{"adoption": {"forks": 262, "observed_at": "2026-08-28T04:06:27.657882+00:00", "stars": 2222}, "canonical_url": "https://ross.abutalabs.com/products/voice_datasets", "card": {"archived": false, "artifact_type": "dataset", "description": "🔊 A comprehensive list of open-source datasets for voice and sound computing (95+ datasets).", "domain": ["speech-processing", "machine-learning", "artificial-intelligence"], "enriched": true, "function": ["speech-recognition", "audio-processing", "machine-learning", "nlp"], "health_score": 20, "homepage": "https://voicecomputing.org", "language": null, "license": null, "license_family": "other", "maturity": "maintenance", "member_repos": ["jim-schwoebel/voice_datasets"], "name": "jim-schwoebel/voice_datasets", "platform": ["cross-platform"], "pushed_at": "2024-06-06T10:47:45+00:00", "repo": "jim-schwoebel/voice_datasets", "stars": 2222, "tags": ["awesome-list", "voice-datasets", "speech-datasets", "audio-datasets", "curated-list", "voice-computing", "audio"], "topics": ["voice-dataset", "voice-datasets", "audio-dataset", "audio-datasets", "datasets", "dataset", "voice", "data", "voice-computing", "voice-control", "voice-synthesis", "voice-commands", "voice-assistant", "voice-recognition", "voice-chat", "voice-activity-detection", "voice-conversion", "noise"], "urls": [], "use_cases": ["find open-source speech recognition datasets", "locate audio datasets for training voice models", "find datasets for speech emotion recognition", "find voice activity detection training data", "find datasets for voice synthesis and TTS", "discover speaker diarization datasets"], "what_it_is": "A curated list of 95+ open-source datasets for voice and sound computing, covering speech, audio events, and music. It serves as a reference catalog for researchers and developers building voice-related machine learning applications.", "when_to_avoid": ["you need the actual dataset files - this is a list of links, not a hosted dataset", "you need a maintained, license-verified dataset catalog with guaranteed up-to-date links", "you need non-audio machine learning datasets"], "when_to_choose": ["you need to discover publicly available voice or audio datasets for ML projects", "you are researching speech, emotion, or audio event recognition and want a starting catalog", "you want a curated reference rather than searching Kaggle or academic sources individually"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/voice_datasets", "repo": "jim-schwoebel/voice_datasets", "role": "main", "score": 23}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:06:27.657882+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:45:45.864582+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3132ddbfbbab3b2c604e6d7c6ff32612d7d9b3acc631ad04a220882f2bed5d5e", "fetched_at": "2026-08-28T04:06:27.657882+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jim-schwoebel/voice_datasets"}, {"content_hash": "09d07d8f50ce6392d8b64db2f87ac4583a7dc51dcfe57607445c9058ff79ff7d", "fetched_at": "2026-08-29T10:26:08.390836+00:00", "kind": "homepage", "missing": false, "url": "https://voicecomputing.org"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:06:27.657882+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:45:45.864582+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3132ddbfbbab3b2c604e6d7c6ff32612d7d9b3acc631ad04a220882f2bed5d5e", "fetched_at": "2026-08-28T04:06:27.657882+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jim-schwoebel/voice_datasets"}, {"content_hash": "09d07d8f50ce6392d8b64db2f87ac4583a7dc51dcfe57607445c9058ff79ff7d", "fetched_at": "2026-08-29T10:26:08.390836+00:00", "kind": "homepage", "missing": false, "url": "https://voicecomputing.org"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:45:45.864582+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3132ddbfbbab3b2c604e6d7c6ff32612d7d9b3acc631ad04a220882f2bed5d5e", "fetched_at": "2026-08-28T04:06:27.657882+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jim-schwoebel/voice_datasets"}, {"content_hash": "09d07d8f50ce6392d8b64db2f87ac4583a7dc51dcfe57607445c9058ff79ff7d", "fetched_at": "2026-08-29T10:26:08.390836+00:00", "kind": "homepage", "missing": false, "url": "https://voicecomputing.org"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:06:27.657882+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:06:27.657882