versatile-audio-upscaler-fixed 0.0.4

Versatile AI-driven audio upscaler to enhance the quality of any audio -- Now supporting Numpy +1.26

Audio Upscaler (AudioSR)

Overview

AudioSR is a powerful tool designed to enhance the fidelity of your audio files, regardless of their type (e.g., music, speech, ambient sounds) or sampling rates. It leverages cutting-edge super-resolution techniques to upscale audio signals, resulting in superior quality output.

Key Features

• Versatility: Works seamlessly with all types of audio content, including music, speech, environmental sounds, and more.
• Scale: Handles audio files of various sampling rates, ensuring compatibility with a wide range of sources.
• High Fidelity: Produces high-quality output with enhanced clarity and detail.
• Ease of Use: Simple and intuitive interface makes it easy to enhance your audio files with just a few clicks.

Acknowledgments

Based on the work of https://github.com/haoheliu/versatile_audio_super_resolution/

@article{liu2023audiosr,
  title={{AudioSR}: Versatile Audio Super-resolution at Scale},
  author={Liu, Haohe and Chen, Ke and Tian, Qiao and Wang, Wenwu and Plumbley, Mark D},
  journal={arXiv preprint arXiv:2309.07314},
  year={2023}
}