Spaces:
Sleeping
Sleeping
| #!/usr/bin/env python3 | |
| """ | |
| Madverse Music - Hugging Face Spaces Version | |
| Streamlit app for HF Spaces deployment | |
| """ | |
| import streamlit as st | |
| import torch | |
| import librosa | |
| import tempfile | |
| import os | |
| import time | |
| import numpy as np | |
| # Import the sonics library for model loading | |
| try: | |
| from sonics import HFAudioClassifier | |
| except ImportError: | |
| st.error("Sonics library not found. Please install it first.") | |
| st.stop() | |
| # Global model variable | |
| model = None | |
| # Page configuration | |
| st.set_page_config( | |
| page_title="Madverse Music: AI Music Detector", | |
| page_icon="🎵", | |
| layout="wide", | |
| initial_sidebar_state="expanded" | |
| ) | |
| # Custom CSS | |
| st.markdown(""" | |
| <style> | |
| .main-header { | |
| background: linear-gradient(90deg, #667eea 0%, #764ba2 100%); | |
| padding: 1rem; | |
| border-radius: 10px; | |
| color: white; | |
| text-align: center; | |
| margin-bottom: 2rem; | |
| } | |
| .result-box { | |
| padding: 1rem; | |
| border-radius: 10px; | |
| margin: 1rem 0; | |
| border-left: 5px solid; | |
| } | |
| .real-music { | |
| background-color: #d4edda; | |
| border-left-color: #28a745; | |
| } | |
| .fake-music { | |
| background-color: #f8d7da; | |
| border-left-color: #dc3545; | |
| } | |
| </style> | |
| """, unsafe_allow_html=True) | |
| def load_model(): | |
| """Load the model with caching for HF Spaces""" | |
| try: | |
| with st.spinner("Loading AI model... This may take a moment..."): | |
| # Use the same loading method as the working API | |
| model = HFAudioClassifier.from_pretrained("awsaf49/sonics-spectttra-alpha-120s") | |
| model.eval() | |
| return model | |
| except Exception as e: | |
| st.error(f"Failed to load model: {str(e)}") | |
| return None | |
| def process_audio(audio_file, model): | |
| """Process audio file and return classification""" | |
| try: | |
| # Save uploaded file temporarily | |
| with tempfile.NamedTemporaryFile(delete=False, suffix='.wav') as tmp_file: | |
| tmp_file.write(audio_file.read()) | |
| tmp_path = tmp_file.name | |
| # Load audio (model uses 16kHz sample rate) | |
| audio, sr = librosa.load(tmp_path, sr=16000) | |
| # Convert to tensor and add batch dimension | |
| audio_tensor = torch.FloatTensor(audio).unsqueeze(0) | |
| # Get prediction using the same pattern as working API | |
| with torch.no_grad(): | |
| output = model(audio_tensor) | |
| # Convert logit to probability using sigmoid | |
| probability = torch.sigmoid(output).item() | |
| # Classify: prob < 0.5 = Real, prob >= 0.5 = Fake | |
| if probability < 0.5: | |
| classification = "Real" | |
| confidence = (1 - probability) * 2 # Convert to 0-1 scale | |
| else: | |
| classification = "Fake" | |
| confidence = (probability - 0.5) * 2 # Convert to 0-1 scale | |
| # Calculate duration | |
| duration = len(audio) / sr | |
| # Clean up | |
| os.unlink(tmp_path) | |
| return { | |
| 'classification': classification, | |
| 'confidence': min(confidence, 1.0), # Cap at 1.0 | |
| 'probability': probability, | |
| 'raw_score': output.item(), | |
| 'duration': duration, | |
| 'success': True | |
| } | |
| except Exception as e: | |
| # Clean up on error | |
| if 'tmp_path' in locals(): | |
| try: | |
| os.unlink(tmp_path) | |
| except: | |
| pass | |
| return { | |
| 'success': False, | |
| 'error': str(e) | |
| } | |
| def main(): | |
| # Header | |
| st.markdown(""" | |
| <div class="main-header"> | |
| <h1>Madverse Music: AI Music Detector</h1> | |
| <p>Detect AI-generated music vs human-created music using advanced AI technology</p> | |
| </div> | |
| """, unsafe_allow_html=True) | |
| # Sidebar | |
| with st.sidebar: | |
| st.markdown("### About") | |
| st.markdown(""" | |
| This AI model can detect whether music is: | |
| - **Real**: Human-created music | |
| - **Fake**: AI-generated music (Suno, Udio, etc.) | |
