Add Tortoise TTS as a pipeline

### Model/Pipeline/Scheduler description

TorToise is a multi-voice text-to-speech system, which describes a way to apply recent advances in the image generative domain to speech synthesis. It would be great to have this model in diffusers.
I would love to contribute this.

### 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/pdf/2305.07243.pdf
Github repo - https://github.com/neonbjb/tortoise-tts

@sanchit-gandhi @Vaibhavs10

Start with the linked Tortoise TTS paper and the neonbjb/tortoise-tts implementation to understand the model and available weights, then compare them with existing Diffusers pipeline integrations. Done means Tortoise TTS is available as a supported pipeline in Diffusers, with its implementation and usage expectations documented.

Vom Indexierungsmodell aus dem Issue-Text verfasst.