911797af4c3b3) english-hebrew code-switching models and datasets. [collection](https://huggingface.co/collections/danielrosehill/code-switching-english-and-hebrew-all-resources-6acfdcb1e11911797af4c3b3)"}, {"cells": ["<a href=\"https://huggingface.co/collections/danielrosehill/hebrew-6ad68f42575d0b5073d19e86\" target=\"_blank\" rel=\"noopener\">Hebrew</a>", "General Hebrew collection: models and datasets across tasks.", "", "<a href=\"https://huggingface.co/collections/danielrosehill/hebrew-6ad68f42575d0b5073d19e86\" target=\"_blank\" rel=\"noopener\">Collection</a>"], "text": "[hebrew](https://huggingface.co/collections/danielrosehill/hebrew-6ad68f42575d0b5073d19e86) general hebrew collection: models and datasets across tasks. [collection](https://huggingface.co/collections/danielrosehill/hebrew-6ad68f42575d0b5073d19e86)"}, {"cells": ["<a href=\"https://huggingface.co/collections/danielrosehill/hebrew-audio-datasets-6ad6923f2ea298b0df13adf5\" target=\"_blank\" rel=\"noopener\">Hebrew audio datasets</a>", "Hebrew speech and audio datasets.", "", "<a href=\"https://huggingface.co/collections/danielrosehill/hebrew-audio-datasets-6ad6923f2ea298b0df13adf5\" target=\"_blank\" rel=\"noopener\">Collection</a>"], "text": "[hebrew audio datasets](https://huggingface.co/collections/danielrosehill/hebrew-audio-datasets-6ad6923f2ea298b0df13adf5) hebrew speech and audio datasets. [collection](https://huggingface.co/collections/danielrosehill/hebrew-audio-datasets-6ad6923f2ea298b0df13adf5)"}, {"cells": ["<a href=\"https://huggingface.co/collections/danielrosehill/hebrew-datasets-680428e2813deb0a8b8d1271\" target=\"_blank\" rel=\"noopener\">Hebrew datasets</a>", "Hebrew text and NLP datasets.", "", "<a href=\"https://huggingface.co/collections/danielrosehill/hebrew-datasets-680428e2813deb0a8b8d1271\" target=\"_blank\" rel=\"noopener\">Collection</a>"], "text": "[hebrew datasets](https://huggingface.co/collections/danielrosehill/hebrew-datasets-680428e2813deb0a8b8d1271) hebrew text and nlp datasets. [collection](https://huggingface.co/collections/danielrosehill/hebrew-datasets-680428e2813deb0a8b8d1271)"}, {"cells": ["<a href=\"https://huggingface.co/collections/danielrosehill/israel-context-datasets-6ad676a3773a64192165a96c\" target=\"_blank\" rel=\"noopener\">Israel Context Datasets</a>", "Datasets about Israel, often Hebrew-language.", "", "<a href=\"https://huggingface.co/collections/danielrosehill/israel-context-datasets-6ad676a3773a64192165a96c\" target=\"_blank\" rel=\"noopener\">Collection</a>"], "text": "[israel context datasets](https://huggingface.co/collections/danielrosehill/israel-context-datasets-6ad676a3773a64192165a96c) datasets about israel, often hebrew-language. [collection](https://huggingface.co/collections/danielrosehill/israel-context-datasets-6ad676a3773a64192165a96c)"}, {"cells": ["<a href=\"https://huggingface.co/collections/danielrosehill/israel-open-data-69fba702e180798fe3761073\" target=\"_blank\" rel=\"noopener\">Israel Open Data</a>", "Israeli government open data on the Hub.", "", "<a href=\"https://huggingface.co/collections/danielrosehill/israel-open-data-69fba702e180798fe3761073\" target=\"_blank\" rel=\"noopener\">Collection</a>"], "text": "[israel open data](https://huggingface.co/collections/danielrosehill/israel-open-data-69fba702e180798fe3761073) israeli government open data on the hub. [collection](https://huggingface.co/collections/danielrosehill/israel-open-data-69fba702e180798fe3761073)"}, {"cells": ["<a