{"adoption": {"forks": 152, "observed_at": "2026-08-28T04:04:36.962416+00:00", "stars": 1399}, "canonical_url": "https://ross.abutalabs.com/products/open-speech-corpora", "card": {"archived": false, "artifact_type": "dataset", "description": "💎 A list of accessible speech corpora for ASR, TTS, and other Speech Technologies", "domain": ["speech-processing", "machine-learning", "awesome-lists"], "enriched": true, "function": ["speech-recognition", "tts", "nlp", "audio-processing"], "health_score": 20, "homepage": null, "language": null, "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["coqui-ai/open-speech-corpora"], "name": "coqui-ai/open-speech-corpora", "platform": ["cross-platform"], "pushed_at": "2024-06-06T11:33:44+00:00", "repo": "coqui-ai/open-speech-corpora", "stars": 1399, "tags": ["speech-corpora", "asr", "dataset-catalog", "curated-list", "open-data", "natural-language-processing"], "topics": ["tts", "stt", "speech-to-text", "text-to-speech", "speech-recognition", "speech-synthesis", "speech-processing", "voice-recognition", "voice-activity-detection", "voice-cloning", "speech-emotion-recognition", "speech-separation"], "urls": [], "use_cases": ["find free speech datasets for training a TTS model", "locate open ASR training corpora for a specific language", "find multilingual speech data like Common Voice for speech recognition research", "source single-speaker datasets for voice cloning experiments", "compare speech corpora by license, hours, and speaker count", "find datasets for speech emotion recognition or voice activity detection"], "what_it_is": "A curated list of open and accessible speech corpora for ASR, TTS, and other speech technologies, organized by license (e.g., CC-0). It catalogs datasets with languages, hours, speaker counts, download links, and licenses.", "when_to_avoid": ["you need the actual audio data itself rather than links to it", "you need a tool or library for processing speech rather than a dataset list"], "when_to_choose": ["you need to discover open-licensed speech datasets for research or commercial use", "you want a curated catalog with download links and license details rather than raw data"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/open-speech-corpora", "repo": "coqui-ai/open-speech-corpora", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:36.962416+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:39:10.153752+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "73200e8effc8ed746abbe0fa060806bb9b16cc76d7892173545b8968fe5cb1f2", "fetched_at": "2026-08-28T04:04:36.962416+00:00", "kind": "readme", "missing": false, "url": "https://github.com/coqui-ai/open-speech-corpora"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:36.962416+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:39:10.153752+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "73200e8effc8ed746abbe0fa060806bb9b16cc76d7892173545b8968fe5cb1f2", "fetched_at": "2026-08-28T04:04:36.962416+00:00", "kind": "readme", "missing": false, "url": "https://github.com/coqui-ai/open-speech-corpora"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:39:10.153752+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "73200e8effc8ed746abbe0fa060806bb9b16cc76d7892173545b8968fe5cb1f2", "fetched_at": "2026-08-28T04:04:36.962416+00:00", "kind": "readme", "missing": false, "url": "https://github.com/coqui-ai/open-speech-corpora"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:36.962416+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:36.962416+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:36.962416+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:39:10.153752+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "73200e8effc8ed746abbe0fa060806bb9b16cc76d7892173545b8968fe5cb1f2", "fetched_at": "2026-08-28T04:04:36.962416+00:00", "kind": "readme", "missing": false, "url": "https://github.com/coqui-ai/open-speech-corpora"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:36.962416+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:36.962416+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:39:10.153752+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "73200e8effc8ed746abbe0fa060806bb9b16cc76d7892173545b8968fe5cb1f2", "fetched_at": "2026-08-28T04:04:36.962416+00:00", "kind": "readme", "missing": false, "url": "https://github.com/coqui-ai/open-speech-corpora"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:36.962416+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:36.962416+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:36.962416+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:39:10.153752+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "73200e8effc8ed746abbe0fa060806bb9b16cc76d7892173545b8968fe5cb1f2", "fetched_at": "2026-08-28T04:04:36.962416+00:00", "kind": "readme", "missing": false, "url": "https://github.com/coqui-ai/open-speech-corpora"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:36.962416+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:36.962416+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:39:10.153752+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "73200e8effc8ed746abbe0fa060806bb9b16cc76d7892173545b8968fe5cb1f2", "fetched_at": "2026-08-28T04:04:36.962416+00:00", "kind": "readme", "missing": false, "url": "https://github.com/coqui-ai/open-speech-corpora"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:39:10.153752+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "73200e8effc8ed746abbe0fa060806bb9b16cc76d7892173545b8968fe5cb1f2", "fetched_at": "2026-08-28T04:04:36.962416+00:00", "kind": "readme", "missing": false, "url": "https://github.com/coqui-ai/open-speech-corpora"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:39:10.153752+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "73200e8effc8ed746abbe0fa060806bb9b16cc76d7892173545b8968fe5cb1f2", "fetched_at": "2026-08-28T04:04:36.962416+00:00", "kind": "readme", "missing": false, "url": "https://github.com/coqui-ai/open-speech-corpora"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:39:10.153752+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "73200e8effc8ed746abbe0fa060806bb9b16cc76d7892173545b8968fe5cb1f2", "fetched_at": "2026-08-28T04:04:36.962416+00:00", "kind": "readme", "missing": false, "url": "https://github.com/coqui-ai/open-speech-corpora"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 2771, "days_push": 818, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 32, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}