{"model_id": "vibevoice/VibeVoice-1.5B-hf", "name": "VibeVoice-1.5B-hf", "owner": "vibevoice", "source_url": "https://huggingface.co/vibevoice/VibeVoice-1.5B-hf", "task": "text-to-speech", "languages": ["en", "zh"], "tags": ["transformers", "safetensors", "vibevoice", "text-to-audio", "Podcast", "text-to-speech", "en", "zh", "arxiv:2508.19205", "arxiv:2412.08635", "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": 41737, "likes": 4, "updated_at": "2026-09-16T12:25:39.000Z", "description": "", "files": [{"name": ".gitattributes", "size": 1623, "format": "autre", "precision": "inconnue"}, {"name": "README.md", "size": 21897, "format": "autre", "precision": "inconnue"}, {"name": "chat_template.jinja", "size": 2420, "format": "autre", "precision": "inconnue"}, {"name": "config.json", "size": 3201, "format": "autre", "precision": "inconnue"}, {"name": "figures/Fig1.png", "size": 153971, "format": "autre", "precision": "inconnue"}, {"name": "generation_config.json", "size": 487, "format": "autre", "precision": "inconnue"}, {"name": "model-00001-of-00003.safetensors", "size": 1973742446, "format": "safetensors", "precision": "inconnue"}, {"name": "model-00002-of-00003.safetensors", "size": 1993066216, "format": "safetensors", "precision": "inconnue"}, {"name": "model-00003-of-00003.safetensors", "size": 1441395288, "format": "safetensors", "precision": "inconnue"}, {"name": "model.safetensors.index.json", "size": 124129, "format": "autre", "precision": "inconnue"}, {"name": "processor_config.json", "size": 511, "format": "autre", "precision": "inconnue"}, {"name": "tokenizer.json", "size": 11421892, "format": "autre", "precision": "inconnue"}, {"name": "tokenizer_config.json", "size": 811, "format": "autre", "precision": "inconnue"}], "parameter_count": 2704021985, "library_name": "transformers", "pipeline_tag": "text-to-speech", "datasets": [], "metrics": [], "github_url": "", "github_metadata": {}, "paper_url": "https://arxiv.org/abs/2508.19205", "paper_doi": "", "paper_metadata": {}, "card_complete": true, "safetensors": true, "provenance": [{"source": "Hugging Face Hub API", "url": "https://huggingface.co/vibevoice/VibeVoice-1.5B-hf", "retrieved_at": "2026-10-10T11:26:55.682561+00:00"}], "retrieved_at": "2026-10-10T11:26:55.682561+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 : 6.5 Go, marge d’exécution de 30% incluse.", "Espace disque minimal indicatif : 5.0 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": 5408203950, "estimated_bytes": 7030665135, "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": []}