{"model_id": "openbmb/VoxCPM2", "name": "VoxCPM2", "owner": "openbmb", "source_url": "https://huggingface.co/openbmb/VoxCPM2", "task": "text-to-speech", "languages": ["zh", "en", "ar", "my", "da", "nl", "fi", "fr", "de", "el", "he", "hi", "id", "it", "ja", "km", "ko", "lo", "ms", "no", "pl", "pt", "ru", "es", "sw", "sv", "tl", "th", "tr", "vi"], "tags": ["voxcpm", "safetensors", "text-to-speech", "tts", "multilingual", "voice-cloning", "voice-design", "diffusion", "audio", "zh", "en", "ar", "my", "da", "nl", "fi", "fr", "de", "el", "he", "hi", "id", "it", "ja", "km", "ko", "lo", "ms", "no", "pl", "pt", "ru", "es", "sw", "sv", "tl", "th", "tr", "vi", "arxiv:2509.24650", "license:apache-2.0", "deploy:sagemaker", "region:us"], "license_id": "apache-2.0", "license_status": "ouverte_permissive", "license_label": "Apache License 2.0", "commercial_use": "possible_a_verifier", "gated": false, "private": false, "downloads": 568444, "likes": 1663, "updated_at": "2026-08-18T07:37:17.000Z", "description": "", "files": [{"name": ".gitattributes", "size": 1519, "format": "autre", "precision": "inconnue"}, {"name": "README.md", "size": 7939, "format": "autre", "precision": "inconnue"}, {"name": "audiovae.pth", "size": 376951122, "format": "pth", "precision": "inconnue"}, {"name": "config.json", "size": 4336, "format": "autre", "precision": "inconnue"}, {"name": "model.safetensors", "size": 4580080592, "format": "safetensors", "precision": "inconnue"}, {"name": "special_tokens_map.json", "size": 1632, "format": "autre", "precision": "inconnue"}, {"name": "tokenization_voxcpm2.py", "size": 2895, "format": "autre", "precision": "inconnue"}, {"name": "tokenizer.json", "size": 3676772, "format": "autre", "precision": "inconnue"}, {"name": "tokenizer_config.json", "size": 5059, "format": "autre", "precision": "inconnue"}], "parameter_count": 2290004544, "library_name": "voxcpm", "pipeline_tag": "text-to-speech", "datasets": [], "metrics": [], "github_url": "", "github_metadata": {}, "paper_url": "https://arxiv.org/abs/2509.24650", "paper_doi": "", "paper_metadata": {}, "card_complete": true, "safetensors": true, "provenance": [{"source": "Hugging Face Hub API", "url": "https://huggingface.co/openbmb/VoxCPM2", "retrieved_at": "2026-10-08T14:28:54.849910+00:00"}], "retrieved_at": "2026-10-08T14:28:54.849910+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 : 5.5 Go, marge d’exécution de 30% incluse.", "Espace disque minimal indicatif : 4.3 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": 4580080592, "estimated_bytes": 5954104769, "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": []}