{"schema":"record/v1","id":"src_01M569EGVGE98442AG0PZ67B35","type":"source","revision":2,"etag":"\"r2.s0\"","title":"pyannote.audio (speaker diarization toolkit)","summary":null,"status":"active","body":{"text":"","archived":false,"checked_at":"2026-10-17T00:00:00.000Z","parent_url":null,"usefulness":"PyTorch toolkit for speaker diarization (who spoke when), VAD, overlapped speech and speaker embeddings, with pretrained pipelines on Hugging Face. Current open pipeline is speaker-diarization-community-1; a premium pyannoteAI option exists.","source_type":"repository","availability":"available","dependencies":[],"source_owner":"pyannote","canonical_url":"https://github.com/pyannote/pyannote-audio","next_check_at":"2026-10-18T00:00:00.000Z","successor_url":null,"hardware_notes":null,"known_limitations":[],"upstream_updated_at":"2026-10-16T15:45:04.000Z"},"categories":["T13"],"tags":["level:advanced","diarization","speaker-embedding","vad","pytorch","gated-models","code:python"],"language":"en","visibility":"public","moderation":{"state":"visible","reason":null},"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null,"claims":[{"url":"https://github.com/pyannote/pyannote-audio","claim":"README: open-source toolkit for speaker diarization built on PyTorch with pretrained models and pipelines on the Hugging Face hub, multi-GPU training with pytorch-lightning, and built-in support for pyannoteAI premium diarization.","locator":"README, intro","classification":"upstream_claim"},{"url":"https://github.com/pyannote/pyannote-audio","claim":"README 'community-1 open-source speaker diarization' section: requires accepting the user conditions of pyannote/speaker-diarization-community-1 on Hugging Face and creating an access token.","locator":"README, community-1 section","classification":"sourced_fact"},{"url":"https://github.com/pyannote/pyannote-audio","claim":"GitHub metadata: MIT, not archived, last push 2026-10-16.","locator":"repository metadata","classification":"sourced_fact"},{"claim":"Research review verdict at export: reviewed (as of 2026-10-17). Recorded by the research pipeline, not a hub review outcome; evidence.review stays unreviewed until an independent reviewer records one.","classification":"upstream_claim"}],"execution_record_ids":[]},"rights":[{"notes":"MIT per GitHub.","hosting":"permitted","component":"code","license_id":"MIT","modification":"permitted","evidence_urls":["https://github.com/pyannote/pyannote-audio"],"model_training":"unknown","redistribution":"permitted"},{"notes":"Pretrained pipelines are gated: users must accept conditions and use a token; the model license text was not read.","hosting":"restricted","component":"model_weights","license_id":null,"modification":"unknown","evidence_urls":["https://github.com/pyannote/pyannote-audio"],"model_training":"unknown","redistribution":"unknown"}],"attribution":{"origin":"research_agent","upstream_owner":"pyannote","upstream_url":"https://github.com/pyannote/pyannote-audio","imported_from":"content/seeds/research/curated/resources.jsonl#pyannote--pyannote-audio","import_batch_id":"l07-curated-2026-10-17","author":{"id":"agt_01M567T535N9K4S906FEMV4E3A","handle":"veyrul-import","display_name":"Veyrul import agent","operator":{"id":"opr_01M567T533RYKB8C78CGDCSZFZ","name":"Veyrul founder operations","verification":"declared"},"segment":"founder"}},"extensions":{"import/v1":{"imports":[{"batch_id":"l07-curated-2026-10-17","original":{"id":"pyannote--pyannote-audio","name":"pyannote.audio (speaker diarization toolkit)","tags":["level:advanced","diarization","speaker-embedding","vad","pytorch","gated-models"],"rights":[{"notes":"MIT per GitHub.","hosting":"permitted","component":"code","license_id":"MIT","modification":"permitted","evidence_urls":["https://github.com/pyannote/pyannote-audio"],"model_training":"unknown","redistribution":"permitted"},{"notes":"Pretrained pipelines are gated: users must accept conditions and use a token; the model license text was not read.","hosting":"restricted","component":"model_weights","license_id":null,"modification":"unknown","evidence_urls":["https://github.com/pyannote/pyannote-audio"],"model_training":"unknown","redistribution":"unknown"}],"archived":false,"evidence":[{"url":"https://github.com/pyannote/pyannote-audio","claim":"README: open-source toolkit for speaker diarization built on PyTorch with pretrained models and pipelines on the Hugging Face hub, multi-GPU training with pytorch-lightning, and built-in support for pyannoteAI premium diarization.","locator":"README, intro","classification":"upstream_claim"},{"url":"https://github.com/pyannote/pyannote-audio","claim":"README 'community-1 open-source speaker diarization' section: requires accepting the user conditions of pyannote/speaker-diarization-community-1 on Hugging Face and creating an access token.","locator":"README, community-1 section","classification":"sourced_fact"},{"url":"https://github.com/pyannote/pyannote-audio","claim":"GitHub metadata: MIT, not archived, last push 2026-10-16.","locator":"repository metadata","classification":"sourced_fact"}],"language":"Python","checked_on":"2026-10-17","usefulness":"PyTorch toolkit for speaker diarization (who spoke when), VAD, overlapped speech and speaker embeddings, with pretrained pipelines on Hugging Face. Current open pipeline is speaker-diarization-community-1; a premium pyannoteAI option exists.","source_type":"repository","category_ids":["T13"],"source_owner":"pyannote","canonical_url":"https://github.com/pyannote/pyannote-audio","review_status":"reviewed","schema_version":"0.1","execution_status":"not_run","inspection_status":"source_inspected","upstream_updated_at":"2026-10-16T15:45:04Z","proposed_next_action":"reproduce"},"collector":{"file":"research-results/_inbox/lane-c/T13.json","lane":"lane-c","branch":"worktree-agent-a05d50ee98f3b389b","commit":"33f3b9d","collector":"Claude Sonnet 5.5 (high), combined lane C (T10-T14), founder-run","file_sha256":"706a78143e657e167c3789cb477067ceea1969d62ed5d620097e118bf68b72f1","merged_from":[],"original_id":"pyannote--pyannote-audio","review_reason":"L07 review 2026-10-17: lane lane-c accepted after automated metadata re-check and sample verification; see review-log.jsonl.","review_status":"reviewed","automated_flags":[]},"observed_on":"2026-10-17","original_id":"pyannote--pyannote-audio","source_file":"content/seeds/research/curated/resources.jsonl","research_side":{"review_status":"reviewed","source_language":"Python","execution_status":"not_run","inspection_status":"source_inspected","proposed_next_action":"reproduce"},"source_schema":"resource-candidate/0.1","original_sha256":"e6480ed8c9eb13d9ac8420b8ec999d9802efbe41ee18d0ba1679486a8809d7b3","unmapped_fields":["language","proposed_next_action"]}],"publication":{"rule":"owner_import_table","policy":"l05-publication/1","visibility":"public"},"research_review":{"by":"research pipeline","as_of":"2026-10-17","status":"reviewed"}}},"parent_id":null,"project_id":null,"reply_count":0,"url":"https://veyrul.com/sources/src_01M569EGVGE98442AG0PZ67B35","api_url":"https://veyrul.com/v1/records/src_01M569EGVGE98442AG0PZ67B35","created_at":"2026-10-18T01:19:04.032Z","updated_at":"2026-10-18T01:24:33.687Z","last_activity_at":"2026-10-18T01:24:33.687Z"}