{"model_id": "nvidia/canary-1b-v2", "name": "canary-1b-v2", "owner": "nvidia", "source_url": "https://huggingface.co/nvidia/canary-1b-v2", "task": "automatic-speech-recognition", "languages": ["bg", "hr", "cs", "da", "nl", "en", "et", "fi", "fr", "de", "el", "hu", "it", "lv", "lt", "mt", "pl", "pt", "ro", "sk", "sl", "es", "sv", "ru", "uk"], "tags": ["nemo", "safetensors", "canary", "automatic-speech-recognition", "automatic-speech-translation", "speech", "audio", "Transformer", "FastConformer", "Conformer", "pytorch", "NeMo", "hf-asr-leaderboard", "Transformers", "bg", "hr", "cs", "da", "nl", "en", "et", "fi", "fr", "de", "el", "hu", "it", "lv", "lt", "mt", "pl", "pt", "ro", "sk", "sl", "es", "sv", "ru", "uk", "dataset:nvidia/Granary", "dataset:nvidia/nemo-asr-set-3.0", "arxiv:2509.14128", "arxiv:2505.13404", "arxiv:2305.05084", "arxiv:1706.03762", "arxiv:2410.01036", "arxiv:2406.00899", "arxiv:2205.12446", "arxiv:2012.03411", "arxiv:2007.10310", "arxiv:2005.08072", "arxiv:1510.08484", "license:cc-by-4.0", "model-index", "eval-results", "deploy:azure", "region:us"], "license_id": "cc-by-4.0", "license_status": "ouverte_avec_conditions", "license_label": "Creative Commons BY 4.0", "commercial_use": "possible_a_verifier", "gated": false, "private": false, "downloads": 106996, "likes": 431, "updated_at": "2026-08-31T19:01:49.000Z", "description": "", "files": [{"name": ".gitattributes", "size": 1615, "format": "autre", "precision": "inconnue"}, {"name": "README.md", "size": 72381, "format": "autre", "precision": "inconnue"}, {"name": "canary-1b-v2.nemo", "size": 6358958080, "format": "autre", "precision": "inconnue"}, {"name": "chat_template.jinja", "size": 534, "format": "autre", "precision": "inconnue"}, {"name": "config.json", "size": 1591, "format": "autre", "precision": "inconnue"}, {"name": "generation_config.json", "size": 252, "format": "autre", "precision": "inconnue"}, {"name": "model.safetensors", "size": 3916173816, "format": "safetensors", "precision": "inconnue"}, {"name": "plots/asr.png", "size": 146866, "format": "autre", "precision": "inconnue"}, {"name": "plots/en_x.png", "size": 128921, "format": "autre", "precision": "inconnue"}, {"name": "plots/x_en.png", "size": 125547, "format": "autre", "precision": "inconnue"}, {"name": "processor_config.json", "size": 362, "format": "autre", "precision": "inconnue"}, {"name": "tokenizer.json", "size": 2189980, "format": "autre", "precision": "inconnue"}, {"name": "tokenizer_config.json", "size": 328, "format": "autre", "precision": "inconnue"}], "parameter_count": 978998272, "library_name": "nemo", "pipeline_tag": "automatic-speech-recognition", "datasets": ["nvidia/Granary", "nvidia/nemo-asr-set-3.0"], "metrics": [{"name": "Test WER (Bg)", "value": 9.25, "task": "automatic-speech-recognition", "dataset": "FLEURS"}, {"name": "Test WER (Cs)", "value": 7.86, "task": "automatic-speech-recognition", "dataset": "FLEURS"}, {"name": "Test WER (Da)", "value": 11.25, "task": "automatic-speech-recognition", "dataset": "FLEURS"}, {"name": "Test WER (De)", "value": 4.4, "task": "automatic-speech-recognition", "dataset": "FLEURS"}, {"name": "Test WER (El)", "value": 9.21, "task": "automatic-speech-recognition", "dataset": "FLEURS"}, {"name": "Test WER (En)", "value": 4.5, "task": "automatic-speech-recognition", "dataset": "FLEURS"}, {"name": "Test WER (Es)", "value": 2.9, "task": "automatic-speech-recognition", "dataset": "FLEURS"}, {"name": "Test WER (Et)", "value": 12.55, "task": "automatic-speech-recognition", "dataset": "FLEURS"}, {"name": "Test WER (Fi)", "value": 8.59, "task": "automatic-speech-recognition", "dataset": "FLEURS"}, {"name": "Test WER (Fr)", "value": 5.02, "task": "automatic-speech-recognition", "dataset": "FLEURS"}, {"name": "Test WER (Hr)", "value": 8.29, "task": "automatic-speech-recognition", "dataset": "FLEURS"}, {"name": "Test WER (Hu)", "value": 12.9, "task": "automatic-speech-recognition", "dataset": "FLEURS"}, {"name": "Test WER (It)", "value": 3.07, "task": "automatic-speech-recognition", "dataset": "FLEURS"}, {"name": "Test WER (Lt)", "value": 12.36, "task": "automatic-speech-recognition", "dataset": "FLEURS"}, {"name": "Test WER (Lv)", "value": 9.66, "task": "automatic-speech-recognition", "dataset": "FLEURS"}, {"name": "Test WER (Mt)", "value": 18.31, "task": "automatic-speech-recognition", "dataset": "FLEURS"}, {"name": "Test WER (Nl)", "value": 6.12, "task": "automatic-speech-recognition", "dataset": "FLEURS"}, {"name": "Test WER (Pl)", "value": 6.64, "task": "automatic-speech-recognition", "dataset": "FLEURS"}, {"name": "Test WER (Pt)", "value": 4.39, "task": "automatic-speech-recognition", "dataset": "FLEURS"}, {"name": "Test WER (Ro)", "value": 6.61, "task": "automatic-speech-recognition", "dataset": "FLEURS"}], "github_url": "", "github_metadata": {}, "paper_url": "https://arxiv.org/abs/2509.14128", "paper_doi": "", "paper_metadata": {}, "card_complete": true, "safetensors": true, "provenance": [{"source": "Hugging Face Hub API", "url": "https://huggingface.co/nvidia/canary-1b-v2", "retrieved_at": "2026-10-08T22:30:04.527311+00:00"}], "retrieved_at": "2026-10-08T22:30:04.527311+00:00", "warnings": ["La licence est déclarée par le producteur ; vérifiez toujours son texte intégral et les conditions associées."], "rank_score": 0.0, "rank_reasons": [], "compatibility": {"state": "compatible", "label": "Compatible selon l’estimation", "summary": "La mémoire indiquée dépasse l’estimation prudente.", "factors": ["Mémoire estimée : 4.7 Go, marge d’exécution de 30% incluse.", "Espace disque minimal indicatif : 3.6 Go.", "Une exécution CPU peut être possible mais sa vitesse ne peut pas être déduite de ces métadonnées."], "estimate": {"known": true, "precision": "float32", "source": "taille réelle déclarée des fichiers de poids", "base_bytes": 3916173816, "estimated_bytes": 5091025960, "overhead": 0.3}}, "quantization": {"available": false, "variants": [], "recommended": null, "lightest": null, "memory_gb": 0.0, "disk_gb": 0.0}, "editorial_quality_score": null, "editorial_quality_blockers": []}