[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

tests/test_models_config.py

@@ -1,7 +1,9 @@
 from __future__ import annotations
 
+import json
 import tempfile
 import unittest
+from pathlib import Path
 
 from owner_voice_pet.config import AppConfig
 from owner_voice_pet.models import (
@@ -12,6 +14,12 @@ from owner_voice_pet.models import (
     PipelineState,
     ProviderError,
 )
+from owner_voice_pet.speech_models import (
+    DEFAULT_DENOISER_PATH,
+    default_manifest,
+    denoiser_model_path,
+    stt_model_paths,
+)
 
 
 class ModelsConfigTests(unittest.TestCase):
@@ -77,6 +85,9 @@ class ModelsConfigTests(unittest.TestCase):
             self.assertEqual(config.post_playback_drain_ms, 0)
             self.assertEqual(config.pipeline_mode, "live_turn_based")
             self.assertEqual(config.endpoint_mode, "primary_speaker")
+            self.assertTrue(config.noise_filter_enabled)
+            self.assertEqual(config.noise_filter_provider, "sherpa_onnx_gtcrn")
+            self.assertFalse(config.wake_denoise_enabled)
             self.assertEqual(config.speaker_profile_ms, 600)
             self.assertEqual(config.speaker_profile_min_ms, 120)
             self.assertEqual(config.speaker_absent_ms, 300)
@@ -88,7 +99,7 @@ class ModelsConfigTests(unittest.TestCase):
             self.assertEqual(config.vad_end_silence_ms, 350)
             self.assertEqual(config.vad_no_speech_timeout_ms, 5000)
             self.assertEqual(config.vad_max_recording_ms, 12000)
-            self.assertEqual(config.speech_provider, "cloud")
+            self.assertEqual(config.speech_provider, "local")
             self.assertEqual(config.asr_model, "mimo-v2.5-asr")
             self.assertEqual(config.tts_model, "mimo-v2.5-tts")
             self.assertEqual(config.tts_voice, "mimo_default")
@@ -117,6 +128,11 @@ class ModelsConfigTests(unittest.TestCase):
         errors = config.validate_basic()
         self.assertTrue(any("OWNER_ENDPOINT_MODE" in error.message for error in errors))
 
+    def test_noise_filter_provider_must_be_gtcrn(self) -> None:
+        config = AppConfig(noise_filter_provider="invalid")
+        errors = config.validate_basic()
+        self.assertTrue(any("OWNER_NOISE_FILTER_PROVIDER" in error.message for error in errors))
+
     def test_speaker_similarity_threshold_range_is_validated(self) -> None:
         config = AppConfig(speaker_similarity_threshold=1.5)
         errors = config.validate_basic()
@@ -153,6 +169,30 @@ class ModelsConfigTests(unittest.TestCase):
         message = Message(role="user", content="你好", created_at=1.0)
         self.assertEqual(message.role, "user")
 
+    def test_default_manifest_uses_ctc_stt_and_denoiser(self) -> None:
+        manifest = default_manifest()
+        stt = manifest["providers"]["stt"]
+        denoiser = manifest["providers"]["denoiser"]
+
+        self.assertEqual(stt["type"], "sherpa-onnx-streaming-zipformer2-ctc")
+        self.assertTrue(stt["model"].endswith("model.int8.onnx"))
+        self.assertEqual(denoiser["path"], DEFAULT_DENOISER_PATH)
+        self.assertIn(DEFAULT_DENOISER_PATH, manifest["required_files"])
+
+    def test_model_path_helpers_support_ctc_manifest_and_denoiser(self) -> None:
+        with tempfile.TemporaryDirectory() as tmp:
+            root = Path(tmp)
+            manifest_path = root / "manifest.json"
+            manifest_path.write_text(
+                json.dumps(default_manifest(), ensure_ascii=False),
+                encoding="utf-8",
+            )
+            paths = stt_model_paths(root)
+
+        self.assertEqual(paths["type"], "sherpa-onnx-streaming-zipformer2-ctc")
+        self.assertTrue(str(paths["model"]).endswith("model.int8.onnx"))
+        self.assertTrue(str(denoiser_model_path(root)).endswith(DEFAULT_DENOISER_PATH))
+
 
 if __name__ == "__main__":
     unittest.main()