SoundGame Dev
f0f0a9b50e
- 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
117 lines
3.8 KiB
Python
117 lines
3.8 KiB
Python
from dataclasses import dataclass
|
|
|
|
from huggingface_hub import hf_hub_download, try_to_load_from_cache
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class ModelConfig:
|
|
repo_id: str
|
|
config_path: str
|
|
ckpt_path: str
|
|
|
|
def resolve(self):
|
|
"""Download files from HuggingFace Hub and return local cached paths."""
|
|
local_config = hf_hub_download(repo_id=self.repo_id, filename=self.config_path)
|
|
local_ckpt = hf_hub_download(repo_id=self.repo_id, filename=self.ckpt_path)
|
|
return local_config, local_ckpt
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class AutoencoderModelConfig:
|
|
"""Config for a standalone autoencoder HF repo (e.g. stabilityai/SAME-S).
|
|
|
|
resolve() first checks whether any full Stable Audio 3 checkpoint that contains the same
|
|
autoencoder is already cached locally. If one is found it is used as-is
|
|
(load_autoencoder strips the pretransform.* prefix automatically), avoiding a
|
|
redundant download. Otherwise the lightweight AE-only repo is fetched instead.
|
|
"""
|
|
|
|
ae_repo_id: str
|
|
ae_config_path: str
|
|
ae_ckpt_path: str
|
|
stable_audio_3: tuple[ModelConfig, ...]
|
|
|
|
def resolve(self):
|
|
"""Return (config_path, ckpt_path), preferring an already-cached Stable Audio 3 checkpoint."""
|
|
for fallback in self.stable_audio_3:
|
|
cached_config = try_to_load_from_cache(
|
|
fallback.repo_id, fallback.config_path
|
|
)
|
|
cached_ckpt = try_to_load_from_cache(fallback.repo_id, fallback.ckpt_path)
|
|
if isinstance(cached_config, str) and isinstance(cached_ckpt, str):
|
|
return cached_config, cached_ckpt
|
|
|
|
# No Stable Audio 3 checkpoint found in local cache — download the AE-only repo.
|
|
local_config = hf_hub_download(
|
|
repo_id=self.ae_repo_id, filename=self.ae_config_path
|
|
)
|
|
local_ckpt = hf_hub_download(
|
|
repo_id=self.ae_repo_id, filename=self.ae_ckpt_path
|
|
)
|
|
return local_config, local_ckpt
|
|
|
|
|
|
models: dict[str, ModelConfig] = {
|
|
"small-music": ModelConfig(
|
|
"stabilityai/stable-audio-3-small-music",
|
|
"model_config.json",
|
|
"model.safetensors",
|
|
),
|
|
"small-music-base": ModelConfig(
|
|
"stabilityai/stable-audio-3-small-music-base",
|
|
"model_config.json",
|
|
"model.safetensors",
|
|
),
|
|
"small-sfx": ModelConfig(
|
|
"stabilityai/stable-audio-3-small-sfx",
|
|
"model_config.json",
|
|
"model.safetensors",
|
|
),
|
|
"small-sfx-base": ModelConfig(
|
|
"stabilityai/stable-audio-3-small-sfx-base",
|
|
"model_config.json",
|
|
"model.safetensors",
|
|
),
|
|
"medium": ModelConfig(
|
|
"stabilityai/stable-audio-3-medium",
|
|
"model_config.json",
|
|
"model.safetensors",
|
|
),
|
|
"medium-base": ModelConfig(
|
|
"stabilityai/stable-audio-3-medium-base",
|
|
"model_config.json",
|
|
"model.safetensors",
|
|
),
|
|
}
|
|
|
|
# Stable Audio 3 full-model configs to probe (in order) before downloading the AE-only repo.
|
|
_small_stable_audio_3: tuple[ModelConfig, ...] = (
|
|
models["small-music"],
|
|
models["small-sfx"],
|
|
)
|
|
_medium_stable_audio_3: tuple[ModelConfig, ...] = (models["medium"],)
|
|
|
|
ae_models: dict[str, AutoencoderModelConfig] = {
|
|
"same-s": AutoencoderModelConfig(
|
|
ae_repo_id="stabilityai/SAME-S",
|
|
ae_config_path="model_config.json",
|
|
ae_ckpt_path="model.safetensors",
|
|
stable_audio_3=_small_stable_audio_3,
|
|
),
|
|
"same-l": AutoencoderModelConfig(
|
|
ae_repo_id="stabilityai/SAME-L",
|
|
ae_config_path="model_config.json",
|
|
ae_ckpt_path="model.safetensors",
|
|
stable_audio_3=_medium_stable_audio_3,
|
|
),
|
|
}
|
|
|
|
base_models: dict[str, ModelConfig] = {
|
|
k: v for k, v in models.items() if k.endswith("-base")
|
|
}
|
|
|
|
all_models: dict[str, ModelConfig | AutoencoderModelConfig] = {
|
|
**models,
|
|
**ae_models,
|
|
}
|