Update app.py and README.md: Enhance local launch configuration for Docker support and update documentation to include Docker deployment instructions.

.dockerignore

@@ -0,0 +1,42 @@
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+env/
+venv/
+ENV/
+.venv
+
+# IDE
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+
+# OS
+.DS_Store
+Thumbs.db
+
+# Git
+.git/
+.gitignore
+
+# Documentation
+*.md
+!README.md
+
+# Logs
+*.log
+
+# Model cache (will be downloaded in container)
+.cache/
+models/
+
+# Test files
+test/
+tests/
+*.test.py
+

Dockerfile

@@ -0,0 +1,38 @@
+# Use Python 3.10 with CUDA support for GPU acceleration
+FROM python:3.10-slim
+
+# Set working directory
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    git \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy requirements file first for better Docker layer caching
+COPY requirements.txt .
+
+# Install PyTorch with CUDA support for GPU acceleration
+# Hugging Face Spaces provides CUDA runtime, so we use CUDA-enabled PyTorch
+RUN pip install --no-cache-dir torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
+
+# Install remaining Python dependencies
+# Note: pip will skip torch since it's already installed (satisfies requirements.txt)
+# The git dependency in requirements.txt requires git (already installed above)
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy application files
+COPY app.py .
+COPY README.md .
+
+# Expose Gradio default port
+EXPOSE 7860
+
+# Set environment variables
+ENV GRADIO_SERVER_NAME=0.0.0.0
+ENV GRADIO_SERVER_PORT=7860
+
+# Run the application
+CMD ["python", "app.py"]
+

README.md

@@ -3,9 +3,7 @@ title: Stable Audio Open
 emoji: 🎵
 colorFrom: blue
 colorTo: purple
-sdk: gradio
-sdk_version: 6.2.0
-app_file: app.py
+sdk: docker
 pinned: false
 ---
 
@@ -38,10 +36,25 @@ An open-source web interface for generating high-quality audio from text prompts
 ## Technical Details
 
 This application uses:
+- **Docker** for containerized deployment
 - **Gradio** for the web interface
-- **PyTorch** and **Transformers** for AI model integration
+- **PyTorch** (with CUDA support) and **Diffusers** for AI model integration
 - **Stable Audio** technology for high-quality audio generation
 
+## Docker Deployment
+
+This Space is containerized using Docker. The Dockerfile includes:
+- Python 3.10 base image
+- CUDA-enabled PyTorch for GPU acceleration
+- All required dependencies from `requirements.txt`
+- Optimized for GPU inference
+
+To build and run locally:
+```bash
+docker build -t stable-audio-open .
+docker run -p 7860:7860 --gpus all stable-audio-open
+```
+
 ## Contributing
 
 This is an open-source project. Contributions are welcome! Feel free to:

app.py

@@ -185,6 +185,10 @@ def create_audio_generation_interface():
 # Create the Gradio interface for Spaces
 demo = create_audio_generation_interface()
 
-# Launch the interface for local development
+# Launch the interface for local development and Docker
 if __name__ == "__main__":
-    demo.launch(theme=gr.themes.Soft())
+    demo.launch(
+        theme=gr.themes.Soft(),
+        server_name="0.0.0.0",  # Allow external connections (required for Docker)
+        server_port=7860
+    )