Add TUNet

Nobody has claimed this yet.

# 🌟 New model addition

The TUNet model for audio superresolution

## Model description

[TUNet: A Block-online Bandwidth Extension Model based on Transformers and Self-supervised Pretraining](https://arxiv.org/abs/2110.13492v3) is a paper by Viet-Anh Nguyen, Anh H. T. Nguyen, and Andy W. H. Khong, introducing a model for audio superresolution based on transformers.

Audio superresolution allows for the upsampling of audio with minimal loss of quality. This is very useful for ASR tasks that require audio to be resampled during preprocessing, which has a big impact on transcriptions depending on the native sample rate.

## Open source status

* [x] the model implementation is available: [The official repo](https://github.com/NXTProduct/TUNet)
* [x] the model weights are available: [ONNX weights](https://github.com/NXTProduct/TUNet/tree/master/lightning_logs)
* [x] who are the authors: Viet-Anh Nguyen, Anh H. T. Nguyen, and Andy W. H. Khong

Start by reading the TUNet paper and the official TUNet repository linked in the issue, including its available ONNX weights. Compare the model and weights with existing Transformers audio model integrations; done means TUNet is implemented and its available weights are integrated and validated for audio superresolution.

Written by the indexing model from the issue text.