v2.1
DigitalPhonetics/IMS-Toucanv2.1Mar 1, 2022by Flux9665
AI Summary
Enables multi-language and multi-speaker synthesis with a self-contained aligner and joint modeling of linguistic and speaker features.
Key Highlights
- Self-contained aligner for high-quality durations.
- Joint modeling of speakers and languages.
- Interactive online demo.
New Features
- Self-contained aligner
- Joint speaker/language modeling
- Interactive online demo
Full Release Notes
- self contained aligner to get high quality durations quickly and easily without reliance on external tools or knowledge distillation - modelling speakers and languages jointly but disentangled, so you can use speakers across languages - look at the demo section for an interactive online demo Pretrained FastSpeech2 model that can speak in many languages in any voices, HiFiGAN model and Aligner model are attached to this commit.