[本地语音降噪]：完成本地语音链路和噪音过滤，包含降噪模型、本地ASR和实时字幕稳定策略

src/owner_voice_pet/config.py

@@ -29,6 +29,9 @@ class AppConfig:
     post_playback_drain_ms: int = 0
     pipeline_mode: str = "live_turn_based"
     endpoint_mode: str = "primary_speaker"
+    noise_filter_enabled: bool = True
+    noise_filter_provider: str = "sherpa_onnx_gtcrn"
+    wake_denoise_enabled: bool = False
     speaker_profile_ms: int = 600
     speaker_profile_min_ms: int = 120
     speaker_absent_ms: int = 300
@@ -40,7 +43,7 @@ class AppConfig:
     vad_end_silence_ms: int = 350
     vad_no_speech_timeout_ms: int = 5000
     vad_max_recording_ms: int = 12000
-    speech_provider: str = "cloud"
+    speech_provider: str = "local"
     asr_model: str = "mimo-v2.5-asr"
     tts_model: str = "mimo-v2.5-tts"
     tts_voice: str = "mimo_default"
@@ -80,6 +83,9 @@ class AppConfig:
             post_playback_drain_ms=int(get("POST_PLAYBACK_DRAIN_MS", "0") or "0"),
             pipeline_mode=(get("PIPELINE_MODE", "live_turn_based") or "live_turn_based").lower(),
             endpoint_mode=(get("ENDPOINT_MODE", "primary_speaker") or "primary_speaker").lower(),
+            noise_filter_enabled=(get("NOISE_FILTER_ENABLED", "1") or "1").lower() not in {"0", "false", "no"},
+            noise_filter_provider=(get("NOISE_FILTER_PROVIDER", "sherpa_onnx_gtcrn") or "sherpa_onnx_gtcrn").lower(),
+            wake_denoise_enabled=(get("WAKE_DENOISE_ENABLED", "0") or "0").lower() in {"1", "true", "yes"},
             speaker_profile_ms=int(get("SPEAKER_PROFILE_MS", "600") or "600"),
             speaker_profile_min_ms=int(get("SPEAKER_PROFILE_MIN_MS", "120") or "120"),
             speaker_absent_ms=int(get("SPEAKER_ABSENT_MS", "300") or "300"),
@@ -93,7 +99,7 @@ class AppConfig:
             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(),
+            speech_provider=(get("SPEECH_PROVIDER", "local") or "local").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",
             tts_voice=get("TTS_VOICE", "mimo_default") or "mimo_default",
@@ -189,6 +195,16 @@ class AppConfig:
                     "startup",
                 )
             )
+        if self.noise_filter_provider not in {"sherpa_onnx_gtcrn"}:
+            errors.append(
+                ProviderError(
+                    ErrorCode.CONFIG_MISSING_VALUE,
+                    "OWNER_NOISE_FILTER_PROVIDER must be sherpa_onnx_gtcrn",
+                    False,
+                    "config",
+                    "startup",
+                )
+            )
         if self.post_playback_drain_ms < 0:
             errors.append(
                 ProviderError(