Joel Mathew Thomas
dc81f36d74
- Implemented test case to verify audio classification with YAMNet - Used 'cafe_crowd_talk.wav' as test file, expecting 'Speech' as the output class
freq-split-enhance
An advanced audio processing pipeline designed to separate and enhance audio components using cutting-edge open-source tools. With freq-split-enhance, you can isolate vocals, instruments, background noise, and more from raw audio files with precision.
🚀 Key Features
- Source Separation: Leverages tools like Demucs, Spleeter, and nussl for powerful audio separation.
- Noise Reduction: Advanced filtering with noise reduction libraries like
noisereduce. - Spectrogram Analysis: Generate and refine audio using spectrogram-based techniques.
- Fully Modular Pipeline: Flexible structure to integrate and customize various audio processing tools.
- Python-First: Written in Python with easy-to-read modular code.
📖 Documentation
📝 Wiki
For detailed instructions on installing dependencies, setting up Python environments, and configuring the project, visit the Wiki.
🛡️ License
This project is licensed under the Apache License 2.0.