Joel Mathew Thomas
0ff6a12829
- Normalize audio to the range [-1, 1] - Trim silence from audio - Add test cases for both functions
freq-split-enhance
An open-source audio processing framework that splits audio into frequency components using spectrogram analysis, allowing users to enhance selected components with deep learning techniques. Ideal for tasks in music processing, speech enhancement, and noise reduction. Fully built with open-source tools for flexibility and extensibility.