Blame for data.json

{
 "built": "2026-11-07",
 "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"
 },
 "datasets": [
  {
   "id": "danielrosehill/Read-Aloud-Voice-Sentences",
   "owner": "danielrosehill",
   "name": "Read Aloud Voice Sentences",
   "group": "Master",
   "gated": true,
   "rows": 26390,
   "hours": 40.26,
   "sha": "fa4256292923df9015bc8a7e092a38dfe2e6418f",
   "bytes": 10984537345,
   "modified": "2026-11-06T13:40:38+00:00",
   "summary": "Read-aloud sentences from one speaker, recorded on a phone (OnePlus Nord 3 5G, internal microphone).",
   "pairs_with": null,
   "banks": []
  },
  {
   "id": "danielrosehill/General-English-Sentences",
   "owner": "danielrosehill",
   "name": "General English Sentences",
   "group": "Everyday and general",
   "gated": false,
   "rows": 1816,
   "hours": 2.76,
   "sha": "212d1308dea333e3232ff13b48cd42abda6763b4",
   "bytes": 791618244,
   "modified": "2026-11-05T22:20:05+00:00",
   "summary": "Plain, everyday English sentences (emails, messages, general prose and homophone pairs) read aloud by one speaker, with no Hebrew or Yiddish words, Israeli names or tech vocabulary. A small, general set for adapting a model to…",
   "pairs_with": null,
   "banks": []
  },
  {
   "id": "Hebrish/Irish-English-Sentences",
   "owner": "Hebrish",
   "name": "Irish English Sentences",
   "group": "Everyday and general",
   "gated": true,
   "rows": 256,
   "hours": 0.38,
   "sha": "842caeb48595707fe8a5b0710787278b17d1c348",
   "bytes": 62087167,
   "modified": "2026-11-06T10:55:30+00:00",
   "summary": "Everyday sentences in Irish English read by one speaker born in Ireland: vocabulary (craic, grand, giving out, press, messages), grammar (I'm after doing it, so it is, ye), Irish-language words used in English (Taoiseach, Dáil…",
   "pairs_with": null,
   "banks": []
  },
  {
   "id": "danielrosehill/Personal-Vocabulary-Sentences",
   "owner": "danielrosehill",
   "name": "Personal Vocabulary Sentences",
   "group": "Everyday and general",
   "gated": false,
   "rows": 182,
   "hours": 0.24,
   "sha": "4450eaf199c456ddc1a5abdc5e51d85144a3dfc0",
   "bytes": 71647390,
   "modified": "2026-11-05T14:25:35+00:00",
   "summary": "English sentences built around names a speech model gets wrong for one speaker: his own name, his company and his project names (Daniel Rosehill, DSR Holdings, Carrot Cake AI, the podcast My Weird Prompts and its hosts Corn and…",
   "pairs_with": null,
   "banks": [
    "Hebrish/Personal-Vocabulary-Sentence-Bank"
   ]
  },
  {
   "id": "danielrosehill/Voice-Command-Sentences",
   "owner": "danielrosehill",
   "name": "Voice Command Sentences",
   "group": "Everyday and general",
   "gated": false,
   "rows": 1266,
   "hours": 0.69,
   "sha": "1ef38cb8d4fa2cea61492ace31585edba88e6d10",
   "bytes": 195230615,
   "modified": "2026-11-05T02:08:22+00:00",
   "summary": "One speaker reading desktop voice commands for a KDE Plasma voice-command agent: launching, switching to and closing apps (Konsole, Kate, Dolphin, Kdenlive, Audacity), browser and terminal tabs, windows and virtual desktops…",
   "pairs_with": null,
   "banks": []
  },
  {
   "id": "danielrosehill/Smart-Home-Sentences",
   "owner": "danielrosehill",
   "name": "Smart Home Sentences",
   "group": "Everyday and general",
   "gated": false,
   "rows": 144,
   "hours": 0.22,
   "sha": "44f2f5ab2068e54821349405cd21583160aab833",
   "bytes": 71091178,
   "modified": "2026-11-06T13:09:30+00:00",
   "summary": "Dictation-style English sentences about home automation (Home Assistant, Zigbee, Z-Wave, Matter, Thread, ESPHome, MQTT and device brands), read aloud by one speaker. Includes product names a speech model writes as an ordinary…",
