初始提交：3 款纯音频游戏 + 共享引擎 + 完整文档与资产管线

- 共享引擎（app/src/main）：GestureEngine 6 手势识别、AudioEngine 三层音频（ExoPlayer BGM 交叉淡入 / 对白 ducking / SoundPool 低延迟）、Game/GameEngine 状态机接口、MainActivity 全屏封面 + TalkBack - 《声命线》storyline：末世互动广播剧，3 幕 8 抉择点 4 结局 - 《声东击西》reflex：听声辨位反应，12 波战斗 + BGM 三档 BPM 变速 - 《暗室》escape：3x3 网格密室逃脱，钥匙→铁柜→保险丝→电箱→大门谜题链 - 文档：setup（从零搭建）/ architecture（架构）/ engine-api（引擎 API）/ asset-pipeline（资产流水线）/ games/*（三款游戏设计文档） - 资产管线：Qwen3-TTS 对白 + 程序合成音效/BGM + Mureka BGM 的 gen 脚本与台账，全部 ogg 资产入库可复现 - env.d 环境脚本：android/tts 入库；sfx/mureka 含密钥不入库，仅提交 .example.sh 模板
2026-08-29 13:00:34 +08:00
commit f0f0a9b50e
446 changed files with 2627836 additions and 0 deletions
@@ -0,0 +1,90 @@
+import torch
+from stable_audio_3.interface.diffusion_cond import create_diffusion_cond_ui
+from stable_audio_3 import StableAudioModel
+from stable_audio_3.verbose import set_verbose
+import sys
+
+# Silence Python warnings (FutureWarning, DeprecationWarning, etc.) unless --verbose.
+# Must run before any ML library imports since most warnings fire at import time.
+# We keep Gradio chatter, HF/torch progress bars, and generation tqdm intact.
+if "--verbose" not in sys.argv:
+    import os as _os
+
+    _os.environ.setdefault("PYTHONWARNINGS", "ignore")
+    import warnings as _warnings
+
+    _warnings.filterwarnings("ignore")
+
+
+def main(args):
+    set_verbose(getattr(args, "verbose", False))
+    torch.manual_seed(42)
+    model_half = args.model_half
+    model = StableAudioModel.from_pretrained(args.model, model_half=model_half)
+    if args.lora_ckpt_path:
+        model.load_lora(args.lora_ckpt_path)
+    interface = create_diffusion_cond_ui(
+        model,
+        gradio_title=args.title if args.title is not None else "Stable Audio 3",
+        default_prompt=args.default_prompt,
+    )
+    interface.queue()
+    interface.launch(
+        share=True,
+        js=getattr(interface, "_sao_js", None),
+        theme=getattr(interface, "_sao_theme", None),
+    )
+
+
+if __name__ == "__main__":
+    import argparse
+
+    parser = argparse.ArgumentParser(description="Run gradio interface")
+    parser.add_argument(
+        "--model", type=str, help="Name of pretrained model", required=True
+    )
+    parser.add_argument(
+        "--model-config", type=str, help="Path to model config", required=False
+    )
+    parser.add_argument(
+        "--ckpt-path", type=str, help="Path to model checkpoint", required=False
+    )
+    parser.add_argument(
+        "--pretransform-ckpt-path",
+        type=str,
+        help="Optional to model pretransform checkpoint",
+        required=False,
+    )
+    parser.add_argument("--username", type=str, help="Gradio username", required=False)
+    parser.add_argument("--password", type=str, help="Gradio password", required=False)
+    parser.add_argument(
+        "--model-half",
+        action="store_true",
+        help="Whether to use half precision",
+        required=False,
+        default=True,
+    )
+    parser.add_argument(
+        "--title", type=str, help="Display Title top of Gradio", required=False
+    )
+    parser.add_argument(
+        "--lora-ckpt-path",
+        type=str,
+        nargs="*",
+        help="Path(s) for LoRA(s) to apply. Can specify multiple.",
+        required=False,
+    )
+    parser.add_argument(
+        "--default-prompt",
+        type=str,
+        default=None,
+        help="Default prompt to pre-fill in the textbox",
+    )
+    parser.add_argument(
+        "--verbose",
+        action="store_true",
+        default=False,
+        help="Print detailed load/generation progress",
+    )
+    args = parser.parse_args()
+    main(args)