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
51 lines
1.7 KiB
Python
51 lines
1.7 KiB
Python
import math
|
|
|
|
import torch
|
|
|
|
AMPLITUDE = 0.8
|
|
|
|
|
|
def sine_wave(
|
|
duration: float,
|
|
sample_rate: int,
|
|
channels: int = 2,
|
|
freq: float = 440.0,
|
|
device: str = "cpu",
|
|
half: bool = False,
|
|
) -> torch.Tensor:
|
|
"""Return a [channels, samples] sine-wave tensor in [-AMPLITUDE, AMPLITUDE]."""
|
|
t = torch.linspace(0, duration, int(duration * sample_rate), device=device)
|
|
wave = AMPLITUDE * torch.sin(2 * math.pi * freq * t)
|
|
if half:
|
|
wave = wave.half()
|
|
return wave.expand(channels, -1).clone()
|
|
|
|
|
|
def assert_audio_valid(
|
|
audio: torch.Tensor, expected_duration: float, sample_rate: int
|
|
) -> None:
|
|
"""Assert that an audio tensor looks like valid, non-trivial audio output.
|
|
|
|
Args:
|
|
audio: Output tensor of shape [B, C, T].
|
|
expected_duration: Expected length in seconds.
|
|
sample_rate: Sample rate in Hz.
|
|
"""
|
|
assert audio is not None, "Audio output is None"
|
|
assert audio.ndim == 3, f"Expected 3D tensor [B, C, T], got shape {audio.shape}"
|
|
|
|
expected_samples = int(expected_duration * sample_rate)
|
|
actual_samples = audio.shape[-1]
|
|
tolerance = 0.15
|
|
relative_error = abs(actual_samples - expected_samples) / expected_samples
|
|
assert relative_error < tolerance, (
|
|
f"Audio length {actual_samples} samples deviates more than {tolerance * 100:.0f}% "
|
|
f"from expected {expected_samples} samples ({expected_duration}s @ {sample_rate}Hz)"
|
|
)
|
|
|
|
assert not torch.isnan(audio).any(), "Audio output contains NaN values"
|
|
|
|
abs_max = audio.abs().max().item()
|
|
assert abs_max > 0.001, f"Audio output appears silent (abs_max={abs_max:.5f})"
|
|
assert abs_max <= 1.0, f"Audio output is clipping (abs_max={abs_max:.5f})"
|