[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/stt.py

@@ -17,12 +17,28 @@ from .models import AudioFrame, AudioSegment, ErrorCode, ProviderError, Transcri
 from .speech_models import stt_model_paths
 
 _MEANINGFUL_TEXT = re.compile(r"[\w\u4e00-\u9fff]", re.UNICODE)
+_PARTIAL_MIN_MEANINGFUL_CHARS = 3
 
 
 def is_valid_transcript_text(text: str) -> bool:
     return bool(_MEANINGFUL_TEXT.search(text.strip()))
 
 
+def _meaningful_text_length(text: str) -> int:
+    return len(_MEANINGFUL_TEXT.findall(text.strip()))
+
+
+def should_emit_partial_transcript(text: str, last_text: str) -> bool:
+    normalized = text.strip()
+    if not is_valid_transcript_text(normalized) or _meaningful_text_length(normalized) < _PARTIAL_MIN_MEANINGFUL_CHARS:
+        return False
+    if normalized == last_text:
+        return False
+    if not last_text:
+        return True
+    return normalized.startswith(last_text)
+
+
 class MetadataSttProvider:
     def __init__(self, language: str = "zh") -> None:
         self.language = language
@@ -73,7 +89,7 @@ class MetadataRealtimeTranscriptSession:
             or frame.metadata.get("transcript")
             or ""
         ).strip()
-        if not is_valid_transcript_text(text) or text == self._last_text:
+        if not should_emit_partial_transcript(text, self._last_text):
             return None
         self._last_text = text
         return Transcript(
@@ -197,7 +213,11 @@ class SherpaOnnxSttProvider:
                 "stt",
             )
         paths = stt_model_paths(self.model_path)
-        missing = [name for name, path in paths.items() if name != "model_dir" and not path.exists()]
+        missing = [
+            name
+            for name, path in paths.items()
+            if name not in {"type", "model_dir"} and isinstance(path, Path) and not path.exists()
+        ]
         if missing:
             raise ProviderError(
                 ErrorCode.STT_MODEL_MISSING,
@@ -219,16 +239,29 @@ class SherpaOnnxSttProvider:
                     "stt",
                 ) from exc
         try:
-            self._recognizer = sherpa_onnx.OnlineRecognizer.from_transducer(
-                tokens=str(paths["tokens"]),
-                encoder=str(paths["encoder"]),
-                decoder=str(paths["decoder"]),
-                joiner=str(paths["joiner"]),
-                num_threads=1,
-                decoding_method="greedy_search",
-                enable_endpoint_detection=True,
-                provider="cpu",
-            )
+            model_type = str(paths.get("type", "sherpa-onnx-streaming-transducer"))
+            if model_type == "sherpa-onnx-streaming-zipformer2-ctc":
+                self._recognizer = sherpa_onnx.OnlineRecognizer.from_zipformer2_ctc(
+                    tokens=str(paths["tokens"]),
+                    model=str(paths["model"]),
+                    num_threads=1,
+                    sample_rate=16000,
+                    feature_dim=80,
+                    enable_endpoint_detection=True,
+                    decoding_method="greedy_search",
+                    provider="cpu",
+                )
+            else:
+                self._recognizer = sherpa_onnx.OnlineRecognizer.from_transducer(
+                    tokens=str(paths["tokens"]),
+                    encoder=str(paths["encoder"]),
+                    decoder=str(paths["decoder"]),
+                    joiner=str(paths["joiner"]),
+                    num_threads=1,
+                    decoding_method="greedy_search",
+                    enable_endpoint_detection=True,
+                    provider="cpu",
+                )
         except Exception as exc:
             raise ProviderError(
                 ErrorCode.STT_TRANSCRIBE_FAILED,
@@ -331,7 +364,7 @@ class SherpaOnnxRealtimeTranscriptSession:
                 "sherpa-onnx-stt",
                 "stt",
             ) from exc
-        if not is_valid_transcript_text(text) or text == self._last_text:
+        if not should_emit_partial_transcript(text, self._last_text):
             return None
         self._last_text = text
         return Transcript(