{"model_id": "Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice", "name": "Qwen3-TTS-12Hz-0.6B-CustomVoice", "owner": "Qwen", "source_url": "https://huggingface.co/Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice", "task": "text-to-speech", "languages": ["zh", "en", "ja", "ko", "de", "fr", "ru", "pt", "es", "it"], "tags": ["safetensors", "qwen3_tts", "tts", "qwen", "audio", "text-to-speech", "zh", "en", "ja", "ko", "de", "fr", "ru", "pt", "es", "it", "arxiv:2601.15621", "license:apache-2.0", "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": 1041682, "likes": 195, "updated_at": "2026-01-29T08:01:51.000Z", "description": "", "files": [{"name": ".gitattributes", "size": 1519, "format": "autre", "precision": "inconnue"}, {"name": "README.md", "size": 3263, "format": "autre", "precision": "inconnue"}, {"name": "config.json", "size": 4908, "format": "autre", "precision": "inconnue"}, {"name": "generation_config.json", "size": 245, "format": "autre", "precision": "inconnue"}, {"name": "merges.txt", "size": 1671839, "format": "autre", "precision": "inconnue"}, {"name": "model.safetensors", "size": 1811626576, "format": "safetensors", "precision": "inconnue"}, {"name": "preprocessor_config.json", "size": 127, "format": "autre", "precision": "inconnue"}, {"name": "speech_tokenizer/config.json", "size": 2336, "format": "autre", "precision": "inconnue"}, {"name": "speech_tokenizer/configuration.json", "size": 76, "format": "autre", "precision": "inconnue"}, {"name": "speech_tokenizer/model.safetensors", "size": 682293092, "format": "safetensors", "precision": "inconnue"}, {"name": "speech_tokenizer/preprocessor_config.json", "size": 234, "format": "autre", "precision": "inconnue"}, {"name": "tokenizer_config.json", "size": 7344, "format": "autre", "precision": "inconnue"}, {"name": "vocab.json", "size": 2776833, "format": "autre", "precision": "inconnue"}], "parameter_count": 905788672, "library_name": "", "pipeline_tag": "text-to-speech", "datasets": [], "metrics": [], "github_url": "", "github_metadata": {}, "paper_url": "https://arxiv.org/abs/2601.15621", "paper_doi": "", "paper_metadata": {}, "card_complete": true, "safetensors": true, "provenance": [{"source": "Hugging Face Hub API", "url": "https://huggingface.co/Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice", "retrieved_at": "2026-10-08T02:41:45.664142+00:00"}], "retrieved_at": "2026-10-08T02:41:45.664142+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 : 3.0 Go, marge d’exécution de 30% incluse.", "Espace disque minimal indicatif : 2.3 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": 2493919668, "estimated_bytes": 3242095568, "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": []}