+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:06:27.657882+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:45:45.864582+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3132ddbfbbab3b2c604e6d7c6ff32612d7d9b3acc631ad04a220882f2bed5d5e", "fetched_at": "2026-08-28T04:06:27.657882+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jim-schwoebel/voice_datasets"}, {"content_hash": "09d07d8f50ce6392d8b64db2f87ac4583a7dc51dcfe57607445c9058ff79ff7d", "fetched_at": "2026-08-29T10:26:08.390836+00:00", "kind": "homepage", "missing": false, "url": "https://voicecomputing.org"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:06:27.657882+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:06:27.657882+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:45:45.864582+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3132ddbfbbab3b2c604e6d7c6ff32612d7d9b3acc631ad04a220882f2bed5d5e", "fetched_at": "2026-08-28T04:06:27.657882+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jim-schwoebel/voice_datasets"}, {"content_hash": "09d07d8f50ce6392d8b64db2f87ac4583a7dc51dcfe57607445c9058ff79ff7d", "fetched_at": "2026-08-29T10:26:08.390836+00:00", "kind": "homepage", "missing": false, "url": "https://voicecomputing.org"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:06:27.657882+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:06:27.657882+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:06:27.657882+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:45:45.864582+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3132ddbfbbab3b2c604e6d7c6ff32612d7d9b3acc631ad04a220882f2bed5d5e", "fetched_at": "2026-08-28T04:06:27.657882+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jim-schwoebel/voice_datasets"}, {"content_hash": "09d07d8f50ce6392d8b64db2f87ac4583a7dc51dcfe57607445c9058ff79ff7d", "fetched_at": "2026-08-29T10:26:08.390836+00:00", "kind": "homepage", "missing": false, "url": "https://voicecomputing.org"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:06:27.657882+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:06:27.657882+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:45:45.864582+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3132ddbfbbab3b2c604e6d7c6ff32612d7d9b3acc631ad04a220882f2bed5d5e", "fetched_at": "2026-08-28T04:06:27.657882+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jim-schwoebel/voice_datasets"}, {"content_hash": "09d07d8f50ce6392d8b64db2f87ac4583a7dc51dcfe57607445c9058ff79ff7d", "fetched_at": "2026-08-29T10:26:08.390836+00:00", "kind": "homepage", "missing": false, "url": "https://voicecomputing.org"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:45:45.864582+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3132ddbfbbab3b2c604e6d7c6ff32612d7d9b3acc631ad04a220882f2bed5d5e", "fetched_at": "2026-08-28T04:06:27.657882+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jim-schwoebel/voice_datasets"}, {"content_hash": "09d07d8f50ce6392d8b64db2f87ac4583a7dc51dcfe57607445c9058ff79ff7d", "fetched_at": "2026-08-29T10:26:08.390836+00:00", "kind": "homepage", "missing": false, "url": "https://voicecomputing.org"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:45:45.864582+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3132ddbfbbab3b2c604e6d7c6ff32612d7d9b3acc631ad04a220882f2bed5d5e", "fetched_at": "2026-08-28T04:06:27.657882+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jim-schwoebel/voice_datasets"}, {"content_hash": "09d07d8f50ce6392d8b64db2f87ac4583a7dc51dcfe57607445c9058ff79ff7d", "fetched_at": "2026-08-29T10:26:08.390836+00:00", "kind": "homepage", "missing": false, "url": "https://voicecomputing.org"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:45:45.864582+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3132ddbfbbab3b2c604e6d7c6ff32612d7d9b3acc631ad04a220882f2bed5d5e", "fetched_at": "2026-08-28T04:06:27.657882+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jim-schwoebel/voice_datasets"}, {"content_hash": "09d07d8f50ce6392d8b64db2f87ac4583a7dc51dcfe57607445c9058ff79ff7d", "fetched_at": "2026-08-29T10:26:08.390836+00:00", "kind": "homepage", "missing": false, "url": "https://voicecomputing.org"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 2597, "days_push": 818, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 23, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}