xsl
f5eae6d37c
- web/harness/engine-voice.test.mjs：引擎 voice 句尾保真三不变式（I1 源未耗尽不得结算 / I2 耗尽后排空窗才断开 / I3 零消耗走旧路径），可驱动 SPN mock 模拟真实消耗， 15 断言全绿；防止未来重构回潮 - tools/audit_voice_tails.py：voice 资产尾部静默审计工具入库（含判读口径头注： 尾静默紧=裁剪工艺≠剪字，句尾完整性验收在引擎层） - 文档：HANDOVER（§1.4 回归清单 / §5.3 质量手段 / §6 已解决账）、roadmap §4 新增全游戏「句尾完整性」真机听测项、asset-pipeline QC 口径、methodology §5 度量盲区教训（媒体播完类问题转写层无效，必须真人耳测+引擎断言）、 web-engine-api voice 自然结束语义 - 修正：结束判定改用 filter.sourcePosition（SimpleFilter 单调精确计数器）； 10 套件全绿（8 playtest + guide + engine-voice）
93 lines
3.4 KiB
Python
93 lines
3.4 KiB
Python
#!/usr/bin/env python3
|
|
# -*- coding: utf-8 -*-
|
|
"""voice 资产尾部静默审计（2026-09 句尾剪字排查的固化工具）。
|
|
|
|
用途：量化每个 voice 文件「最后一段人声能量 → 文件末尾」的静默长度，观察
|
|
生产管线的尾部裁剪松紧、发现异常文件（如 0 静默且能量戛然而止的可疑样本）。
|
|
|
|
⚠ 判读口径（2026-09 排查结论，勿推翻）：
|
|
- 本项目 TTS 管线峰值归一 + 静音尾裁剪很紧，**绝大多数文件尾部静默 <120ms
|
|
属预期**，不等于剪字。tail 静默长度不能单独作为「句尾被剪」的证据。
|
|
- 「句子是否读完」的验收在**引擎层**（voice 自然结束以源消耗位置判定 +
|
|
300ms 管线排空，见 web/engine/audio.js _finishVoice 与
|
|
web/harness/engine-voice.test.mjs），不在资产层。
|
|
- 资产侧怀疑剪字时，用 SenseVoice ASR 抽查可疑文件并核对末字/语气词
|
|
（管线：.venv-asr/bin/python，参照 research/new8 排查记录）。
|
|
|
|
用法：
|
|
.venv-tts/bin/python tools/audit_voice_tails.py # 全部 8 游戏
|
|
.venv-tts/bin/python tools/audit_voice_tails.py --tail-min 0.08
|
|
"""
|
|
import argparse
|
|
import array
|
|
import os
|
|
import subprocess
|
|
|
|
ROOT = os.environ.get(
|
|
"SG_ROOT",
|
|
os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))),
|
|
)
|
|
FF = os.path.join(ROOT, "tools", "bin", "ffmpeg")
|
|
WEB = os.path.join(ROOT, "web")
|
|
GAMES = ["storyline", "escape", "simon", "rhythm", "space", "rpg", "radio", "dungeon"]
|
|
|
|
ap = argparse.ArgumentParser(description="voice 资产尾部静默审计")
|
|
ap.add_argument("--tail-min", type=float, default=0.120,
|
|
help="尾部静默阈值（秒），低于此列入报告（默认 0.120）")
|
|
TAIL_MIN = ap.parse_args().tail_min
|
|
|
|
|
|
def profile(path):
|
|
"""解码 16k mono pcm_s16le，返回 (dur, head_sil, tail_sil) 秒。"""
|
|
p = subprocess.run([FF, "-v", "error", "-i", path, "-ac", "1", "-ar", "16000",
|
|
"-f", "s16le", "-"], capture_output=True)
|
|
data = p.stdout
|
|
if len(data) < 3200:
|
|
return None
|
|
a = array.array('h')
|
|
a.frombytes(data)
|
|
n = len(a)
|
|
win = 320 # 20ms @16k
|
|
|
|
def rms(i):
|
|
seg = a[i:i + win]
|
|
return (sum(x * x for x in seg) / win) ** 0.5
|
|
|
|
last, first = -1, -1
|
|
for i in range(0, n - win, win):
|
|
if rms(i) > 500: # ≈ -30dBFS 记为有人声
|
|
if first < 0:
|
|
first = i
|
|
last = i
|
|
if last < 0:
|
|
return None
|
|
dur = n / 16000.0
|
|
tail = (n - (last + win)) / 16000.0
|
|
head = first / 16000.0
|
|
return dur, head, tail
|
|
|
|
|
|
def main():
|
|
bad, total = [], 0
|
|
for g in GAMES:
|
|
vdir = os.path.join(WEB, g, "audio", "voice")
|
|
for dp, _dn, fs in os.walk(vdir):
|
|
for f in fs:
|
|
if not f.endswith((".ogg", ".m4a")):
|
|
continue
|
|
total += 1
|
|
r = profile(os.path.join(dp, f))
|
|
if not r:
|
|
continue
|
|
dur, _head, tail = r
|
|
if tail < TAIL_MIN:
|
|
bad.append((os.path.relpath(os.path.join(dp, f), WEB), dur, tail))
|
|
print(f"scanned {total} voice files")
|
|
print(f"tail silence < {int(TAIL_MIN*1000)}ms: {len(bad)}（判读口径见文件头注）")
|
|
for rel, dur, tail in sorted(bad, key=lambda x: x[2])[:40]:
|
|
print(f" tail={int(tail*1000):4d}ms dur={dur:5.2f}s {rel}")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|