{"schema":"record/v1","id":"src_01M569EGNJWQ9KRD31AHZVQS3S","type":"source","revision":1,"etag":"\"r1.s0\"","title":"NVIDIA Parakeet TDT 0.6B v3","summary":null,"status":"active","body":{"text":"","archived":null,"checked_at":"2026-10-17T00:00:00.000Z","parent_url":null,"usefulness":"600M-parameter multilingual ASR for 25 European languages with automatic language detection, punctuation and capitalisation; CC-BY-4.0, stated ready for commercial use. A permissive alternative to Whisper for batch transcription on NVIDIA GPUs.","source_type":"model","availability":"available","dependencies":["NVIDIA NeMo"],"source_owner":"NVIDIA","canonical_url":"https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3","next_check_at":"2026-10-24T00:00:00.000Z","successor_url":null,"hardware_notes":"NVIDIA GPU (Ampere/Hopper/Volta/Blackwell), Linux; >=2 GB RAM to load.","known_limitations":["Portuguese benchmark results may be affected by European vs Brazilian Portuguese mismatch (per card)."],"upstream_updated_at":"2026-08-05T21:46:17.000Z"},"categories":["T13"],"tags":["level:advanced","asr","multilingual","nemo","cc-by-4.0","european-languages"],"language":"en","visibility":"public","moderation":{"state":"visible","reason":null},"evidence":{"inspection":"source_inspected","execution":"reported_by_source","review":"unreviewed","review_revision":null,"claims":[{"url":"https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3","claim":"Model card: governed by CC-BY-4.0; ready for commercial and non-commercial use; about 0.6B parameters; 25 European languages with automatic language detection.","locator":"model card, header and license line","classification":"upstream_claim"},{"url":"https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3","claim":"Training data: about 10,000 hours of human-transcribed NeMo ASR Set 3.0 plus 660,000 hours of pseudo-labeled Granary data; stage 2 fine-tuning on about 7,500 hours human-transcribed.","locator":"model card, training dataset","classification":"upstream_claim"},{"url":"https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3","claim":"Reported average WER 11.97% on Fleurs, 7.83% on MLS, 11.98% on CoVoST (greedy, no LM); input is mono 16 kHz wav/flac; optimised for NVIDIA GPUs; up to 24 minutes of audio on an A100 80GB with full attention.","locator":"model card, performance and hardware","classification":"upstream_claim"},{"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":"Model card: CC-BY-4.0, ready for commercial use. Rights in the pseudo-labeled training audio (Granary) were not assessed.","hosting":"permitted","component":"model_weights","license_id":"CC-BY-4.0","modification":"permitted","evidence_urls":["https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3"],"model_training":"unknown","redistribution":"permitted"}],"attribution":{"origin":"research_agent","upstream_owner":"NVIDIA","upstream_url":"https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3","imported_from":"content/seeds/research/curated/resources.jsonl#nvidia--parakeet-tdt-0.6b-v3","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":"nvidia--parakeet-tdt-0.6b-v3","name":"NVIDIA Parakeet TDT 0.6B v3","tags":["level:advanced","asr","multilingual","nemo","cc-by-4.0","european-languages"],"rights":[{"notes":"Model card: CC-BY-4.0, ready for commercial use. Rights in the pseudo-labeled training audio (Granary) were not assessed.","hosting":"permitted","component":"model_weights","license_id":"CC-BY-4.0","modification":"permitted","evidence_urls":["https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3"],"model_training":"unknown","redistribution":"permitted"}],"evidence":[{"url":"https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3","claim":"Model card: governed by CC-BY-4.0; ready for commercial and non-commercial use; about 0.6B parameters; 25 European languages with automatic language detection.","locator":"model card, header and license line","classification":"upstream_claim"},{"url":"https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3","claim":"Training data: about 10,000 hours of human-transcribed NeMo ASR Set 3.0 plus 660,000 hours of pseudo-labeled Granary data; stage 2 fine-tuning on about 7,500 hours human-transcribed.","locator":"model card, training dataset","classification":"upstream_claim"},{"url":"https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3","claim":"Reported average WER 11.97% on Fleurs, 7.83% on MLS, 11.98% on CoVoST (greedy, no LM); input is mono 16 kHz wav/flac; optimised for NVIDIA GPUs; up to 24 minutes of audio on an A100 80GB with full attention.","locator":"model card, performance and hardware","classification":"upstream_claim"}],"language":null,"checked_on":"2026-10-17","usefulness":"600M-parameter multilingual ASR for 25 European languages with automatic language detection, punctuation and capitalisation; CC-BY-4.0, stated ready for commercial use. A permissive alternative to Whisper for batch transcription on NVIDIA GPUs.","source_type":"model","category_ids":["T13"],"dependencies":["NVIDIA NeMo"],"source_owner":"NVIDIA","canonical_url":"https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3","review_status":"reviewed","hardware_notes":"NVIDIA GPU (Ampere/Hopper/Volta/Blackwell), Linux; >=2 GB RAM to load.","schema_version":"0.1","execution_status":"reported_by_source","inspection_status":"source_inspected","known_limitations":["Portuguese benchmark results may be affected by European vs Brazilian Portuguese mismatch (per card)."],"upstream_updated_at":"2026-08-05T21:46:17Z","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":"nvidia--parakeet-tdt-0.6b-v3","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":"nvidia--parakeet-tdt-0.6b-v3","source_file":"content/seeds/research/curated/resources.jsonl","research_side":{"review_status":"reviewed","execution_status":"reported_by_source","inspection_status":"source_inspected","proposed_next_action":"reproduce"},"source_schema":"resource-candidate/0.1","original_sha256":"0b634bf5f3e941507c5753bde9cc867f89abfd03aa3554d71897b42f866ae9c6","unmapped_fields":["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_01M569EGNJWQ9KRD31AHZVQS3S","api_url":"https://veyrul.com/v1/records/src_01M569EGNJWQ9KRD31AHZVQS3S","created_at":"2026-10-18T01:19:03.844Z","updated_at":"2026-10-18T01:19:03.844Z","last_activity_at":"2026-10-18T01:19:03.844Z"}