Fix: numpy dependency order, add proper error handling

Dockerfile

@@ -1,23 +1,28 @@
+# Dockerfile
 FROM python:3.10-slim
 
 WORKDIR /app
 
-# Install system dependencies
+# Install system dependencies FIRST
 RUN apt-get update && apt-get install -y \
     ffmpeg \
+    libsndfile1 \
     && rm -rf /var/lib/apt/lists/*
 
 # Copy requirements
 COPY requirements.txt .
 
-# Install Python dependencies
-RUN pip install --no-cache-dir -r requirements.txt
+# Install Python dependencies in CORRECT ORDER
+# numpy MUST be first, before torch/torchaudio
+RUN pip install --no-cache-dir numpy>=1.24.0,<2.0.0 && \
+    pip install --no-cache-dir -r requirements.txt
 
-# Copy app code
+# Copy application code
 COPY . .
 
 # Expose port
 EXPOSE 7860
 
-# Run the API
-CMD ["python", "app.py"]
+# Run with proper Python settings
+ENV PYTHONUNBUFFERED=1
+CMD ["python", "app.py"]

app.py

@@ -1,23 +1,39 @@
 # app.py
+import logging
+import os
+import sys
+from pathlib import Path
 from fastapi import FastAPI, UploadFile, File, HTTPException
 from fastapi.responses import JSONResponse
 from fastapi.middleware.cors import CORSMiddleware
-import logging
-import os
-from diagnosis.ai_engine.detect_stuttering import get_stutter_detector
 
-# Configure logging
-logging.basicConfig(level=logging.INFO)
+# Configure logging FIRST
+logging.basicConfig(
+    level=logging.INFO,
+    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
+    stream=sys.stdout
+)
 logger = logging.getLogger(__name__)
 
+# Add project root to path
+sys.path.insert(0, str(Path(__file__).parent))
+
+# Import detector
+try:
+    from diagnosis.ai_engine.detect_stuttering import get_stutter_detector
+    logger.info("✅ Successfully imported StutterDetector")
+except ImportError as e:
+    logger.error(f"❌ Failed to import StutterDetector: {e}")
+    raise
+
 # Initialize FastAPI
 app = FastAPI(
     title="Stutter Detector API",
-    description="Speech analysis using Wav2Vec2 models",
+    description="Speech analysis using Wav2Vec2 models for stutter detection",
     version="1.0.0"
 )
 
-# Add CORS
+# Add CORS middleware
 app.add_middleware(
     CORSMiddleware,
     allow_origins=["*"],
@@ -26,73 +42,111 @@ app.add_middleware(
     allow_headers=["*"],
 )
 
-# Initialize detector (loads models once)
+# Global detector instance
 detector = None
 
 @app.on_event("startup")
 async def startup_event():
-    """Load models when app starts"""
+    """Load models on startup"""
     global detector
-    logger.info("🚀 Starting up... Loading models...")
-    detector = get_stutter_detector()
-    logger.info("✅ Models loaded successfully!")
+    try:
+        logger.info("🚀 Startup event: Loading AI models...")
+        detector = get_stutter_detector()
+        logger.info("✅ Models loaded successfully!")
+    except Exception as e:
+        logger.error(f"❌ Failed to load models: {e}", exc_info=True)
+        raise
 
 @app.get("/health")
 async def health_check():
     """Health check endpoint"""
     return {
         "status": "healthy",
-        "models_loaded": detector is not None
+        "models_loaded": detector is not None,
+        "timestamp": str(os.popen("date").read()).strip()
     }
 
 @app.post("/analyze")
 async def analyze_audio(
     audio: UploadFile = File(...),
-    transcript: str = None
+    transcript: str = ""
 ):
     """
-    Analyze audio for stuttering
+    Analyze audio file for stuttering
     
     Parameters:
-    - audio: MP3/WAV file upload
+    - audio: WAV or MP3 audio file
     - transcript: Optional expected transcript
     
-    Returns: Stuttering analysis results
+    Returns: Complete stutter analysis results
     """
+    temp_file = None
     try:
-        # Save uploaded file temporarily
-        file_path = f"/tmp/{audio.filename}"
-        with open(file_path, "wb") as f:
-            contents = await audio.read()
-            f.write(contents)
+        if not detector:
+            raise HTTPException(status_code=503, detail="Models not loaded yet. Try again in a moment.")
         
