lucidrains/e2-tts-pytorch
A PyTorch implementation of E2-TTS, a fully non-autoregressive zero-shot text-to-speech model for synthesizing speech from text.
Not currently ranked — collecting fresh signals.
star history
Implements E2-TTS using a multistream transformer architecture for joint text and audio conditioning. The model generates speech non-autoregressively, avoiding the sequential generation bottleneck of traditional TTS systems. It supports zero-shot voice cloning without requiring explicit alignment engineering. The repository includes a duration predictor module and working end-to-end training code.
Frequently asked
- What is lucidrains/e2-tts-pytorch?
- A PyTorch implementation of E2-TTS, a fully non-autoregressive zero-shot text-to-speech model for synthesizing speech from text.
- Is e2-tts-pytorch open source?
- Yes — lucidrains/e2-tts-pytorch is open source, released under the MIT license.
- What language is e2-tts-pytorch written in?
- lucidrains/e2-tts-pytorch is primarily written in Python.
- How popular is e2-tts-pytorch?
- lucidrains/e2-tts-pytorch has 516 stars on GitHub.
- Where can I find e2-tts-pytorch?
- lucidrains/e2-tts-pytorch is on GitHub at https://github.com/lucidrains/e2-tts-pytorch.