This Streamlit web application provides a user-friendly interface for high-quality audio noise reduction powered by the DeepFilterNet framework.
- Simple Audio Upload: Drag and drop your audio files (WAV, MP3, M4A, FLAC, OGG) or video files (MOV) directly into the web app.
- Audio Playback: Preview both the original audio and the cleaned version.
- Spectrogram Visualizations: Compare the before and after spectrograms to visually understand the noise reduction process.
- Powered by DeepFilterNet: Leverages the robust deep learning capabilities of DeepFilterNet for superior results.
- Download Support: Download the cleaned audio (WAV) or video (MP4) with enhanced audio.
- Upload your audio file.
- Preview the original audio.
- Click the 'Clean Audio' button.
- Listen to the enhanced audio.
- Compare spectrograms for a deeper look at the results.
Ensure you have the following prerequisites:
- Python >= 3.9
- Streamlit
- PyTorch
- DeepFilterNet
Simply run:
./run.sh
This will:
- Check for required dependencies
- Create a virtual environment
- Install all necessary packages
- Start the application
If you prefer to install manually:
git clone https://github.com/chuck1z/AudioCleaner
cd AudioCleaner
pip install -r requirements.txt
streamlit run main.py
DeepFilterNet is an advanced deep learning framework for real-time speech enhancement. To learn more about this powerful tool, visit the GitHub repository: https://github.com/Rikorose/DeepFilterNet
Feel free to submit issues or feature requests on this project's GitHub repository. Contributions are welcome!