using hamming window for onnx inference

[jie-chen]

Hi, I notice hamming window is used instead of the default povey in onnx inference demo https://github.com/wenet-e2e/wespeaker/blob/master/wespeaker/bin/infer_onnx.py#L47 . May I know the reason for using this? Are all models trained using hamming window? What are the benefits compared with the default povey window?

[JiJiJiang]

We did not compare the results between hamming window and the default povey window.
Models are trained using hamming window, so we use the same during inference.