Does the official script of fish-speech 1.5 support batch_size > 1 during the inference stage?

[Ht-zhang-xianyu]

Hi,
I followed the guide from fish-speech/docs/zh/inference.md to run inference using the official model. However, I'm wondering if the inference script supports batch_size > 1 during the inference stage. If so, what changes should I make to the inference code?
Thank you!