Starstruk Logo MarkStarstruk

v3.1

trycompai/compv3.1Jul 25, 2024by Flux9665

AI Summary

Improves the TTS model for 7000 languages by making prosody prediction stochastic and expanding support for IPA modifiers and language pretraining data.

Key Highlights

  • Stochastic prosody prediction (pitch, energy, and durations)
  • Added support for more IPA modifiers
  • Added more languages to the pretraining data
  • Overhauled language similarity prediction modules

New Features

  • Stochastic prosody sampling
  • Extended IPA modifier support
  • Expanded multilingual pretraining

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