[唤醒应答与快速端点]:完成唤醒后我在播报和本地VAD端点优化,包含缓冲清理、配置项和测试覆盖

This commit is contained in:
mkbk
2026-06-17 20:51:14 +08:00
parent 860c2909fc
commit 44f708a3dc
12 changed files with 224 additions and 7 deletions
+62
View File
@@ -24,6 +24,14 @@ class AppConfig:
wake_keywords_file: Path | None = None
wake_kws_threshold: float = 0.25
wake_kws_score: float = 1.0
wake_ack_text: str = "我在"
post_playback_drain_ms: int = 250
vad_provider: str = "local"
vad_threshold: float = 0.5
vad_min_duration_ms: int = 250
vad_end_silence_ms: int = 350
vad_no_speech_timeout_ms: int = 5000
vad_max_recording_ms: int = 12000
speech_provider: str = "cloud"
asr_model: str = "mimo-v2.5-asr"
tts_model: str = "mimo-v2.5-tts"
@@ -57,6 +65,14 @@ class AppConfig:
wake_keywords_file=Path(value) if (value := get("WAKE_KEYWORDS_FILE")) else None,
wake_kws_threshold=float(get("WAKE_KWS_THRESHOLD", "0.25") or "0.25"),
wake_kws_score=float(get("WAKE_KWS_SCORE", "1.0") or "1.0"),
wake_ack_text=get("WAKE_ACK_TEXT", "我在") or "我在",
post_playback_drain_ms=int(get("POST_PLAYBACK_DRAIN_MS", "250") or "250"),
vad_provider=(get("VAD_PROVIDER", "local") or "local").lower(),
vad_threshold=float(get("VAD_THRESHOLD", "0.5") or "0.5"),
vad_min_duration_ms=int(get("VAD_MIN_DURATION_MS", "250") or "250"),
vad_end_silence_ms=int(get("VAD_END_SILENCE_MS", "350") or "350"),
vad_no_speech_timeout_ms=int(get("VAD_NO_SPEECH_TIMEOUT_MS", "5000") or "5000"),
vad_max_recording_ms=int(get("VAD_MAX_RECORDING_MS", "12000") or "12000"),
speech_provider=(get("SPEECH_PROVIDER", "cloud") or "cloud").lower(),
asr_model=get("ASR_MODEL", "mimo-v2.5-asr") or "mimo-v2.5-asr",
tts_model=get("TTS_MODEL", "mimo-v2.5-tts") or "mimo-v2.5-tts",
@@ -152,6 +168,52 @@ class AppConfig:
"startup",
)
)
if self.post_playback_drain_ms < 0:
errors.append(
ProviderError(
ErrorCode.CONFIG_MISSING_VALUE,
"OWNER_POST_PLAYBACK_DRAIN_MS must be non-negative",
False,
"config",
"startup",
)
)
if self.vad_provider not in {"local", "energy"}:
errors.append(
ProviderError(
ErrorCode.CONFIG_MISSING_VALUE,
"OWNER_VAD_PROVIDER must be local or energy",
False,
"config",
"startup",
)
)
if self.vad_threshold <= 0:
errors.append(
ProviderError(
ErrorCode.CONFIG_MISSING_VALUE,
"OWNER_VAD_THRESHOLD must be positive",
False,
"config",
"startup",
)
)
for name, value in {
"OWNER_VAD_MIN_DURATION_MS": self.vad_min_duration_ms,
"OWNER_VAD_END_SILENCE_MS": self.vad_end_silence_ms,
"OWNER_VAD_NO_SPEECH_TIMEOUT_MS": self.vad_no_speech_timeout_ms,
"OWNER_VAD_MAX_RECORDING_MS": self.vad_max_recording_ms,
}.items():
if value <= 0:
errors.append(
ProviderError(
ErrorCode.CONFIG_MISSING_VALUE,
f"{name} must be positive",
False,
"config",
"startup",
)
)
if not self.llm_base_url.startswith(("http://", "https://")):
errors.append(
ProviderError(