{"slug":"nvidia-canary","name":"NVIDIA Canary","domain":"nvidia.com","best_rank":7,"categories":1,"entries":[{"slug":"best-open-source-speech-to-text-model","title":"Best open-source speech-to-text model","rank":7,"of":11,"score":3,"appearances":1,"modelRanks":{"Gemini":3},"reason":"Delivers state-of-the-art accuracy for English and 25 European languages using FastConformer architecture, often outperforming Whisper on word error rate (WER) and speech translation.","reasons":[{"model":"Gemini","reason":"Delivers state-of-the-art accuracy for English and 25 European languages using FastConformer architecture, often outperforming Whisper on word error rate (WER) and speech translation."}],"fixes":[{"model":"Gemini","fix":"Deeply tied to NVIDIA's heavy NeMo framework, making CPU-only or lightweight edge deployment highly impractical."}],"updated":"2026-07-15","api":"https://modelsagree.com/api/v1/best/best-open-source-speech-to-text-model.json"}],"page":"https://modelsagree.com/product/nvidia-canary","check":"https://modelsagree.com/check?q=NVIDIA%20Canary","updated":"2026-07-16T03:47:53.793Z","attribution":"modelsagree.com, CC BY 4.0"}