{"model_id": "microsoft/VibeVoice-ASR-BitNet", "name": "VibeVoice-ASR-BitNet", "owner": "microsoft", "source_url": "https://huggingface.co/microsoft/VibeVoice-ASR-BitNet", "task": "automatic-speech-recognition", "languages": ["en", "zh", "fr", "it", "ko", "pt", "vi"], "tags": ["ggml", "safetensors", "gguf", "vibevoice", "ASR", "quantization", "cpu-inference", "bitnet", "multilingual", "automatic-speech-recognition", "en", "zh", "fr", "it", "ko", "pt", "vi", "arxiv:2607.21075", "license:mit", "endpoints_compatible", "region:us", "conversational"], "license_id": "mit", "license_status": "ouverte_permissive", "license_label": "MIT License", "commercial_use": "possible_a_verifier", "gated": false, "private": false, "downloads": 69210, "likes": 204, "updated_at": "2026-07-24T06:03:32.000Z", "description": "", "files": [{"name": ".gitattributes", "size": 306, "format": "autre", "precision": "inconnue"}, {"name": "README.md", "size": 4124, "format": "autre", "precision": "inconnue"}, {"name": "config.json", "size": 3527, "format": "autre", "precision": "inconnue"}, {"name": "figures/report_overview.png", "size": 223086, "format": "autre", "precision": "inconnue"}, {"name": "generation_config.json", "size": 138, "format": "autre", "precision": "inconnue"}, {"name": "model-00001-of-00003.safetensors", "size": 4996674400, "format": "safetensors", "precision": "inconnue"}, {"name": "model-00002-of-00003.safetensors", "size": 4963184724, "format": "safetensors", "precision": "inconnue"}, {"name": "model-00003-of-00003.safetensors", "size": 1296761656, "format": "safetensors", "precision": "inconnue"}, {"name": "model.safetensors.index.json", "size": 120151, "format": "autre", "precision": "inconnue"}, {"name": "tokenizer.json", "size": 7028015, "format": "autre", "precision": "inconnue"}, {"name": "tokenizer_config.json", "size": 1289, "format": "autre", "precision": "inconnue"}, {"name": "vibeasr-lm-i2_s-embed-q6_k.gguf", "size": 992877600, "format": "gguf", "precision": "inconnue"}, {"name": "vibeasr-vae-encoder-i8_s.gguf", "size": 703080064, "format": "gguf", "precision": "inconnue"}, {"name": "vocab.json", "size": 2776833, "format": "autre", "precision": "inconnue"}], "parameter_count": 322592829, "library_name": "ggml", "pipeline_tag": "automatic-speech-recognition", "datasets": [], "metrics": [], "github_url": "", "github_metadata": {}, "paper_url": "https://arxiv.org/abs/2607.21075", "paper_doi": "", "paper_metadata": {}, "card_complete": true, "safetensors": true, "provenance": [{"source": "Hugging Face Hub API", "url": "https://huggingface.co/microsoft/VibeVoice-ASR-BitNet", "retrieved_at": "2026-10-08T13:00:09.899627+00:00"}], "retrieved_at": "2026-10-08T13:00:09.899627+00:00", "warnings": ["La licence est déclarée par le producteur ; vérifiez toujours son texte intégral et les conditions associées.", "Plusieurs variantes GGUF sont publiées : l’estimation retient la plus petite taille connue, pas leur somme."], "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 : 13.6 Go, marge d’exécution de 30% incluse.", "Espace disque minimal indicatif : 10.5 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": 11256620780, "estimated_bytes": 14633607014, "overhead": 0.3}}, "quantization": {"available": true, "variants": [{"label": "variante", "filename": "vibeasr-vae-encoder-i8_s.gguf", "size": 703080064, "size_human": "671 Mo", "memory_bytes": 914004083, "memory_human": "872 Mo", "note": "", "rank": 34, "memory_gb": 0.9, "state": "tient", "verdict": "Tient dans la mémoire déclarée"}, {"label": "Q6_K", "filename": "vibeasr-lm-i2_s-embed-q6_k.gguf", "size": 992877600, "size_human": "947 Mo", "memory_bytes": 1290740880, "memory_human": "1.2 Go", "note": "Très proche du modèle non quantifié.", "rank": 28, "memory_gb": 1.2, "state": "tient", "verdict": "Tient dans la mémoire déclarée"}], "recommended": {"label": "variante", "filename": "vibeasr-vae-encoder-i8_s.gguf", "size": 703080064, "size_human": "671 Mo", "memory_bytes": 914004083, "memory_human": "872 Mo", "note": "", "rank": 34, "memory_gb": 0.9, "state": "tient", "verdict": "Tient dans la mémoire déclarée"}, "lightest": {"label": "variante", "filename": "vibeasr-vae-encoder-i8_s.gguf", "size": 703080064, "size_human": "671 Mo", "memory_bytes": 914004083, "memory_human": "872 Mo", "note": "", "rank": 34, "memory_gb": 0.9, "state": "tient", "verdict": "Tient dans la mémoire déclarée"}, "memory_gb": 8.0, "disk_gb": 20.0, "fitting_count": 2, "overhead": 0.3, "note": "Tailles issues des fichiers déclarés par le producteur, majorées de 30% pour l’exécution. Une variante plus compressée consomme moins de mémoire et dégrade les réponses : cette dégradation n’est pas mesurée ici."}, "editorial_quality_score": null, "editorial_quality_blockers": []}