   "pairs_with": null,
   "banks": [
    "Hebrish/Smart-Home-Sentence-Bank"
   ]
  },
  {
   "id": "danielrosehill/AI-Interactions-Sentences",
   "owner": "danielrosehill",
   "name": "AI Interactions Sentences",
   "group": "Everyday and general",
   "gated": false,
   "rows": 572,
   "hours": 0.73,
   "sha": "dc52bfeeb828d4a34e650eaf8a0a9bbc49ec997b",
   "bytes": 247849317,
   "modified": "2026-11-05T21:46:43+00:00",
   "summary": "Instructions dictated to AI coding agents (Claude Code, Codex and others) and the git and GitHub workflow around them, read aloud by one speaker: subagents, worktrees, compaction, plan mode, hooks, MCP servers, pull requests…",
   "pairs_with": null,
   "banks": [
    "Hebrish/AI-Interactions-Sentence-Bank"
   ]
  },
  {
   "id": "danielrosehill/Tech-Sentences",
   "owner": "danielrosehill",
   "name": "Tech Sentences",
   "group": "Tech",
   "gated": false,
   "rows": 6538,
   "hours": 10.0,
   "sha": "8694e8146bb31818f9184fdb1e96a6262bb11385",
   "bytes": 3235162861,
   "modified": "2026-11-06T13:26:24+00:00",
   "summary": "Dictation-style English sentences dense in software, DevOps, cloud, self-hosting and AI vocabulary (product names, CLI tools, acronyms, model names), read aloud by one speaker. Terms use the vendor's own casing (GitHub…",
   "pairs_with": null,
   "banks": [
    "Hebrish/AI-Tech-Vocabulary-Sentence-Bank"
   ]
  },
  {
   "id": "danielrosehill/Tech-Sentences-For-ASR-Training",
   "owner": "danielrosehill",
   "name": "Tech Sentences For ASR Training",
   "group": "Tech",
   "gated": false,
   "rows": 205,
   "hours": 1.25,
   "sha": "91730ca76270f75dcdbb51b25f4b152d175087c4",
   "bytes": 144192607,
   "modified": "2026-11-03T18:40:20+00:00",
   "summary": "A specialized speech dataset for fine-tuning Automatic Speech Recognition (ASR) models on technical and developer vocabulary. Contains human-recorded audio samples covering software engineering, cloud infrastructure, DevOps, and…",
   "pairs_with": null,
   "banks": []
  },
  {
   "id": "danielrosehill/Linux-Admin-Sentences",
   "owner": "danielrosehill",
   "name": "Linux Admin Sentences",
   "group": "Tech",
   "gated": false,
   "rows": 527,
   "hours": 0.86,
   "sha": "89f3001d11f537e865fedeca9559db3d248d6ec1",
   "bytes": 281636138,
   "modified": "2026-11-05T21:46:40+00:00",
   "summary": "Dictation-style English sentences about Linux desktop and server administration (KDE Plasma, GNOME, systemd, storage, networking, homelab), read aloud by one speaker. The focus is names that a speech model writes as an ordinary…",
   "pairs_with": null,
   "banks": [
    "Hebrish/Linux-Admin-Sentence-Bank"
   ]
  },
  {
   "id": "Hebrish/Acronym-Sentences",
   "owner": "Hebrish",
   "name": "Acronym Sentences",
   "group": "Tech",
   "gated": false,
   "rows": 93,
   "hours": 0.11,
   "sha": "0d2d3dd5c8c5391ecaa28f63ed51ec8ac9ce3065",
   "bytes": 29048163,
   "modified": "2026-11-06T11:01:32+00:00",
   "summary": "Natural sentences with acronyms read by one speaker, both spelled out (API, SSH, HTTPS) and said as words (NASA, JSON, YAML), each in its standard written form. prompt_kind is letters, word or mixed.",
   "pairs_with": null,
   "banks": []
  },
  {
   "id": "Hebrish/Expanded-Acronym-Sentences",
   "owner": "Hebrish",
   "name": "Expanded Acronym Sentences",
   "group": "Tech",
   "gated": true,
   "rows": 50,
   "hours": 0.07,
   "sha": "c8b0f891c1d54d2bb30e66b51b1a0b8a576539d8",
   "bytes": 10331927,
   "modified": "2026-11-05T13:56:16+00:00",
   "summary": "Chat and business shorthand said as letters by one speaker (\"by E O D\", \"F Y I\", \"I M O\") with the transcript writing it out in full (\"by end of day\", \"For your information\", \"In my opinion\"). spoken_text is the script with the…",
