DigitalPhonetics/IMS-Toucan
A PyTorch-based Text-to-Speech toolkit for training and running massively multilingual speech synthesis models supporting over 7000 languages.
Not currently ranked — collecting fresh signals.
star history
IMS-Toucan is a toolkit developed at the University of Stuttgart for training and deploying state-of-the-art Text-to-Speech systems. It is built on PyTorch and deep learning techniques to provide controllable and computationally efficient speech synthesis. The project includes the ToucanTTS system with a Hugging Face demo space and a companion multilingual dataset (BibleMMS) covering thousands of languages.
Frequently asked
- What is DigitalPhonetics/IMS-Toucan?
- A PyTorch-based Text-to-Speech toolkit for training and running massively multilingual speech synthesis models supporting over 7000 languages.
- Is IMS-Toucan open source?
- Yes — DigitalPhonetics/IMS-Toucan is open source, released under the Apache-2.0 license.
- What language is IMS-Toucan written in?
- DigitalPhonetics/IMS-Toucan is primarily written in Python.
- How popular is IMS-Toucan?
- DigitalPhonetics/IMS-Toucan has 2.2k stars on GitHub.
- Where can I find IMS-Toucan?
- DigitalPhonetics/IMS-Toucan is on GitHub at https://github.com/DigitalPhonetics/IMS-Toucan.