Starstruk Logo MarkStarstruk

v3.1

hexgrad/kokorov3.1Jul 25, 2024by Flux9665

AI Summary

Enhances the 7000-language TTS model with stochastic prosody prediction, expanded IPA modifier support, and an overhauled language similarity prediction module.

Key Highlights

  • Stochastic prosody prediction for pitch, energy, and durations.
  • Added support for more IPA modifiers to cover more languages.
  • More languages added to the pretraining.
  • Overhauled language similarity prediction modules and visualization.

New Features

  • Stochastic prosody prediction.
  • Expanded IPA modifier support.
  • Language pretraining updates.

Full Release Notes

## What's Changed

This release provides new checkpoints and improves some aspects of the previous release that were not included due to time constraints.  For more information on the universal TTS model for 7000 languages, please refer to the previous release v3.0

- Prosody prediction in terms of pitch, energy and durations are now stochastic and sample from a distribution instead of assuming a one-to-one mapping. 
- Added support for more IPA modifiers to cover more languages
- Added more languages into the pretraining 
- Overhauled language similarity prediction modules and visualization

**Full Changelog**: https://github.com/DigitalPhonetics/IMS-Toucan/compare/v3.0...v3.1