{"schema":"record/v1","id":"src_01M569EGSVM7N346FE5S54X20Z","type":"source","revision":2,"etag":"\"r2.s0\"","title":"OpenAI Whisper","summary":null,"status":"active","body":{"text":"","archived":false,"checked_at":"2026-10-17T00:00:00.000Z","parent_url":null,"usefulness":"General-purpose multilingual speech recognition, speech translation, language ID and VAD from one Transformer; the baseline for transcripts, subtitles and dialogue indexing. Code and weights are MIT.","source_type":"repository","availability":"available","dependencies":["PyTorch","ffmpeg","tiktoken"],"source_owner":"OpenAI","canonical_url":"https://github.com/openai/whisper","next_check_at":"2026-10-24T00:00:00.000Z","successor_url":null,"hardware_notes":null,"known_limitations":[],"upstream_updated_at":"2026-08-31T17:19:19.000Z"},"categories":["T13"],"tags":["level:established","asr","transcription","speech-translation","subtitles","mit","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/openai/whisper","claim":"README: Whisper is trained on multiple speech tasks (multilingual speech recognition, speech translation, spoken language identification, voice activity detection) represented as a sequence of tokens for a Transformer sequence-to-sequence model.","locator":"README, Approach","classification":"upstream_claim"},{"url":"https://github.com/openai/whisper","claim":"README License: code and model weights are released under the MIT License.","locator":"README, License","classification":"sourced_fact"},{"url":"https://github.com/openai/whisper","claim":"README setup: trained with Python 3.9.9 and PyTorch 1.10.1; expected compatible with Python 3.8-3.11; may need rust for tiktoken; GitHub: not archived, last push 2026-08-31.","locator":"README, Setup","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 README.","hosting":"permitted","component":"code","license_id":"MIT","modification":"permitted","evidence_urls":["https://github.com/openai/whisper/blob/main/LICENSE"],"model_training":"unknown","redistribution":"permitted"},{"notes":"README states weights are MIT; training data terms are not addressed.","hosting":"permitted","component":"model_weights","license_id":"MIT","modification":"permitted","evidence_urls":["https://github.com/openai/whisper#license"],"model_training":"unknown","redistribution":"permitted"}],"attribution":{"origin":"research_agent","upstream_owner":"OpenAI","upstream_url":"https://github.com/openai/whisper","imported_from":"content/seeds/research/curated/resources.jsonl#openai--whisper","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":"openai--whisper","name":"OpenAI Whisper","tags":["level:established","asr","transcription","speech-translation","subtitles","mit"],"rights":[{"notes":"MIT per README.","hosting":"permitted","component":"code","license_id":"MIT","modification":"permitted","evidence_urls":["https://github.com/openai/whisper/blob/main/LICENSE"],"model_training":"unknown","redistribution":"permitted"},{"notes":"README states weights are MIT; training data terms are not addressed.","hosting":"permitted","component":"model_weights","license_id":"MIT","modification":"permitted","evidence_urls":["https://github.com/openai/whisper#license"],"model_training":"unknown","redistribution":"permitted"}],"archived":false,"evidence":[{"url":"https://github.com/openai/whisper","claim":"README: Whisper is trained on multiple speech tasks (multilingual speech recognition, speech translation, spoken language identification, voice activity detection) represented as a sequence of tokens for a Transformer sequence-to-sequence model.","locator":"README, Approach","classification":"upstream_claim"},{"url":"https://github.com/openai/whisper","claim":"README License: code and model weights are released under the MIT License.","locator":"README, License","classification":"sourced_fact"},{"url":"https://github.com/openai/whisper","claim":"README setup: trained with Python 3.9.9 and PyTorch 1.10.1; expected compatible with Python 3.8-3.11; may need rust for tiktoken; GitHub: not archived, last push 2026-08-31.","locator":"README, Setup","classification":"sourced_fact"}],"language":"Python","checked_on":"2026-10-17","usefulness":"General-purpose multilingual speech recognition, speech translation, language ID and VAD from one Transformer; the baseline for transcripts, subtitles and dialogue indexing. Code and weights are MIT.","source_type":"repository","category_ids":["T13"],"dependencies":["PyTorch","ffmpeg","tiktoken"],"source_owner":"OpenAI","canonical_url":"https://github.com/openai/whisper","review_status":"reviewed","schema_version":"0.1","execution_status":"not_run","inspection_status":"source_inspected","upstream_updated_at":"2026-08-31T17:19:19Z","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":"openai--whisper","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":"openai--whisper","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":"4f77ec508b1dc85b00cb294f1227b40f34ef31eefd5f14d65f449b7c0469dfc3","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_01M569EGSVM7N346FE5S54X20Z","api_url":"https://veyrul.com/v1/records/src_01M569EGSVM7N346FE5S54X20Z","created_at":"2026-10-18T01:19:03.981Z","updated_at":"2026-10-18T01:24:31.262Z","last_activity_at":"2026-10-18T01:24:31.262Z"}