Optimizing the Dockerfile: fixing dependency installation order, adding build tools, and resolving potential conflicts

Dockerfile

@@ -2,37 +2,29 @@ FROM python:3.10-slim
 
 WORKDIR /app
 
-# Install system dependencies FIRST (including build tools for compiling packages)
+# Install system dependencies FIRST
 RUN apt-get update && apt-get install -y \
     ffmpeg \
     libsndfile1 \
-    build-essential \
     && rm -rf /var/lib/apt/lists/*
 
-# Upgrade pip and install wheel first
-RUN pip install --upgrade pip setuptools wheel
-
-# Copy requirements early for better Docker layer caching
+# Copy requirements
 COPY requirements.txt .
 
 # Install Python dependencies in CORRECT ORDER
-# numpy MUST be installed first, before torch/torchaudio (prevents conflicts)
+# numpy MUST be first, before torch/torchaudio
 RUN pip install --no-cache-dir "numpy>=1.24.0,<2.0.0"
 
-# Install remaining requirements
-# numpy is already installed above, pip will skip it if version matches
-# Use --prefer-binary to prefer pre-built wheels (faster, more reliable)
-RUN pip install --no-cache-dir --prefer-binary -r requirements.txt
+RUN pip install --no-cache-dir -r requirements.txt
 
 # Copy application code
 COPY . .
 
-# Expose port (HuggingFace Spaces uses 7860)
+# Expose port
 EXPOSE 7860
 
-# Set environment variables
+# Run with proper Python settings
 ENV PYTHONUNBUFFERED=1
-ENV PORT=7860
 
 # Run with uvicorn directly (required for HuggingFace Spaces)
 # Use PORT environment variable if provided, otherwise default to 7860

app.py

@@ -3,7 +3,7 @@ import logging
 import os
 import sys
 from pathlib import Path
-from fastapi import FastAPI, UploadFile, File, Form, HTTPException
+from fastapi import FastAPI, UploadFile, File, HTTPException
 from fastapi.responses import JSONResponse
 from fastapi.middleware.cors import CORSMiddleware
 
@@ -55,10 +55,7 @@ async def startup_event():
         logger.info("✅ Models loaded successfully!")
     except Exception as e:
         logger.error(f"❌ Failed to load models: {e}", exc_info=True)
-        # Don't raise - allow app to start and return 503 on analyze requests
-        # This allows HuggingFace Spaces to show the app is running
-        logger.warning("⚠️ App will start but models are not loaded. Analyze requests will return 503.")
-        detector = None
+        raise
 
 @app.get("/health")
 async def health_check():
@@ -73,8 +70,7 @@ async def health_check():
 @app.post("/analyze")
 async def analyze_audio(
     audio: UploadFile = File(...),
-    transcript: str = Form(""),
-    language: str = Form("english")
+    transcript: str = ""
 ):
     """
     Analyze audio file for stuttering
@@ -82,7 +78,6 @@ async def analyze_audio(
     Parameters:
     - audio: WAV or MP3 audio file
     - transcript: Optional expected transcript
-    - language: Language code (e.g., 'hindi', 'english', 'tamil'). Defaults to 'english'
     
     Returns: Complete stutter analysis results
     """
@@ -91,7 +86,7 @@ async def analyze_audio(
         if not detector:
             raise HTTPException(status_code=503, detail="Models not loaded yet. Try again in a moment.")
         
-        logger.info(f"📥 Processing: {audio.filename} [Language: {language}]")
+        logger.info(f"📥 Processing: {audio.filename}")
         
         # Create temp directory if needed
         temp_dir = "/tmp/stutter_analysis"
@@ -106,10 +101,9 @@ async def analyze_audio(
         
         logger.info(f"📂 Saved to: {temp_file} ({len(content) / 1024 / 1024:.2f} MB)")
         
-        # Analyze with language parameter
-        transcript_preview = transcript[:50] if transcript else "None"
-        logger.info(f"🔄 Analyzing audio with transcript: '{transcript_preview}...' [Language: {language}]")
-        result = detector.analyze_audio(temp_file, transcript, language=language)
+        # 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
@@ -138,7 +132,7 @@ async def root():
         "status": "running",
         "endpoints": {
             "health": "GET /health",
-            "analyze": "POST /analyze (multipart form: audio file, transcript (optional), language (optional, default: 'english'))",
+            "analyze": "POST /analyze (multipart: audio file + optional transcript field)",
             "docs": "GET /docs (interactive API docs)"
         },
         "models": {
@@ -150,12 +144,10 @@ async def root():
 
 if __name__ == "__main__":
     import uvicorn
-    # Read port from environment variable (HuggingFace Spaces provides this)
-    port = int(os.environ.get("PORT", 7860))
-    logger.info(f"🚀 Starting SLAQ Stutter Detector API on port {port}...")
+    logger.info("🚀 Starting SLAQ Stutter Detector API...")
     uvicorn.run(
         app,
         host="0.0.0.0",
-        port=port,
+        port=7860,
         log_level="info"
     )

requirements.txt

@@ -1,5 +1,5 @@
 # Core ML Dependencies - ORDER MATTERS!
-# Note: In Dockerfile, numpy is installed separately first to prevent conflicts
+
 numpy>=1.24.0,<2.0.0
 torch==2.0.1
 torchaudio==2.0.2
@@ -9,11 +9,6 @@ transformers==4.35.0
 # Audio Processing
 soundfile>=0.12.1
 scipy>=1.11.0
-parselmouth>=0.4.0
-
-# Machine Learning
-scikit-learn>=1.3.0
-fastdtw>=0.3.0
 
 # API Framework
 fastapi==0.104.1