Giters

etzinis / sudo_rm_rf

Code for SuDoRm-Rf networks for efficient audio source separation. SuDoRm-Rf stands for SUccessive DOwnsampling and Resampling of Multi-Resolution Features which enables a more efficient way of separating sources from mixtures.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Didn't get the result I wanted.

afterimagex opened this issue · comments

commented

I selected several custom noise files and input them into the network. Then I found that there was no noise reduction effect. I followed the sudormrf_how_to_use.ipynb file. I was curious whether the provided pre training model was only valid in the whamr data set.

commented

No it is not - it should be able to provide noise reduction with ohter files. Try to make sure you sample at 8kHz, normalize your input.