   "pairs_with": null,
   "banks": []
  },
  {
   "id": "Hebrish/Brand-Name-Sentences",
   "owner": "Hebrish",
   "name": "Brand Name Sentences",
   "group": "Tech",
   "gated": true,
   "rows": 378,
   "hours": 0.7,
   "sha": "20a9ae91243a66ab534dfe768cb4070556290855",
   "bytes": 85326816,
   "modified": "2026-11-05T13:44:59+00:00",
   "summary": "Natural sentences with company, product, AI model and open-source project names (Anthropic, OpenRouter, Amazon Bedrock, Qwen, Kubernetes, Nginx) read by one speaker, written in each name's official form. target_terms lists the…",
   "pairs_with": null,
   "banks": []
  },
  {
   "id": "danielrosehill/English-Hebrew-Codeswitching-Sentences",
   "owner": "danielrosehill",
   "name": "English Hebrew Codeswitching Sentences",
   "group": "Hebrew, Yiddish and Jewish life",
   "gated": true,
   "rows": 8056,
   "hours": 13.77,
   "sha": "3bc5099ebcec044b88928ac70c00b263aa8b457e",
   "bytes": 3073679888,
   "modified": "2026-11-06T13:40:55+00:00",
   "summary": "English sentences with everyday Hebrew words and Israeli names written in Latin letters, read aloud by one English speaker living in Israel. Hebrew words follow one canonical spelling convention, and Hebrew proper nouns are…",
   "pairs_with": null,
   "banks": []
  },
  {
   "id": "Hebrish/English-Hebrew-Mixed-Sentences",
   "owner": "Hebrish",
   "name": "English Hebrew Mixed Sentences",
   "group": "Hebrew, Yiddish and Jewish life",
   "gated": true,
   "rows": 637,
   "hours": 0.75,
   "sha": "c5c640282e72b6450c3a1a7abef75b73b8e4ce0d",
   "bytes": 86493826,
   "modified": "2026-10-30T13:05:48+00:00",
   "summary": "A dataset of English sentences with Hebrew words and phrases interspersed, designed for speech-to-text training and evaluation for English speakers in Israel.",
   "pairs_with": null,
   "banks": []
  },
  {
   "id": "Hebrish/Hebrish-TTS-Voice-Recordings",
   "owner": "Hebrish",
   "name": "Hebrish TTS Voice Recordings",
   "group": "Hebrew, Yiddish and Jewish life",
   "gated": true,
   "rows": 10700,
   "hours": 14.98,
   "sha": "1ae5f7b53a2f2f271491c6daa07fbcf38ca950c9",
   "bytes": 5279062075,
   "modified": "2026-11-06T14:01:37+00:00",
   "summary": "Single-speaker read and spontaneous speech for training a text-to-speech voice that code-switches between English and Hebrew (\"Hebrish\") the way an English-speaking immigrant in Israel does.",
   "pairs_with": null,
   "banks": []
  },
  {
   "id": "Hebrish/Yiddish-Sentences",
   "owner": "Hebrish",
   "name": "Yiddish Sentences",
   "group": "Hebrew, Yiddish and Jewish life",
   "gated": true,
   "rows": 348,
   "hours": 0.55,
   "sha": "9f26c5e4d0ca6d35aacb13de5fb22685643b7485",
   "bytes": 127013388,
   "modified": "2026-11-03T20:35:41+00:00",
   "summary": "English sentences with Yiddish words written in Latin letters (shul, daven, cholent, mensch, freier, tachles), the way English speakers in Israel use them, read aloud by one speaker. Many of these words are also used in modern…",
   "pairs_with": null,
   "banks": []
  },
  {
   "id": "Hebrish/Jewish-Religious-Terminology-Sentences",
   "owner": "Hebrish",
   "name": "Jewish Religious Terminology Sentences",
   "group": "Hebrew, Yiddish and Jewish life",
   "gated": true,
   "rows": 2096,
   "hours": 3.78,
   "sha": "4e89d3f4e9b690e29580b5232a257f0fc7dde109",
   "bytes": 880924421,
   "modified": "2026-11-06T13:40:55+00:00",
   "summary": "English sentences with Jewish religious vocabulary written in Latin letters: Shabbat and the festivals, prayer and the synagogue, Torah portions, Talmud and halacha, kashrut, and life-cycle events, read aloud by one speaker. Many…",
   "pairs_with": null,
