{"adoption": {"forks": 503, "observed_at": "2026-08-28T04:09:26.068458+00:00", "stars": 5630}, "canonical_url": "https://ross.abutalabs.com/products/whisper-diarization", "card": {"archived": false, "artifact_type": "library", "description": "Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper", "domain": ["speech-processing", "artificial-intelligence"], "enriched": true, "function": ["speech-recognition", "audio-processing", "machine-learning", "cli"], "health_score": 79, "homepage": null, "language": "Jupyter Notebook", "license": "BSD-2-Clause", "license_family": "permissive", "maturity": "active", "member_repos": ["MahmoudAshraf97/whisper-diarization"], "name": "MahmoudAshraf97/whisper-diarization", "platform": ["python", "cross-platform"], "pushed_at": "2026-08-15T09:11:27+00:00", "repo": "MahmoudAshraf97/whisper-diarization", "stars": 5630, "tags": ["whisper", "speaker-diarization", "asr", "transcription", "vad", "nemo", "speech-to-text", "natural-language-processing", "gpu"], "topics": ["asr", "speaker-diarization", "speech", "speech-recognition", "speech-to-text", "whisper"], "urls": [], "use_cases": ["transcribe a meeting recording with speaker labels", "add speaker diarization to whisper transcripts", "convert podcast audio into a who-said-what transcript", "identify speakers in an interview audio file", "transcribe multi-speaker audio with timestamps", "run speech-to-text with diarization on GPU"], "what_it_is": "A pipeline that combines OpenAI Whisper transcription with speaker diarization using Voice Activity Detection (MarbleNet) and speaker embeddings (TitaNet). It aligns timestamps with ctc-forced-aligner to attribute each word in the transcript to the correct speaker.", "when_to_avoid": ["you only need plain transcription without speaker labels", "you need real-time streaming diarization", "you cannot run GPU-accelerated models locally"], "when_to_choose": ["you need transcripts with per-word or per-sentence speaker attribution", "you want a ready-made pipeline combining Whisper, VAD, and speaker embeddings", "you want a Colab-friendly or CLI transcription tool with diarization"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/whisper-diarization", "repo": "MahmoudAshraf97/whisper-diarization", "role": "main", "score": 75}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:09:26.068458+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:55:20.725690+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7d7495515358f98d8a62b17ab0b024e6781016f857ad3fd1cfb2f62e860bea89", "fetched_at": "2026-08-28T04:09:26.068458+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MahmoudAshraf97/whisper-diarization"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:09:26.068458+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:55:20.725690+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7d7495515358f98d8a62b17ab0b024e6781016f857ad3fd1cfb2f62e860bea89", "fetched_at": "2026-08-28T04:09:26.068458+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MahmoudAshraf97/whisper-diarization"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:55:20.725690+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7d7495515358f98d8a62b17ab0b024e6781016f857ad3fd1cfb2f62e860bea89", "fetched_at": "2026-08-28T04:09:26.068458+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MahmoudAshraf97/whisper-diarization"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:09:26.068458+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:09:26.068458+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:09:26.068458+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:55:20.725690+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7d7495515358f98d8a62b17ab0b024e6781016f857ad3fd1cfb2f62e860bea89", "fetched_at": "2026-08-28T04:09:26.068458+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MahmoudAshraf97/whisper-diarization"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:09:26.068458+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:09:26.068458+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:55:20.725690+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7d7495515358f98d8a62b17ab0b024e6781016f857ad3fd1cfb2f62e860bea89", "fetched_at": "2026-08-28T04:09:26.068458+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MahmoudAshraf97/whisper-diarization"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:09:26.068458+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:09:26.068458+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:09:26.068458+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:55:20.725690+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7d7495515358f98d8a62b17ab0b024e6781016f857ad3fd1cfb2f62e860bea89", "fetched_at": "2026-08-28T04:09:26.068458+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MahmoudAshraf97/whisper-diarization"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:09:26.068458+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:09:26.068458+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:55:20.725690+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7d7495515358f98d8a62b17ab0b024e6781016f857ad3fd1cfb2f62e860bea89", "fetched_at": "2026-08-28T04:09:26.068458+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MahmoudAshraf97/whisper-diarization"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:55:20.725690+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7d7495515358f98d8a62b17ab0b024e6781016f857ad3fd1cfb2f62e860bea89", "fetched_at": "2026-08-28T04:09:26.068458+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MahmoudAshraf97/whisper-diarization"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:55:20.725690+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7d7495515358f98d8a62b17ab0b024e6781016f857ad3fd1cfb2f62e860bea89", "fetched_at": "2026-08-28T04:09:26.068458+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MahmoudAshraf97/whisper-diarization"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:55:20.725690+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7d7495515358f98d8a62b17ab0b024e6781016f857ad3fd1cfb2f62e860bea89", "fetched_at": "2026-08-28T04:09:26.068458+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MahmoudAshraf97/whisper-diarization"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 97, "longevity": 94, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1316, "days_push": 18, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 75, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}