{"adoption": {"forks": 2387, "observed_at": "2026-08-28T04:11:35.338006+00:00", "stars": 23765}, "canonical_url": "https://ross.abutalabs.com/products/whisperx", "card": {"archived": false, "artifact_type": "library", "description": "WhisperX:  Automatic Speech Recognition with Word-level Timestamps (& Diarization)", "domain": ["speech-processing", "machine-learning"], "enriched": true, "function": ["speech-recognition", "machine-learning", "audio-processing"], "health_score": 94, "homepage": null, "language": "Python", "license": "BSD-2-Clause", "license_family": "permissive", "maturity": "active", "member_repos": ["m-bain/whisperX"], "name": "m-bain/whisperX", "platform": ["python", "cli"], "pushed_at": "2026-07-13T08:30:07+00:00", "repo": "m-bain/whisperX", "stars": 23765, "tags": ["asr", "whisper", "word-level-timestamps", "speaker-diarization", "forced-alignment", "transcription", "faster-whisper", "wav2vec2", "pyannote", "audio", "gpu"], "topics": ["asr", "speech", "speech-recognition", "speech-to-text", "whisper"], "urls": [], "use_cases": ["transcribe audio files with word-level timestamps", "add speaker labels to meeting or interview transcripts", "run fast batched speech-to-text on GPU", "reduce Whisper hallucinations with voice activity detection", "align existing transcripts to audio at phoneme level", "diarize multi-speaker recordings"], "what_it_is": "WhisperX is a Python library providing fast automatic speech recognition with word-level timestamps and speaker diarization. It combines Whisper-based batched inference (up to 70x realtime), wav2vec2 forced alignment for accurate word timings, VAD preprocessing, and pyannote-audio speaker labeling.", "when_to_avoid": ["you need a hosted transcription API with real speaker names from meeting platforms", "you only need rough utterance-level transcripts and want a simpler setup", "you have no GPU and need maximum throughput"], "when_to_choose": ["you need per-word timing accuracy beyond Whisper's utterance-level timestamps", "you want fast GPU transcription with batching and a memory-efficient backend", "you need speaker diarization integrated into the ASR pipeline"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/whisperx", "repo": "m-bain/whisperX", "role": "main", "score": 91}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:11:35.338006+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T16:56:21.055951+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ec77381252da213e1ca221b8b901fcd303d6be8f9c650d1d1806f246f466b709", "fetched_at": "2026-08-28T04:11:35.338006+00:00", "kind": "readme", "missing": false, "url": "https://github.com/m-bain/whisperX"}, {"content_hash": "20531f2c2abd34869448e97c2566a09e2863c5ac7a0806c819aa6b2cd828dad4", "fetched_at": "2026-08-29T07:53:56.868266+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/whisperx/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:11:35.338006+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T16:56:21.055951+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ec77381252da213e1ca221b8b901fcd303d6be8f9c650d1d1806f246f466b709", "fetched_at": "2026-08-28T04:11:35.338006+00:00", "kind": "readme", "missing": false, "url": "https://github.com/m-bain/whisperX"}, {"content_hash": "20531f2c2abd34869448e97c2566a09e2863c5ac7a0806c819aa6b2cd828dad4", "fetched_at": "2026-08-29T07:53:56.868266+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/whisperx/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T16:56:21.055951+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ec77381252da213e1ca221b8b901fcd303d6be8f9c650d1d1806f246f466b709", "fetched_at": "2026-08-28T04:11:35.338006+00:00", "kind": "readme", "missing": false, "url": "https://github.com/m-bain/whisperX"}, {"content_hash": "20531f2c2abd34869448e97c2566a09e2863c5ac7a0806c819aa6b2cd828dad4", "fetched_at": "2026-08-29T07:53:56.868266+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/whisperx/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:11:35.338006+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:11:35.338006+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:11:35.338006+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T16:56:21.055951+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ec77381252da213e1ca221b8b901fcd303d6be8f9c650d1d1806f246f466b709", "fetched_at": "2026-08-28T04:11:35.338006+00:00", "kind": "readme", "missing": false, "url": "https://github.com/m-bain/whisperX"}, {"content_hash": "20531f2c2abd34869448e97c2566a09e2863c5ac7a0806c819aa6b2cd828dad4", "fetched_at": "2026-08-29T07:53:56.868266+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/whisperx/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:11:35.338006+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:11:35.338006+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T16:56:21.055951+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ec77381252da213e1ca221b8b901fcd303d6be8f9c650d1d1806f246f466b709", "fetched_at": "2026-08-28T04:11:35.338006+00:00", "kind": "readme", "missing": false, "url": "https://github.com/m-bain/whisperX"}, {"content_hash": "20531f2c2abd34869448e97c2566a09e2863c5ac7a0806c819aa6b2cd828dad4", "fetched_at": "2026-08-29T07:53:56.868266+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/whisperx/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:11:35.338006+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:11:35.338006+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:11:35.338006+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T16:56:21.055951+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ec77381252da213e1ca221b8b901fcd303d6be8f9c650d1d1806f246f466b709", "fetched_at": "2026-08-28T04:11:35.338006+00:00", "kind": "readme", "missing": false, "url": "https://github.com/m-bain/whisperX"}, {"content_hash": "20531f2c2abd34869448e97c2566a09e2863c5ac7a0806c819aa6b2cd828dad4", "fetched_at": "2026-08-29T07:53:56.868266+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/whisperx/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:11:35.338006+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:11:35.338006+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T16:56:21.055951+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ec77381252da213e1ca221b8b901fcd303d6be8f9c650d1d1806f246f466b709", "fetched_at": "2026-08-28T04:11:35.338006+00:00", "kind": "readme", "missing": false, "url": "https://github.com/m-bain/whisperX"}, {"content_hash": "20531f2c2abd34869448e97c2566a09e2863c5ac7a0806c819aa6b2cd828dad4", "fetched_at": "2026-08-29T07:53:56.868266+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/whisperx/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T16:56:21.055951+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ec77381252da213e1ca221b8b901fcd303d6be8f9c650d1d1806f246f466b709", "fetched_at": "2026-08-28T04:11:35.338006+00:00", "kind": "readme", "missing": false, "url": "https://github.com/m-bain/whisperX"}, {"content_hash": "20531f2c2abd34869448e97c2566a09e2863c5ac7a0806c819aa6b2cd828dad4", "fetched_at": "2026-08-29T07:53:56.868266+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/whisperx/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T16:56:21.055951+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ec77381252da213e1ca221b8b901fcd303d6be8f9c650d1d1806f246f466b709", "fetched_at": "2026-08-28T04:11:35.338006+00:00", "kind": "readme", "missing": false, "url": "https://github.com/m-bain/whisperX"}, {"content_hash": "20531f2c2abd34869448e97c2566a09e2863c5ac7a0806c819aa6b2cd828dad4", "fetched_at": "2026-08-29T07:53:56.868266+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/whisperx/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T16:56:21.055951+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ec77381252da213e1ca221b8b901fcd303d6be8f9c650d1d1806f246f466b709", "fetched_at": "2026-08-28T04:11:35.338006+00:00", "kind": "readme", "missing": false, "url": "https://github.com/m-bain/whisperX"}, {"content_hash": "20531f2c2abd34869448e97c2566a09e2863c5ac7a0806c819aa6b2cd828dad4", "fetched_at": "2026-08-29T07:53:56.868266+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/whisperx/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 92, "longevity": 97, "rhythm": 85}, "computed_at": "2026-09-03T02:39:23.370411+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1364, "days_push": 51, "days_rel": 100, "gap_med": 1, "n_releases_24m": 36}, "score": 91, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}