   "banks": []
  },
  {
   "id": "Hebrish/Judaica-Sentences",
   "owner": "Hebrish",
   "name": "Judaica Sentences",
   "group": "Hebrew, Yiddish and Jewish life",
   "gated": false,
   "rows": 672,
   "hours": 1.27,
   "sha": "4e815717a1636d11fdc3bb7b97ccda4cd0177d55",
   "bytes": 461160555,
   "modified": "2026-11-06T13:41:13+00:00",
   "summary": "Real sentences from traditional Jewish works in English, read by one speaker, Hebrew terms in romanized form: Tanach (Metsudah), Mishnah Yomit (Joshua Kulp), Talmud Bavli (Sefaria Community Translation; Tractate Berakot, A.…",
   "pairs_with": null,
   "banks": []
  },
  {
   "id": "Hebrish/Israeli-Name-Sentences",
   "owner": "Hebrish",
   "name": "Israeli Name Sentences",
   "group": "Hebrew, Yiddish and Jewish life",
   "gated": true,
   "rows": 112,
   "hours": 0.17,
   "sha": "1b1dffc23f6ba147a5ed1e215b582d8d455a1186",
   "bytes": 55541697,
   "modified": "2026-11-03T14:33:32+00:00",
   "summary": "English messages and emails that mention an Israeli or Jewish person's name, a first name (Naftali, Yotam, Tzlil, Bat-El) or a surname (Buskila, Ifergan, Weinberg), written in its common Israeli-English spelling, read aloud by…",
   "pairs_with": null,
   "banks": []
  },
  {
   "id": "Hebrish/Hard-ASR-Sentences",
   "owner": "Hebrish",
   "name": "Hard ASR Sentences",
   "group": "Hard words and numbers",
   "gated": true,
   "rows": 63,
   "hours": 0.07,
   "sha": "976c5bded46307a916f44b666478f2a3280923b2",
   "bytes": 17779988,
   "modified": "2026-11-03T06:54:59+00:00",
   "summary": "English sentences speech recognition finds hard, read by one speaker: Harvard sentences (IEEE 1969, public domain), tongue twisters, homographs, garden-path sentences, rare words, dense numbers and units, unusual proper nouns.…",
   "pairs_with": null,
   "banks": []
  },
  {
   "id": "danielrosehill/Homophone-Context-Sentences",
   "owner": "danielrosehill",
   "name": "Homophone Context Sentences",
   "group": "Hard words and numbers",
   "gated": false,
   "rows": 156,
   "hours": 0.24,
   "sha": "8a9122590458535967a7e7a5eee544986ac78485",
   "bytes": 68626177,
   "modified": "2026-11-03T18:39:35+00:00",
   "summary": "English sentences whose context settles which spelling of a homophone is meant (their/there, principal/principle, and 58 more sets), read aloud by one speaker. Sentences to read: Homophone-Context-Sentence-Bank.",
   "pairs_with": null,
   "banks": [
    "Hebrish/Homophone-Context-Sentence-Bank"
   ]
  },
  {
   "id": "Hebrish/Pronunciation-Variants",
   "owner": "Hebrish",
   "name": "Pronunciation Variants",
   "group": "Hard words and numbers",
   "gated": true,
   "rows": 164,
   "hours": 0.23,
   "sha": "c5a8dd4e764a02c04c40bf6823af3717217e6716",
   "bytes": 57254520,
   "modified": "2026-11-06T11:04:15+00:00",
   "summary": "Takes in which a word was deliberately said one particular way, from the main dataset, stratified by variant_category. Two kinds: a term from the project's pronunciation registry said in a recorded variant…",
   "pairs_with": null,
   "banks": []
  },
  {
   "id": "Hebrish/Currency-Sentences",
   "owner": "Hebrish",
   "name": "Currency Sentences",
   "group": "Hard words and numbers",
   "gated": true,
   "rows": 156,
   "hours": 0.23,
   "sha": "21b0ce02c3af43c9346cf9df1b2d13bfd1e0bb2d",
   "bytes": 39118677,
   "modified": "2026-11-05T13:56:15+00:00",
   "summary": "One speaker saying amounts of money the natural way (\"50 shekels\", \"a dollar fifty\", \"6 pounds 50\"). spoken_text is the script that was read; text is the written form a dictation model should give: 50 NIS, $1.50, €18, £6.50 (NIS…",
   "pairs_with": null,
   "banks": []
  },
  {
   "id": "Hebrish/Noisy-Condition-Sentences",
