{
 "built": "2026-11-08",
 "collections": {
  "audio_mine": "danielrosehill/audio-datasets-mine-6aee9e80cb04e786c3fdbeaa",
  "audio_classics": "danielrosehill/audio-datasets-third-party-classics-6aeea2c2b9ec48969f48e054",
  "sentences_third_party": "danielrosehill/sentence-datasets-third-party-6aeea2c7b5a404455057151a",
  "sentences_mine": "danielrosehill/sentence-datasets-mine-6aeeb2ae61663e960fade58c",
  "sentences_all": "danielrosehill/sentence-datasets-all-6aeeb0facb33a09378459623"
 },
 "datasets": [
  {
   "id": "Hebrish/AI-Interactions-Sentence-Bank",
   "owner": "Hebrish",
   "name": "AI Interactions Sentence Bank",
   "group": "Sentence banks",
   "gated": false,
   "rows": 677,
   "bytes": 338815,
   "modified": "2026-10-31T11:18:12+00:00",
   "summary": "English sentences in the register of instructions dictated to AI coding agents (Claude Code, Codex, Cursor and others) during a working day: subagents, background agents, worktrees, context and compaction, plan mode, hooks, MCP…",
   "pairs_with": "danielrosehill/AI-Interactions-Sentences"
  },
  {
   "id": "Hebrish/AI-Tech-Vocabulary-Sentence-Bank",
   "owner": "Hebrish",
   "name": "AI Tech Vocabulary Sentence Bank",
   "group": "Sentence banks",
   "gated": true,
   "rows": 2874,
   "bytes": 1713372,
   "modified": "2026-10-31T11:18:10+00:00",
   "summary": "English sentences dense in AI and developer vocabulary: model and lab names (Claude, Qwen, DeepSeek, Kimi, GLM), benchmarks (SWE-bench, GPQA, ARC-AGI), inference tooling (vLLM, llama.cpp, Ollama, Unsloth), cloud and DevOps tools.…",
   "pairs_with": "danielrosehill/Tech-Sentences"
  },
  {
   "id": "Hebrish/Linux-Admin-Sentence-Bank",
   "owner": "Hebrish",
   "name": "Linux Admin Sentence Bank",
   "group": "Sentence banks",
   "gated": true,
   "rows": 724,
   "bytes": 369075,
   "modified": "2026-10-31T11:18:13+00:00",
   "summary": "English sentences about Linux desktop and server administration, built around names a speech model writes as an ordinary English word: Konsole (console), Okular (ocular), Thunar (thunder), LUKS (looks), Btrfs, GRUB, Chrony…",
   "pairs_with": "danielrosehill/Linux-Admin-Sentences"
  },
  {
   "id": "Hebrish/Smart-Home-Sentence-Bank",
   "owner": "Hebrish",
   "name": "Smart Home Sentence Bank",
   "group": "Sentence banks",
   "gated": false,
   "rows": 270,
   "bytes": 142519,
   "modified": "2026-10-31T11:18:23+00:00",
   "summary": "English sentences about home automation: Home Assistant and its features (Assist, Wyoming, Piper), protocols (Zigbee, Z-Wave, Matter, Thread), firmware (ESPHome, Tasmota, WLED) and device brands. Includes names a speech model…",
   "pairs_with": "danielrosehill/Smart-Home-Sentences"
  },
  {
   "id": "Hebrish/Personal-Vocabulary-Sentence-Bank",
   "owner": "Hebrish",
   "name": "Personal Vocabulary Sentence Bank",
   "group": "Sentence banks",
   "gated": true,
   "rows": 282,
   "bytes": 156886,
   "modified": "2026-10-31T11:18:55+00:00",
   "summary": "English sentences built around names speech models get wrong for me: my own name, my company and my project names (Daniel Rosehill, DSR Holdings, Carrot Cake AI), and my podcast My Weird Prompts with its hosts Corn and Herman…",
   "pairs_with": "danielrosehill/Personal-Vocabulary-Sentences"
  },
  {
   "id": "Hebrish/Homophone-Context-Sentence-Bank",
   "owner": "Hebrish",
   "name": "Homophone Context Sentence Bank",
   "group": "Sentence banks",
   "gated": true,
   "rows": 408,
   "bytes": 212970,
