F5-TTS Integration

### Model/Pipeline/Scheduler description

F5-TTS is a fully non-autoregressive text-to-speech system based on flow matching with Diffusion Transformer (DiT).
It has excellent voice cloning capabilities, and audio generation is of quite high quality.

### Open source status

- [X] The model implementation is available.
- [X] The model weights are available (Only relevant if addition is not a scheduler).

### Provide useful links for the implementation

Paper - https://arxiv.org/abs/2410.06885
Code - https://github.com/SWivid/F5-TTS?tab=readme-ov-file
Weights - https://huggingface.co/SWivid/F5-TTS

Author - @SWivid

Start by reading the F5-TTS paper and the linked SWivid/F5-TTS implementation, then inspect the model weights on Hugging Face. Compare the existing diffusers architecture for audio generation with F5-TTS to determine the integration points. Done means F5-TTS is supported in diffusers, but the issue does not define specific files, tests, or acceptance criteria.

Scritto dal modello di indicizzazione a partire dal testo della issue.