Regarding the reconstruction of some models using keras3 code.

[rezzsl]

Describe your question

Hi, I'm currently using the keras3 framework to rebuild some speech separation models, but it's difficult for me because some features are used differently. I would like to ask the ESPnet team if there is any way they can help me get this done quickly? Thank you so much.

[sw005320]

We have some experience on using espnet models in the other framework, e.g., PyTorch Lightning. We're preparing some examples (but not very soon).