Add UniCATS implementation

[cyysky2]

✨ Description

The PR adds the UniCATS into the Amphion toolkit.

UniCATS: A Unified Context-Aware Text-to-Speech Framework with Contextual VQ-Diffusion and Vocoding, which is capable of both speech continuation and editing.

• UniCATS repo: https://github.com/cpdu/unicats

• UniCATS paper: https://arxiv.org/abs/2306.07547

• UniCATS demo page: https://cpdu.github.io/unicats/

The PR is the Final project for AIR6063. This is a solo project by 王洋珺 (Wang Yangjun), ID: 119010315

👨‍💻 Changes Proposed

• [x] Add UniCATS/CTXtxt2vec and UniCATS/CTXvec2wav in models/
• [x] Add UniCATS manual and run script in egs/tts
• [x] Add utils and configuration for the two UniCATS projects

🧑‍🤝‍🧑 Who Can Review?

@zhizhengwu @Adorable-Qin @HeCheng0625

🛠 TODO

• [ ] Finish training the CTXtxt2vec model

✅ Checklist

• [ ] Code has been reviewed
• [ ] Code complies with the project's code standards and best practices
• [ ] Code has passed all tests
• [ ] Code does not affect the normal use of existing features
• [ ] Code has been commented properly
• [ ] Documentation has been updated (if applicable)
• [ ] Demo/checkpoint has been attached (if applicable)

[lmxue]

Please format the code using 'black' formatter as described here.

Please provide the final checkpoints and samples.

Additionally, the commit information should be concise.