   "owner": "Hebrish",
   "name": "Noisy Condition Sentences",
   "group": "Speech conditions",
   "gated": true,
   "rows": 7202,
   "hours": 10.1,
   "sha": "371cdabe72a70c191ff100a685d72be875b427d7",
   "bytes": 3199547777,
   "modified": "2026-11-06T11:04:00+00:00",
   "summary": "Every take from the main dataset recorded in noise, whatever its category: outdoors, in a noisy room, with traffic, other people talking, background noise or a crying baby. A robustness and evaluation set for dictation in real…",
   "pairs_with": null,
   "banks": []
  },
  {
   "id": "Hebrish/Whispered-Sentences",
   "owner": "Hebrish",
   "name": "Whispered Sentences",
   "group": "Speech conditions",
   "gated": false,
   "rows": 312,
   "hours": 0.49,
   "sha": "f4aa818b33d2c42f9bf51b24eae17c67e82abc94",
   "bytes": 160507066,
   "modified": "2026-11-06T01:41:44+00:00",
   "summary": "Experimental robustness data. Plain English sentences, short and dictation-length, whispered by one speaker into a phone, the way he dictates when someone is asleep nearby.",
   "pairs_with": null,
   "banks": []
  },
  {
   "id": "Hebrish/Disfluent-Read-Sentences",
   "owner": "Hebrish",
   "name": "Disfluent Read Sentences",
   "group": "Speech conditions",
   "gated": true,
   "rows": 55,
   "hours": 0.22,
   "sha": "5e468305a0cba2bdd934a8c54cdb42158e5d4e17",
   "bytes": 25580949,
   "modified": "2026-10-30T13:46:43+00:00",
   "summary": "Experimental. Plain English sentences read with deliberate hesitations (uh, um, eh; repeated words have their own dataset since 2026-10-20) by one speaker.",
   "pairs_with": null,
   "banks": []
  },
  {
   "id": "Hebrish/Repeated-Word-Sentences",
   "owner": "Hebrish",
   "name": "Repeated Word Sentences",
   "group": "Speech conditions",
   "gated": true,
   "rows": 19,
   "hours": 0.06,
   "sha": "a2bd83ab4541ea49d912d987ddb085391c525501",
   "bytes": 7321178,
   "modified": "2026-10-30T13:46:07+00:00",
   "summary": "Experimental. Plain English sentences read by one speaker repeating a word or phrase now and then (\"the the report\", \"I think I think\"), with no fillers.",
   "pairs_with": null,
   "banks": []
  },
  {
   "id": "Hebrish/Self-Correction-Sentences",
   "owner": "Hebrish",
   "name": "Self Correction Sentences",
   "group": "Speech conditions",
   "gated": false,
   "rows": 27,
   "hours": 0.05,
   "sha": "d1e0b4d80c5ced37bbbd0d89077b7c43419018cd",
   "bytes": 14303421,
   "modified": "2026-10-30T13:46:18+00:00",
   "summary": "One speaker correcting himself mid-sentence (\"send it Tuesday, no, Wednesday\"). spoken_text is the script that was read; text is the corrected sentence only, the transcript a dictation model should give.",
   "pairs_with": null,
   "banks": []
  },
  {
   "id": "Hebrish/Spoken-Aside-Sentences",
   "owner": "Hebrish",
   "name": "Spoken Aside Sentences",
   "group": "Speech conditions",
   "gated": false,
   "rows": 5,
   "hours": 0.01,
   "sha": "12b1eb92578ea6f7c9068f68b7b8ac3c99b5236a",
   "bytes": 2849598,
   "modified": "2026-10-30T13:45:40+00:00",
   "summary": "One speaker dictating a sentence and, partway through, saying something to someone in the room (\"come in, Hannah\"). text excludes the aside; aside_text and aside_position (start, middle, end) give it; spoken_text is the full…",
   "pairs_with": null,
   "banks": []
  },
  {
   "id": "Hebrish/Singing-Sentences",
   "owner": "Hebrish",
   "name": "Singing Sentences",
   "group": "Speech conditions",
   "gated": false,
   "rows": 16,
   "hours": 0.02,
   "sha": "f934067e2142a8e83d0b8956b31df754fbeac6ed",
   "bytes": 2771750,
   "modified": "2026-10-30T13:45:58+00:00",
   "summary": "Experimental. Short plain English sentences sung by one speaker, to any tune.",
