Add Hugging Face authentication and update server port

- Implemented environment variable loading with dotenv for Hugging Face token.
- Added Hugging Face authentication logic in app.py with error handling.
- Updated README with setup instructions for Hugging Face authentication.
- Changed server port from 7860 to 8080 in app.py.
- Added huggingface_hub and python-dotenv to requirements.txt.

Dockerfile

@@ -10,6 +10,8 @@ ENV PYTHONUNBUFFERED=1
 ENV GRADIO_SERVER_NAME=0.0.0.0
 ENV GRADIO_SERVER_PORT=7860
 ENV HF_HOME=/tmp/.cache/huggingface
+# Optional: Set HF_TOKEN for Hugging Face authentication
+# ENV HF_TOKEN=your_token_here
 
 # Install system dependencies for audio processing and ML libraries
 RUN apt-get update && apt-get install -y \

README.md

@@ -21,6 +21,22 @@ An open-source web interface for generating high-quality audio from text prompts
 - 🎧 **Real-time Playback**: Listen to generated audio instantly
 - 📝 **Example Prompts**: Pre-built examples to get you started
 
+## Setup
+
+### Hugging Face Authentication (Recommended)
+
+For the best experience and to avoid rate limits, set up Hugging Face authentication:
+
+1. Create a Hugging Face account at [huggingface.co](https://huggingface.co/join)
+2. Go to [Settings > Access Tokens](https://huggingface.co/settings/tokens) and create a new token
+3. Copy `env-example.txt` to `.env` and add your token:
+   ```
+   HF_TOKEN=hf_your_token_here
+   ```
+4. Install dependencies: `pip install -r requirements.txt`
+
+**Note**: Without authentication, you may experience rate limits or reduced access to some models.
+
 ## Usage
 
 1. Enter a text description of the audio you want to generate

app.py

@@ -3,6 +3,8 @@ import numpy as np
 import torch
 import os
 import warnings
+from dotenv import load_dotenv
+from huggingface_hub import login
 
 # Try to import Stable Audio pipeline
 try:
@@ -21,6 +23,21 @@ except ImportError:
 # Suppress warnings for cleaner output
 warnings.filterwarnings("ignore", category=UserWarning)
 
+# Load environment variables
+load_dotenv()
+
+# Set up Hugging Face authentication
+hf_token = os.getenv("HF_TOKEN")
+if hf_token:
+    try:
+        login(token=hf_token)
+        print("✅ Hugging Face authentication successful")
+    except Exception as e:
+        print(f"⚠️  Hugging Face authentication failed: {e}")
+        print("   Continuing without authentication...")
+else:
+    print("ℹ️  No Hugging Face token found. Some models may have rate limits.")
+
 # Model configuration
 MODEL_ID = "stabilityai/stable-audio-open-small"
 DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
@@ -417,4 +434,4 @@ if __name__ == "__main__":
         print(f"CUDA device: {torch.cuda.get_device_name(0)}")
     
     interface = create_audio_generation_interface()
-    interface.launch(server_name="0.0.0.0", server_port=7860)
+    interface.launch(server_name="0.0.0.0", server_port=8080)

requirements.txt

@@ -5,3 +5,5 @@ diffusers>=0.25.0
 transformers>=4.35.0
 accelerate>=0.25.0
 scipy>=1.7.0
+huggingface_hub>=0.17.0
+python-dotenv>=1.0.0