Amphion is an open-source toolkit designed to support research and development in audio, music and speech generation. According to the project’s GitHub site, it offers unique visualizations of classic models and architectures to help junior researchers and engineers better understand them.
The toolkit supports various individual generation tasks such as text-to-speech (TTS), singing voice synthesis (SVS), voice conversion (VC), singing voice conversion (SVC), text-to-audio (TTA), and text-to-music (TTM). It also includes several vocoders for high-quality audio production and evaluation metrics to ensure consistent measurements across generation tasks. Amphion aims to advance audio generation in real-world applications, including building large-scale datasets like Emilia for speech synthesis.
Source: Hacker News