F5-TTS

Loading the README

1. 1.1.222026-07-23fix: allocate fix_duration across chunks to avoid N× duration blow-up
2. 1.1.212026-07-05update gradio>=6.15.0 in pyproject.toml
3. 1.1.202026-04-20fix: refactor cache handling in DiT, MMDiT, and UNetT classes (lazyinit to avoid EMA deepcopy failure while training)
4. 1.1.192026-04-16reuse resamplers and cache vocos MelSpectrogram instances
5. 1.1.182026-03-24Add Arabic model details to SHARED.md

• ElevenLabsVoice cloning from a short reference clip, with a Gradio app.Partial