Changes made

Dockerfile

@@ -24,7 +24,8 @@ RUN apt-get update && \
     libtesseract-dev \
     tesseract-ocr-eng \
     tesseract-ocr-fra \
-    tesseract-ocr-spa && \
+    tesseract-ocr-spa \
+    curl && \
     rm -rf /var/lib/apt/lists/*
 
 # Copy Python dependencies from system locations
@@ -33,10 +34,6 @@ COPY --from=builder /usr/local/bin/gunicorn /usr/local/bin/
 COPY --from=builder /usr/local/bin/uvicorn /usr/local/bin/
 COPY . .
 
-# Health check endpoint
-HEALTHCHECK --interval=30s --timeout=30s --start-period=5s --retries=3 \
-    CMD curl -f http://localhost:8000/health || exit 1
-
 # Create non-root user and set permissions
 RUN useradd -m appuser && \
     chown -R appuser:appuser /app && \
@@ -46,6 +43,11 @@ RUN useradd -m appuser && \
 # Switch to non-root user
 USER appuser
 
-EXPOSE 8000
+# Health check with longer intervals and start period for model loading
+HEALTHCHECK --interval=60s --timeout=30s --start-period=300s --retries=5 \
+    CMD curl -f http://localhost:7860/health || exit 1
+
+EXPOSE 7860
 
-CMD ["gunicorn", "-k", "uvicorn.workers.UvicornWorker", "-b", "0.0.0.0:8000", "--timeout", "120", "app.main:app"]
+# Use port 7860 which is standard for Hugging Face Spaces
+CMD ["gunicorn", "-k", "uvicorn.workers.UvicornWorker", "-b", "0.0.0.0:7860", "--timeout", "300", "--worker-connections", "10", "app.main:app"]

app/main.py

@@ -1,18 +1,97 @@
 from fastapi import FastAPI
 from fastapi.middleware.cors import CORSMiddleware
+from fastapi.responses import JSONResponse
+import asyncio
 from fastapi import FastAPI
 from .api.v1.router import router as api_router
 from app.api.v1.endpoints import transcription, ocr, translation, tts
+import logging
+logging.basicConfig(level=logging.INFO)
 
 app = FastAPI(generate_unique_id_function=lambda route: f"{route.tags[0]}_{route.name}")
 
-app.include_router(api_router)
+# Global flag to track if models are loaded
+models_loaded = False
+loading_progress = {"status": "initializing", "message": "Starting model loading..."}
 
-#app = FastAPI(
-#    title="Polyglot API",
-#    description="Multilingual Communication Suite",
-#    version="1.0.0"
-#)
+async def load_models():
+    """Load heavy models asynchronously during startup"""
+    global models_loaded, loading_progress
+    
+    try:
+        loading_progress["status"] = "loading"
+        loading_progress["message"] = "Loading Whisper model..."
+        
+        # Load your Whisper model here
+        # whisper_model = whisper.load_model("base")
+        
+        loading_progress["message"] = "Loading TTS model..."
+        # Load your TTS model here
+        
+        loading_progress["message"] = "Loading translator..."
+        # Initialize deep-translator
+        
+        models_loaded = True
+        loading_progress["status"] = "ready"
+        loading_progress["message"] = "All models loaded successfully"
+        logging.info("All models loaded successfully")
+        
+    except Exception as e:
+        loading_progress["status"] = "error"
+        loading_progress["message"] = f"Error loading models: {str(e)}"
+        logging.error(f"Error loading models: {str(e)}")
+
+@app.on_event("startup")
+async def startup_event():
+    """Start model loading in background during app startup"""
+    asyncio.create_task(load_models())
+
+@app.get("/health")
+async def health_check():
+    """
+    Health check endpoint that responds quickly
+    Returns different status based on model loading progress
+    """
+    if models_loaded:
+        return JSONResponse(
+            status_code=200,
+            content={
+                "status": "healthy",
+                "models_loaded": True,
+                "message": "Service is ready"
+            }
+        )
+    else:
+        # Return 200 even during loading to pass health checks
+        # But indicate that models are still loading
+        return JSONResponse(
+            status_code=200,
+            content={
+                "status": "loading",
+                "models_loaded": False,
+                "progress": loading_progress
+            }
+        )
+
+@app.get("/ready")
+async def readiness_check():
+    """
+    Separate readiness endpoint for when models are fully loaded
+    """
+    if models_loaded:
+        return JSONResponse(
+            status_code=200,
+            content={"status": "ready", "models_loaded": True}
+        )
+    else:
+        return JSONResponse(
+            status_code=503,
+            content={
+                "status": "not_ready", 
+                "models_loaded": False,
+                "progress": loading_progress
+            }
+        )
 
 # CORS configuration
 app.add_middleware(