Add TransformerVC & VITSVC implementation

[ArkhamImp]

✨ Description

VC implementations with Transformer and VITS model architectures. Samples refer to the previous PR: https://github.com/open-mmlab/Amphion/pull/90

👨‍💻 Changes Proposed

• [x] Add Hubert token as input
• [x] Add speaker embedding as condition for zero-shot VC

🧑‍🤝‍🧑 Who Can Review?

@lmxue @RMSnow

✅ 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)

[RMSnow]

Hi @ArkhamImp, Haorui @HarryHe11 and I are also developing the zero-shot VC/SVC. We will leave this PR to review when we find a unified way to integrate all our code including yours!