1 repo
Mechanisms that map linguistic features to speaker-specific voice embeddings.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Cross-Modal Alignment Models. Refine with filters or upvote what's useful.
GPT-SoVITS is a text-to-speech synthesis engine and voice cloning toolkit designed for generating natural-sounding human speech. It functions as a neural audio processing pipeline that maps input text to high-fidelity audio waveforms, utilizing conditional variational autoencoders and flow-based decoders to ensure expr