[🌟 New Model] ConsistencyTTA: Accelerating Diffusion-Based Text-to-Audio Generation with Consistency Distillation

### Model/Pipeline/Scheduler description

ConsistencyTTA, introduced in the paper [_Accelerating Diffusion-Based Text-to-Audio Generation
with Consistency Distillation_](https://arxiv.org/abs/2309.10740), is an efficient text-to-audio generation model. Compared to a comparable diffusion-based TTA model, ConsistencyTTA achieves a 400x generation speed-up, while retaining the generation quality and diversity.

Due to its high generation quality and fast inference, we believe integrating this model into `diffusers` will make `diffusers` more appealing to text-to-audio generation researchers and users! Thank you very much.

### 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

The open-source code implementation can be found at https://github.com/Bai-YT/ConsistencyTTA.

There is also a simplified implementation for inference only: https://github.com/Bai-YT/ConsistencyTTA/tree/main/easy_inference.

The model checkpoints can be found at https://huggingface.co/Bai-YT/ConsistencyTTA.

I am the main author of the code, and am more than happy to assist the integration.

Start by reading the ConsistencyTTA implementation and its easy_inference version at the linked upstream repository, then inspect the available checkpoints on Hugging Face. Compare the model's inference flow with diffusers' existing audio-generation integrations. Done means ConsistencyTTA is integrated into diffusers with its model implementation and checkpoints usable through the project APIs.

Vom Indexierungsmodell aus dem Issue-Text verfasst.