-        logger.info(f"📥 Analyzing: {audio.filename}")
+        logger.info(f"📥 Processing: {audio.filename}")
         
-        # Run analysis
-        result = detector.analyze_audio(file_path, transcript or "")
+        # Create temp directory if needed
+        temp_dir = "/tmp/stutter_analysis"
+        os.makedirs(temp_dir, exist_ok=True)
         
-        # Cleanup
-        os.remove(file_path)
+        # Save uploaded file
+        temp_file = os.path.join(temp_dir, audio.filename)
+        content = await audio.read()
+        
+        with open(temp_file, "wb") as f:
+            f.write(content)
+        
+        logger.info(f"📂 Saved to: {temp_file} ({len(content) / 1024 / 1024:.2f} MB)")
         
-        logger.info(f"✅ Analysis complete for {audio.filename}")
+        # Analyze
+        logger.info(f"🔄 Analyzing audio with transcript: '{transcript[:50]}...'")
+        result = detector.analyze_audio(temp_file, transcript)
+        
+        logger.info(f"✅ Analysis complete: severity={result['severity']}, mismatch={result['mismatch_percentage']}%")
         return result
         
+    except HTTPException:
+        raise
     except Exception as e:
-        logger.error(f"❌ Error: {str(e)}")
-        raise HTTPException(status_code=500, detail=str(e))
+        logger.error(f"❌ Error during analysis: {str(e)}", exc_info=True)
+        raise HTTPException(status_code=500, detail=f"Analysis failed: {str(e)}")
+    
+    finally:
+        # Cleanup
+        if temp_file and os.path.exists(temp_file):
+            try:
+                os.remove(temp_file)
+                logger.info(f"🧹 Cleaned up: {temp_file}")
+            except Exception as e:
+                logger.warning(f"Could not clean up {temp_file}: {e}")
 
 @app.get("/")
 async def root():
     """API documentation"""
     return {
-        "message": "Stutter Detector API",
+        "name": "SLAQ Stutter Detector API",
+        "version": "1.0.0",
+        "status": "running",
         "endpoints": {
-            "health": "/health",
-            "analyze": "/analyze (POST with audio file + optional transcript)",
-            "docs": "/docs"
+            "health": "GET /health",
+            "analyze": "POST /analyze (multipart: audio file + optional transcript field)",
+            "docs": "GET /docs (interactive API docs)"
+        },
+        "models": {
+            "base": "facebook/wav2vec2-base-960h",
+            "large": "facebook/wav2vec2-large-960h-lv60-self",
+            "xlsr": "jonatasgrosman/wav2vec2-large-xlsr-53-english"
         }
     }
 
 if __name__ == "__main__":
     import uvicorn
-    uvicorn.run(app, host="0.0.0.0", port=7860)
+    logger.info("🚀 Starting SLAQ Stutter Detector API...")
+    uvicorn.run(
+        app,
+        host="0.0.0.0",
+        port=7860,
+        log_level="info"
+    )

requirements.txt

@@ -1,7 +1,18 @@
-librosa==0.10.0
+# Core ML Dependencies - ORDER MATTERS!
+numpy>=1.24.0,<2.0.0
 torch==2.0.1
 torchaudio==2.0.2
+librosa>=0.10.0
 transformers==4.35.0
+
+# Audio Processing
+soundfile>=0.12.1
+scipy>=1.11.0
+
+# API Framework
 fastapi==0.104.1
 uvicorn==0.24.0
-python-multipart==0.0.6
+python-multipart==0.0.6
+
+# Logging
+python-json-logger>=2.0.0