modelscope/ClearerVoice-Studio
An open-source speech processing toolkit providing deep learning models for enhancement, separation, super-resolution, and target speaker extraction.

Velocity · 7d
+7.4
★ / day
Trend
→steady
star history
ClearerVoice-Studio is an AI-powered speech processing toolkit built on PyTorch that offers state-of-the-art pre-trained models for tasks including speech enhancement, speaker separation, speech super-resolution, and target speaker extraction. It provides training and inference scripts along with a pip-installable package for easy model access.