Overview of the Amphion Toolkit (v0.2)

TL;DR

Amphion v0.2 is an open-source toolkit that simplifies audio, music, and speech generation tasks by providing diverse models, a large multilingual dataset, and comprehensive tutorials for researchers and engineers.

Contribution

This paper introduces Amphion v0.2, featuring a large multilingual dataset, new models, and tutorials, enhancing accessibility and usability for audio generation research.

Findings

100K-hour multilingual dataset available

New models for TTS, audio coding, and voice conversion

Comprehensive tutorials for user guidance

Abstract

Amphion is an open-source toolkit for Audio, Music, and Speech Generation, designed to lower the entry barrier for junior researchers and engineers in these fields. It provides a versatile framework that supports a variety of generation tasks and models. In this report, we introduce Amphion v0.2, the second major release developed in 2024. This release features a 100K-hour open-source multilingual dataset, a robust data preparation pipeline, and novel models for tasks such as text-to-speech, audio coding, and voice conversion. Furthermore, the report includes multiple tutorials that guide users through the functionalities and usage of the newly released models.