rookiejunchen / inter-subnet Goto Github PK

I'm trying to retrain your InterSubnet. I have some questions about training datasets.

1. I saw you used interspeech 2020 datasets in your code but the subset of the interspeech 2021 datasets in your paper. Which is correct ?
2. If you use the subset of interspeech 2021 datasets, what kind of dataset did you use? Fullband or Wideband? Only use clean read_speech or do you use emotional speech and non-English speech?
   Thanks

An error happened when i run this code:
ModuleNotFoundError: No module named 'tools.plot_utils'

great job!
But I found that when training the cIRM will using drop_band=2, but the validating will not using drop_band? why?and how to fix this problem?

Thank you for your excellent work,
can you provide your test set?

Thank you for your excellent work，
How to export Pytorch model in ONNX format？thx

First of all, thank you for your work. I would like to ask if it is possible to provide a pre-trained model to test the optimal performance of this algorithm.

MACs: 36.71 G
The computational power is very large. Has the author tried the performance after the computational power optimization？