Migrate backend jobs to Redis Streams

backend/tts_asr.py

@@ -40,7 +40,8 @@ try:
 except Exception as e:  # pragma: no cover
     logger.debug("modelscope import failed (optional): %s", e)
 
-router = APIRouter()
+meta_router = APIRouter()
+generation_router = APIRouter()
 
 # Global model instances
 _tts_model: Optional["Qwen3TTSModel"] = None
@@ -314,7 +315,7 @@ def _ensure_align_model():
     return _align_model
 
 
-@router.get("/status", response_model=ModelStatus)
+@meta_router.get("/status", response_model=ModelStatus)
 async def get_status():
     """获取模型状态"""
     return ModelStatus(
@@ -324,7 +325,7 @@ async def get_status():
     )
 
 
-@router.get("/config")
+@meta_router.get("/config")
 async def get_config():
     """获取配置信息"""
     return {
@@ -340,7 +341,7 @@ async def get_config():
     }
 
 
-@router.post("/warmup")
+@meta_router.post("/warmup")
 async def warmup_models():
     """手动触发模型预热"""
     await _warmup_tts()
@@ -355,39 +356,34 @@ async def warmup_models():
     }
 
 
-@router.post("/tts", response_model=TTSResponse)
-async def tts_endpoint(req: TTSRequest):
-    """TTS 文字转语音端点"""
+async def generate_tts_response(
+    text: str,
+    instruct: str = "",
+    speaker: str = "Vivian",
+    output_format: str = "wav",
+) -> TTSResponse:
+    del speaker  # current model path does not expose multi-speaker routing
+    del output_format  # current implementation always returns wav
     try:
         model = _ensure_tts_model()
     except Exception as e:  # noqa: ANN001
         raise HTTPException(status_code=500, detail=str(e))
 
-    text = req.text
-    instruct = req.instruct or ""
-
     try:
-        # VoiceDesign 模型使用 generate_voice_design 方法
         wavs, sr = model.generate_voice_design(  # type: ignore
             text=text,
             language="Chinese",
-            instruct=instruct,
+            instruct=instruct or "",
         )
     except Exception as e:  # noqa: ANN001
         logger.exception("TTS 推理失败")
         raise HTTPException(status_code=500, detail=f"TTS 推理失败: {e}")
 
-    # Get first audio data
     wav_data = wavs[0] if isinstance(wavs, (list, tuple)) else wavs
-
-    # Convert to numpy array
     if hasattr(wav_data, 'numpy'):  # type: ignore
         wav_data = wav_data.cpu().numpy()  # type: ignore
     wav_data = np.asarray(wav_data, dtype=np.float32)
 
-    logger.debug("wav_data shape: %s, dtype: %s, sr: %s", wav_data.shape, wav_data.dtype, sr)
-
-    # Encode WAV to memory
     tmp_path = None
     try:
         import soundfile as sf  # type: ignore
@@ -404,22 +400,15 @@ async def tts_endpoint(req: TTSRequest):
         if tmp_path and os.path.exists(tmp_path):  # noqa: SIM201
             try:
                 os.unlink(tmp_path)
-            except Exception as e:  # noqa: ANN001
+            except Exception:
                 pass
 
     duration_ms = int(len(wav_data) / sr * 1000) if sr > 0 else 0
-
     audio_base64 = base64.b64encode(audio_bytes).decode("utf-8")
-    return TTSResponse(
-        audio_base64=audio_base64,
-        format="wav",
-        duration_ms=duration_ms,
-    )
+    return TTSResponse(audio_base64=audio_base64, format="wav", duration_ms=duration_ms)
 
 
-@router.post("/asr", response_model=ASRResponse)
-async def asr_endpoint(req: ASRRequest):
-    """语音识别端点（非流式）"""
+async def generate_asr_response(audio_bytes: bytes, language: Optional[str] = "zh-CN") -> ASRResponse:
     if Qwen3ASRModel is None:
         raise HTTPException(status_code=501, detail="mlx_audio 未安装，ASR 功能不可用")
 
@@ -429,10 +418,6 @@ async def asr_endpoint(req: ASRRequest):
         raise HTTPException(status_code=500, detail=f"ASR 模型加载失败: {e}")
 
     try:
-        # Decode base64 audio to WAV bytes
-        audio_bytes = base64.b64decode(req.audio_base64)
-
-        # Load WAV file and convert to 16kHz mono numpy array
         wav_buffer = io.BytesIO(audio_bytes)
         with wave.open(wav_buffer, 'rb') as wf:  # noqa: SIM115
             n_channels = wf.getnchannels()
@@ -443,11 +428,9 @@ async def asr_endpoint(req: ASRRequest):
             raw_data = wf.readframes(n_frames)
             audio_array = np.frombuffer(raw_data, dtype=np.int16 if sampwidth == 2 else np.float32)
 
-            # Convert to mono
             if n_channels > 1:
                 audio_array = np.mean(audio_array.reshape(-1, n_channels), axis=1)
 
-            # Resample to 16kHz if needed
             if framerate != 16000:
                 try:
                     import scipy.signal as signal  # type: ignore
@@ -457,34 +440,47 @@ async def asr_endpoint(req: ASRRequest):
                 except Exception as e2:  # noqa: ANN001
                     logger.warning("重采样失败，使用原始音频: %s", e2)
 
-            # Convert to float32 normalized
             if audio_array.dtype == np.int16:
                 audio_array = audio_array.astype(np.float32) / 32768.0
 
-        # Run ASR inference (non-streaming)
         result = model.generate(  # type: ignore
             audio_array,
-            language=req.language if req.language else None,
+            language=language if language else None,
         )
 
-        # Extract text and detected language from result (STTOutput)
         recognized_text = getattr(result, 'text', str(result)) if hasattr(result, 'text') else str(result)
-        detected_lang = getattr(result, 'language', req.language or "zh-CN")
-
-        # If language is a list (from segments), take the first one
+        detected_lang = getattr(result, 'language', language or "zh-CN")
         if isinstance(detected_lang, list) and len(detected_lang) > 0:
             detected_lang = detected_lang[0]
 
-        return ASRResponse(
-            text=recognized_text,
-            language=str(detected_lang),
-        )
-
+        return ASRResponse(text=recognized_text, language=str(detected_lang))
+    except HTTPException:
+        raise
     except Exception as e:  # noqa: ANN001
         logger.exception("ASR 推理失败")
         raise HTTPException(status_code=500, detail=f"ASR 推理失败: {e}")
 
 
-def register_tts_asr_routes(app):
+@generation_router.post("/tts", response_model=TTSResponse)
+async def tts_endpoint(req: TTSRequest):
+    """TTS 文字转语音端点"""
+    return await generate_tts_response(
+        text=req.text,
+        instruct=req.instruct or "",
+        speaker=req.speaker,
+        output_format=req.format,
+    )
+
+
+@generation_router.post("/asr", response_model=ASRResponse)
+async def asr_endpoint(req: ASRRequest):
+    """语音识别端点（非流式）"""
+    audio_bytes = base64.b64decode(req.audio_base64)
+    return await generate_asr_response(audio_bytes, req.language if req.language else None)
+
+
+def register_tts_asr_routes(app, include_generation_routes: bool = True):
     """注册 TTS/ASR 路由到 FastAPI 应用"""
-    app.include_router(router, prefix="/v1/tts-asr")
+    app.include_router(meta_router, prefix="/v1/tts-asr")
+    if include_generation_routes:
+        app.include_router(generation_router, prefix="/v1/tts-asr")