{"schema":"postcutoff/model@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/m/nvidia-parakeet-canary/","md":"https://postcutoff.com/m/nvidia-parakeet-canary/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"nvidia-parakeet-canary","name":"NVIDIA Parakeet / Canary / Nemotron Speech ASR (open)","org":"NVIDIA","family":"NeMo ASR","released":"2025-08-14","status":"current","type":"audio/speech","modality_in":["audio"],"modality_out":["text"],"open_weights":true,"model_license":"cc-by-4.0 (Parakeet TDT v3, Canary-Qwen); NVIDIA Open Model License / OpenMDW (2026 models)","context_window":null,"max_output":null,"knowledge_cutoff":null,"pricing":null,"price_line":"Price not published","access":[{"provider":"Hugging Face","model_id":"nvidia/parakeet-tdt-0.6b-v3","url":"https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3"},{"provider":"Hugging Face","model_id":"nvidia/canary-qwen-2.5b","url":"https://huggingface.co/nvidia/canary-qwen-2.5b"},{"provider":"Hugging Face","model_id":"nvidia/parakeet-unified-en-0.6b","url":"https://huggingface.co/nvidia/parakeet-unified-en-0.6b"},{"provider":"Hugging Face","model_id":"nvidia/nemotron-speech-streaming-en-0.6b","url":"https://huggingface.co/nvidia/nemotron-speech-streaming-en-0.6b"},{"provider":"Hugging Face","model_id":"nvidia/nemotron-3.5-asr-streaming-0.6b","url":"https://huggingface.co/nvidia/nemotron-3.5-asr-streaming-0.6b"},{"provider":"NVIDIA NIM / build.nvidia.com","url":"https://build.nvidia.com"}],"capabilities":[{"name":"Parakeet TDT 0.6B v3: 25 European languages, very high throughput","detail":"600M FastConformer-TDT with auto language ID, punctuation, word timestamps, up to 24 min (3 h with local attention); 6.34% avg WER on Open ASR Leaderboard; trained on the Granary dataset.","first":false,"discovered":"launch","source":"https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3"},{"name":"Canary-Qwen-2.5B speech-augmented LLM","detail":"FastConformer encoder + Qwen LLM (SALM); 5.63% mean WER topped the HF Open ASR Leaderboard at release (2025-07-17); can summarize/answer questions about the transcript. English, max 40 s clips.","first":false,"discovered":"launch","source":"https://huggingface.co/nvidia/canary-qwen-2.5b"},{"name":"Cache-aware streaming ASR, 80-1120 ms chunks","detail":"Nemotron Speech Streaming EN 0.6B (Jan/Mar 2026) and Nemotron 3.5 ASR Streaming 0.6B (June 2026, 40 language-locales) switch latency at inference without retraining; Parakeet-unified-en-0.6B (2026-04-07) does both offline (5.91% WER) and streaming down to 160 ms.","first":false,"discovered":"later","source":"https://huggingface.co/nvidia/nemotron-3.5-asr-streaming-0.6b"}],"entry":null,"notes":"One file for NVIDIA's open ASR family. Also canary-1b-v2 (European ASR + translation) and parakeet-tdt-0.6b-v2 (English, NIM). Nemotron 3.5 ASR HF card shows a garbled date; June 2026 per NVIDIA/press. NVIDIA's open TTS: magpie_tts_multilingual_357m. Full-duplex model: see nemotron-voicechat.","verified":"2026-09-29","body_md":"Sources: https://huggingface.co/collections/nvidia/nemotron-speech , https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3 , https://huggingface.co/nvidia/canary-qwen-2.5b","page_url":"https://postcutoff.com/m/nvidia-parakeet-canary/","standing":{"kind":"speech and audio","newer_count":90,"newer":[{"id":"nemotron-3-5-transcribe","name":"NVIDIA Nemotron 3.5 Transcribe (30B-A4B)","org":"NVIDIA","released":"2026-10-28","page_url":"https://postcutoff.com/m/nemotron-3-5-transcribe/"},{"id":"hy-simulmt-30b-a3b","name":"Hy-SimulMT-30B-A3B","org":"Tencent","released":"2026-10-22","page_url":"https://postcutoff.com/m/hy-simulmt-30b-a3b/"},{"id":"eleven-realtime-v1-max","name":"Eleven Realtime v1 Max / Mini","org":"ElevenLabs","released":"2026-10-20","page_url":"https://postcutoff.com/m/eleven-realtime-v1-max/"},{"id":"voxtral-mini-transcribe-3","name":"Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3)","org":"Mistral AI","released":"2026-10-20","page_url":"https://postcutoff.com/m/voxtral-mini-transcribe-3/"},{"id":"voxtral-small-transcribe-3","name":"Voxtral Small Transcribe 3","org":"Mistral AI","released":"2026-10-20","page_url":"https://postcutoff.com/m/voxtral-small-transcribe-3/"}],"before":null,"after":{"id":"nvidia-magpie-tts-multilingual","name":"NVIDIA MagpieTTS Multilingual 357M","org":"NVIDIA","released":"2025-12-11","page_url":"https://postcutoff.com/m/nvidia-magpie-tts-multilingual/"},"weights":"public","licence":"cc-by-4.0 (Parakeet TDT v3, Canary-Qwen); NVIDIA Open Model License / OpenMDW (2026 models)","licence_permissive":false,"summary":"Weights are public. Licence: cc-by-4.0; NVIDIA Open Model License / OpenMDW. See the licence for commercial terms."}}