It's possible to finetune with Chinese voice database?

[urn333]

Due diligence

• I have done my due diligence in trying to find the answer myself.

Topic

The paper

Question

I'm working on a humanoid robot project and looking into real-time speech models. I have a dataset of Chinese *.wav files, each with a corresponding JSON file. Would this be sufficient to fine-tune a model, Can Mandarin be used during inference?