href=\"https://huggingface.co/collections/danielrosehill/sentence-datasets-all-6aeeb0facb33a09378459623\" target=\"_blank\" rel=\"noopener\">Sentence Datasets - All</a>", "Sentence datasets (mixed languages; Hebrew ones are listed here).", "", "<a href=\"https://huggingface.co/collections/danielrosehill/sentence-datasets-all-6aeeb0facb33a09378459623\" target=\"_blank\" rel=\"noopener\">Collection</a>"], "text": "[sentence datasets - all](https://huggingface.co/collections/danielrosehill/sentence-datasets-all-6aeeb0facb33a09378459623) sentence datasets (mixed languages; hebrew ones are listed here). [collection](https://huggingface.co/collections/danielrosehill/sentence-datasets-all-6aeeb0facb33a09378459623)"}, {"cells": ["<a href=\"https://huggingface.co/collections/danielrosehill/sentence-datasets-mine-6aeeb2ae61663e960fade58c\" target=\"_blank\" rel=\"noopener\">Sentence Datasets - Mine</a>", "The maintainer's own sentence datasets.", "", "<a href=\"https://huggingface.co/collections/danielrosehill/sentence-datasets-mine-6aeeb2ae61663e960fade58c\" target=\"_blank\" rel=\"noopener\">Collection</a>"], "text": "[sentence datasets - mine](https://huggingface.co/collections/danielrosehill/sentence-datasets-mine-6aeeb2ae61663e960fade58c) the maintainer's own sentence datasets. [collection](https://huggingface.co/collections/danielrosehill/sentence-datasets-mine-6aeeb2ae61663e960fade58c)"}, {"cells": ["<a href=\"https://huggingface.co/collections/danielrosehill/sentence-datasets-third-party-6aeea2c7b5a404455057151a\" target=\"_blank\" rel=\"noopener\">Sentence Datasets - Third Party</a>", "Third-party sentence datasets. All collections: <a href=\"https://huggingface.co/danielrosehill/collections\" target=\"_blank\" rel=\"noopener\">https://huggingface.co/danielrosehill/collections</a>", "", "<a href=\"https://huggingface.co/collections/danielrosehill/sentence-datasets-third-party-6aeea2c7b5a404455057151a\" target=\"_blank\" rel=\"noopener\">Collection</a>"], "text": "[sentence datasets - third party](https://huggingface.co/collections/danielrosehill/sentence-datasets-third-party-6aeea2c7b5a404455057151a) third-party sentence datasets. all collections: [https://huggingface.co/danielrosehill/collections](https://huggingface.co/danielrosehill/collections) [collection](https://huggingface.co/collections/danielrosehill/sentence-datasets-third-party-6aeea2c7b5a404455057151a)"}]}]}]; | |
| const main=document.getElementById('main'),chips=document.getElementById('chips'),q=document.getElementById('q'); | |
| let active=null; | |
| DATA.forEach((s,i)=>{const b=document.createElement('button');b.textContent=s.name;b.onclick=()=>{active=active===i?null:i;render()};chips.appendChild(b)}); | |
| function render(){ | |
| const term=q.value.toLowerCase();main.innerHTML=''; | |
| [...chips.children].forEach((b,i)=>b.className=active===i?'on':''); | |
| DATA.forEach((s,i)=>{ | |
| if(active!==null&&active!==i)return; | |
| let out=''; | |
| s.tables.forEach(t=>{ | |
| const rows=t.rows.filter(r=>!term||r.text.includes(term)); | |
| if(!rows.length)return; | |
| out+=(t.subsection?`<h3>${t.subsection}</h3>`:'')+'<table><tr>'+t.columns.map(c=>`<th>${c}</th>`).join('')+'</tr>'+ | |
| rows.map(r=>'<tr>'+r.cells.map(c=>`<td>${c}</td>`).join('')+'</tr>').join('')+'</table>'; | |
| }); | |
| if(out)main.innerHTML+=`<h2>${s.name}</h2>`+out; | |
| }); | |
| if(!main.innerHTML)main.innerHTML='<p>No matches.</p>'; | |
| } | |
| q.oninput=render;render(); | |
| </script></body></html> | |