| **Model**: SpecTTTra-α (120s) | |
| **Accuracy**: 97% F1 score | |
| **Max Duration**: 120 seconds | |
| """) | |
| st.markdown("### Supported Formats") | |
| st.markdown("- WAV (.wav)") | |
| st.markdown("- MP3 (.mp3)") | |
| st.markdown("- FLAC (.flac)") | |
| st.markdown("- M4A (.m4a)") | |
| st.markdown("- OGG (.ogg)") | |
| st.markdown("### Links") | |
| st.markdown("- [Madverse Website](https://madverse.co)") | |
| st.markdown("- [GitHub Repository](#)") | |
| # Load model | |
| model = load_model() | |
| if model is None: | |
| st.error("Model failed to load. Please refresh the page.") | |
| return | |
| st.success("AI model loaded successfully!") | |
| # File upload | |
| st.markdown("### Upload Audio File") | |
| uploaded_file = st.file_uploader( | |
| "Choose an audio file", | |
| type=['wav', 'mp3', 'flac', 'm4a', 'ogg'], | |
| help="Upload an audio file to analyze (max 120 seconds)" | |
| ) | |
| if uploaded_file is not None: | |
| # Display file info | |
| st.markdown("### File Information") | |
| col1, col2, col3 = st.columns(3) | |
| with col1: | |
| st.metric("Filename", uploaded_file.name) | |
| with col2: | |
| st.metric("File Size", f"{uploaded_file.size / 1024:.1f} KB") | |
| with col3: | |
| st.metric("Format", uploaded_file.type) | |
| # Audio player | |
| st.markdown("### Preview") | |
| st.audio(uploaded_file) | |
| # Analysis button | |
| if st.button("Analyze Audio", type="primary", use_container_width=True): | |
| try: | |
| with st.spinner("Analyzing audio... This may take a few seconds..."): | |
| # Reset file pointer | |
| uploaded_file.seek(0) | |
| # Process audio | |
| start_time = time.time() | |
| result = process_audio(uploaded_file, model) | |
| processing_time = time.time() - start_time | |
| if not result['success']: | |
| st.error(f"Error processing audio: {result['error']}") | |
| return | |
| # Display results | |
| st.markdown("### Analysis Results") | |
| classification = result['classification'] | |
| confidence = result['confidence'] | |
| # Result box | |
| if classification == "Real": | |
| st.markdown(f""" | |
| <div class="result-box real-music"> | |
| <h3>Result: Human-Created Music</h3> | |
| <p><strong>Classification:</strong> {classification}</p> | |
| <p><strong>Confidence:</strong> {confidence:.1%}</p> | |
| <p><strong>Message:</strong> This appears to be human-created music!</p> | |
| </div> | |
| """, unsafe_allow_html=True) | |
| else: | |
| st.markdown(f""" | |
| <div class="result-box fake-music"> | |
| <h3>Result: AI-Generated Music</h3> | |
| <p><strong>Classification:</strong> {classification}</p> | |
| <p><strong>Confidence:</strong> {confidence:.1%}</p> | |
| <p><strong>Message:</strong> This appears to be AI-generated music!</p> | |
| </div> | |
| """, unsafe_allow_html=True) | |
| # Detailed metrics | |
| with st.expander("Detailed Metrics"): | |
| col1, col2, col3 = st.columns(3) | |
| with col1: | |
| st.metric("Confidence", f"{confidence:.1%}") | |
| with col2: | |
| st.metric("Probability", f"{result['probability']:.3f}") | |
| with col3: | |
| st.metric("Processing Time", f"{processing_time:.2f}s") | |
| if result['duration'] > 0: | |
| st.metric("Duration", f"{result['duration']:.1f}s") | |
| st.markdown("**Interpretation:**") | |
| st.markdown(""" | |
| - **Probability < 0.5**: Classified as Real (human-created) | |
| - **Probability ≥ 0.5**: Classified as Fake (AI-generated) | |
| - **Confidence**: How certain the model is about its prediction | |
| """) | |
| except Exception as e: | |
| st.error(f"Error processing audio: {str(e)}") | |
| # Footer | |
| st.markdown("---") | |
| st.markdown(""" | |
| <div style="text-align: center; color: #666;"> | |
| <p>Powered by <strong>Madverse Music</strong> | Built with Streamlit & PyTorch</p> | |
| <p>This tool is for research and educational purposes. Results may vary depending on audio quality.</p> | |
| </div> | |
| """, unsafe_allow_html=True) | |
| if __name__ == "__main__": | |
| main() |