   "modified": "2026-10-31T11:19:26+00:00",
   "summary": "English sentences whose context settles which spelling of a homophone is meant (their/there/they're, to/too/two, write/right/rite and 57 more sets). homophone_set names the set.",
   "pairs_with": "danielrosehill/Homophone-Context-Sentences"
  },
  {
   "id": "Hebrish/October-7-Memorial-Sentence-Bank",
   "owner": "Hebrish",
   "name": "October 7 Memorial Sentence Bank",
   "group": "Memorial",
   "gated": true,
   "rows": 3806,
   "bytes": 694799,
   "modified": "2026-11-05T23:27:22+00:00",
   "summary": "This dataset is dedicated to those who were murdered and who fell on October 7, 2023. Reading their names aloud is an act of remembrance, and it helps speech models write those names correctly.",
   "pairs_with": null
  },
  {
   "id": "Hebrish/Example-Sentence-Bank",
   "owner": "Hebrish",
   "name": "Example Sentence Bank",
   "group": "Format reference",
   "gated": true,
   "rows": 6,
   "bytes": 14579,
   "modified": "2026-11-06T01:19:22+00:00",
   "summary": "This is the Hebrish project's reference for the sentence dataset format. It is the example a new sentence dataset copies, and sentence.schema.json beside it is the checkable form.",
   "pairs_with": "Hebrish/Example-Audio-Sentences"
  }
 ],
 "third_party": [
  {
   "id": "agentlans/high-quality-english-sentences",
   "note": "Filtered English sentences from C4 and FineWeb. ODC-By."
  },
  {
   "id": "nineninesix/harvard-sentences-tts-benchmark",
   "note": "Harvard sentences as plain text. No licence tag on the repo."
  },
  {
   "id": "tomron87/hebrew-wikipedia-sentences-corpus",
   "note": "About 11M Hebrew sentences from Wikipedia. CC BY-SA 3.0."
  },
  {
   "id": "sentence-transformers/parallel-sentences-tatoeba",
   "note": "Short everyday sentences; use the en-he config. No licence tag on the repo."
  },
  {
   "id": "sentence-transformers/parallel-sentences-talks",
   "note": "Spoken-style talk sentences; use the en-he config. No licence tag on the repo."
  },
  {
   "id": "sentence-transformers/parallel-sentences-global-voices",
   "note": "News-style sentences; use the en-he config. No licence tag on the repo."
  },
  {
   "id": "tor24/smart-home-voice-commands-v1",
   "note": "Short smart-home commands with intent labels. CC BY 4.0."
  },
  {
   "id": "danielrosehill/Sentence-Dataset-Navigator",
   "note": "Browse text-only sentence datasets, mine and third party."
  },
  {
   "id": "openlanguagedata/flores_plus",
   "note": "Standard multilingual set, source of FLEURS; use the eng_Latn and heb_Hebr configs. Gated. Recording it contaminates FLEURS evaluations. CC BY-SA 4.0."
  },
  {
   "id": "hpprc/enwiki-paragraphs",
   "note": "Paragraph (median 87 words). English Wikipedia paragraphs, 47M rows, clean of markup. Encyclopedic register with some number-heavy rows. CC BY-SA 4.0."
  },
  {
   "id": "roneneldan/TinyStories",
   "note": "Paragraph (median 145 words). Short GPT-written children's stories, 2.1M rows, simple vocabulary, split by paragraph for shorter reads. CDLA-Sharing 1.0."
  },
  {
   "id": "hamishivi/ROCStories",
   "note": "Long (median 44 words). Five-sentence everyday stories, 98k rows, natural spoken register. CC BY 4.0 tag on this repackage; check the original corpus terms before redistribution."
  },
  {
   "id": "rajpurkar/squad",
   "note": "Paragraph (median 148 words). Canonical Wikipedia paragraphs, in the context column. Dedupe first: many question rows share a paragraph. CC BY-SA 4.0."
  }
 ]
}