π ClearerVoice-Studio New Feature: Speech Super-Resolution with MossFormer2 ! π Weβre excited to announce that ClearerVoice-Studio now supports speech super-resolution, powered by our latest MossFormer2-based model! Whatβs New?
π Convert Low-Resolution to High-Resolution Audio: Transform low-resolution audio (effective sampling rate β₯ 16 kHz) into crystal-clear, high-resolution audio at 48 kHz.
π€ Cutting-Edge Technology: Leverages the MossFormer2 model plus HiFi-GAN, optimised for generating high-quality audio with enhanced perceptual clarity.
π§ Enhanced Listening Experience: Perfect for speech enhancement, content restoration, and high-fidelity audio applications.
π Try It Out! Upgrade to the latest version of ClearerVoice-Studio (https://github.com/modelscope/ClearerVoice-Studio) to experience this powerful feature. Check out the updated documentation and examples in our repository.
Let us know your thoughts, feedback, or feature requests in the Issues section.