Starstruk Logo MarkStarstruk

v3.0

OpenMOSS/MOSS-Audiov3.0Jun 10, 2024by Flux9665

AI Summary

A major milestone release enabling text-to-speech synthesis in over 7000 languages through model extrapolation, alongside improved quality and a new watermarking feature.

Key Highlights

  • Support for over 7000 languages (ISO-639-3)
  • Improved overall TTS quality
  • Watermarking added to prevent misuse
  • Extrapolation from 462 to 7000+ languages

New Features

  • 7000 language support
  • TTS quality improvements
  • Watermarking

Full Release Notes

This release extends the toolkits' functionality and provides new checkpoints.

- We improved the overall TTS quality, with further enhancements already on their way
- Watermarking is added to prevent misuse
- We extend the support for almost all languages in the ISO-639-3 standard (that's over 7000 languages!)
- With a few clever designs, we were able to extrapolate from a pretrained checkpoint using 462 languages to a checkpoint that can speak all languages for which we now support a text frontend!
- Lots of simplifications and quality of life changes.

This is the outcome of a collaboration with colleagues from the University of Groningen and the Fraunhofer IIS in Erlangen. Together with our group from the University of Stuttgart, we have built this model, which is the first of its kind. 

We will present this at the Interspeech 2024, the full list of authors is Florian Lux, Sarina Meyer, Lyonel Behringer, Frank Zalkow, Phat Do, Matt Coler, Emanuël Habets and Thang Vu.

Paper: https://arxiv.org/abs/2406.06403
Dataset: https://huggingface.co/datasets/Flux9665/BibleMMS
Interactive Demo: https://huggingface.co/spaces/Flux9665/MassivelyMultilingualTTS
Static Demo: https://anondemos.github.io/MMDemo/