{"model_id": "microsoft/VibeVoice-ASR", "name": "VibeVoice-ASR", "owner": "microsoft", "source_url": "https://huggingface.co/microsoft/VibeVoice-ASR", "task": "automatic-speech-recognition", "languages": ["en", "zh", "es", "pt", "de", "ja", "ko", "fr", "ru", "id", "sv", "it", "he", "nl", "pl", "no", "tr", "th", "ar", "hu", "ca", "cs", "da", "fa", "af", "hi", "fi", "et", "aa", "el"], "tags": ["transformers", "safetensors", "vibevoice", "ASR", "Transcriptoin", "Diarization", "Speech-to-Text", "automatic-speech-recognition", "en", "zh", "es", "pt", "de", "ja", "ko", "fr", "ru", "id", "sv", "it", "he", "nl", "pl", "no", "tr", "th", "ar", "hu", "ca", "cs", "da", "fa", "af", "hi", "fi", "et", "aa", "el", "ro", "vi", "bg", "is", "sl", "sk", "lt", "sw", "uk", "kl", "lv", "hr", "ne", "sr", "tl", "yi", "ms", "ur", "mn", "hy", "jv", "arxiv:2601.18184", "license:mit", "endpoints_compatible", "region:us"], "license_id": "mit", "license_status": "ouverte_permissive", "license_label": "MIT License", "commercial_use": "possible_a_verifier", "gated": false, "private": false, "downloads": 722738, "likes": 1303, "updated_at": "2026-01-27T13:12:22.000Z", "description": "", "files": [{"name": ".gitattributes", "size": 199, "format": "autre", "precision": "inconnue"}, {"name": "README.md", "size": 4345, "format": "autre", "precision": "inconnue"}, {"name": "config.json", "size": 3520, "format": "autre", "precision": "inconnue"}, {"name": "figures/DER.jpg", "size": 62653, "format": "autre", "precision": "inconnue"}, {"name": "figures/VibeVoice_ASR_archi.png", "size": 149474, "format": "autre", "precision": "inconnue"}, {"name": "figures/cpWER.jpg", "size": 68492, "format": "autre", "precision": "inconnue"}, {"name": "figures/language_distribution_horizontal.png", "size": 888409, "format": "autre", "precision": "inconnue"}, {"name": "figures/tcpWER.jpg", "size": 64251, "format": "autre", "precision": "inconnue"}, {"name": "model-00001-of-00008.safetensors", "size": 2488346272, "format": "safetensors", "precision": "inconnue"}, {"name": "model-00002-of-00008.safetensors", "size": 2389315976, "format": "safetensors", "precision": "inconnue"}, {"name": "model-00003-of-00008.safetensors", "size": 2466376368, "format": "safetensors", "precision": "inconnue"}, {"name": "model-00004-of-00008.safetensors", "size": 2466376400, "format": "safetensors", "precision": "inconnue"}, {"name": "model-00005-of-00008.safetensors", "size": 2499431136, "format": "safetensors", "precision": "inconnue"}, {"name": "model-00006-of-00008.safetensors", "size": 2483469928, "format": "safetensors", "precision": "inconnue"}, {"name": "model-00007-of-00008.safetensors", "size": 1464887482, "format": "safetensors", "precision": "inconnue"}, {"name": "model-00008-of-00008.safetensors", "size": 1089994848, "format": "safetensors", "precision": "inconnue"}, {"name": "model.safetensors.index.json", "size": 120151, "format": "autre", "precision": "inconnue"}], "parameter_count": 8674021857, "library_name": "transformers", "pipeline_tag": "automatic-speech-recognition", "datasets": [], "metrics": [], "github_url": "", "github_metadata": {}, "paper_url": "https://arxiv.org/abs/2601.18184", "paper_doi": "", "paper_metadata": {}, "card_complete": true, "safetensors": true, "provenance": [{"source": "Hugging Face Hub API", "url": "https://huggingface.co/microsoft/VibeVoice-ASR", "retrieved_at": "2026-10-08T12:28:13.776427+00:00"}], "retrieved_at": "2026-10-08T12:28:13.776427+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": "insuffisante", "label": "Mémoire probablement insuffisante", "summary": "La mémoire indiquée est inférieure au besoin estimé.", "factors": ["Mémoire estimée : 21.0 Go, marge d’exécution de 30% incluse.", "Espace disque minimal indicatif : 16.2 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": 17348198410, "estimated_bytes": 22552657933, "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": []}