   "pairs_with": null,
   "banks": []
  },
  {
   "id": "Hebrish/Weird-Voice-Sentences",
   "owner": "Hebrish",
   "name": "Weird Voice Sentences",
   "group": "Speech conditions",
   "gated": false,
   "rows": 6,
   "hours": 0.01,
   "sha": "0b43ef5dd362b9b1ed765588ca0dc184bcdaee9f",
   "bytes": 1477153,
   "modified": "2026-10-30T13:45:47+00:00",
   "summary": "Experimental. Plain English sentences read by one speaker in a put-on voice (very deep, squeaky, robot, cartoon, mock accent, mumbly).",
   "pairs_with": null,
   "banks": []
  },
  {
   "id": "Hebrish/English-Hebrew-Codeswitching-ASR-Benchmark",
   "owner": "Hebrish",
   "name": "English Hebrew Codeswitching ASR Benchmark",
   "group": "Evaluation and task sets",
   "gated": true,
   "rows": 324,
   "hours": 0.61,
   "sha": "1b36999d49f0206bbec76667c3e712f11dd4f1d6",
   "bytes": 70266482,
   "modified": "2026-10-30T14:08:41+00:00",
   "summary": "A frozen, versioned test set for measuring how well speech recognition handles English speech with Hebrew words in it: \"pick up some bamba from the makolet\", \"I have to go to Bituach Leumi tomorrow\". The references write each…",
   "pairs_with": null,
   "banks": []
  },
  {
   "id": "Hebrish/Hebrish-Validation",
   "owner": "Hebrish",
   "name": "Hebrish Validation",
   "group": "Evaluation and task sets",
   "gated": false,
   "rows": 16,
   "hours": 0.52,
   "sha": "940fbee293900f8b9790ef9e330516c7105674e4",
   "bytes": 113343745,
   "modified": "2026-11-02T21:09:11+00:00",
   "summary": "A validation benchmark for the Hebrish English-Hebrew code-switching speech recognition models (Sabich and the other lines). Each row is one continuous read of a fixed script of about one minute, with the script as the exact…",
   "pairs_with": null,
   "banks": []
  },
  {
   "id": "danielrosehill/Small-STT-Eval-Audio-Dataset",
   "owner": "danielrosehill",
   "name": "Small STT Eval Audio Dataset",
   "group": "Evaluation and task sets",
   "gated": false,
   "rows": 92,
   "hours": 0.21,
   "sha": "d523de0a8cab061d209a16edbbe4bf13241774d0",
   "bytes": 24749911,
   "modified": "2026-10-30T15:17:06+00:00",
   "summary": "A small speech-to-text evaluation dataset containing 92 audio samples with ground truth transcriptions. Designed for evaluating STT systems on technical vocabulary, code-switching (English/Hebrew), and various speaking styles.",
   "pairs_with": null,
   "banks": []
  },
  {
   "id": "danielrosehill/Paragraph-Dictation-Passages",
   "owner": "danielrosehill",
   "name": "Paragraph Dictation Passages",
   "group": "Evaluation and task sets",
   "gated": false,
   "rows": 3,
   "hours": 0.01,
   "sha": "44da4a64b51d2f18e8a8c13dca3b3905e0594561",
   "bytes": 1444794,
   "modified": "2026-11-03T18:39:48+00:00",
   "summary": "Data for a separate paragraph-inference model; not used to train any Hebrish model. Passages of 2 to 4 paragraphs (emails, prompts to AI coding agents, voice notes, messages, meeting notes, blog drafts) dictated in one take by…",
   "pairs_with": null,
   "banks": []
  },
  {
   "id": "danielrosehill/Proofed-ASR-Cleanup-Training-Data",
   "owner": "danielrosehill",
   "name": "Proofed ASR Cleanup Training Data",
   "group": "Evaluation and task sets",
   "gated": false,
   "rows": 606,
   "hours": 1.15,
   "sha": "5827d2a754a834c3061973a44922906c6dde5604",
   "bytes": 159539347,
   "modified": "2026-10-30T14:01:43+00:00",
   "summary": "Audio paired with clean, proofed target text for training an ASR model to do its own post-processing: no fillers, repeats or false starts, numbers and money as digits, self-corrections applied, asides to other people left out…",
   "pairs_with": null,
   "banks": []
  }
 ]
}