RookieJunChen / FullSubNet-plus

The official PyTorch implementation of "FullSubNet+: Channel Attention FullSubNet with Complex Spectrograms for Speech Enhancement".
Apache License 2.0
235 stars 55 forks source link

Inference is getting Killed automatically. #20

Open Bhavik-Ardeshna opened 1 year ago

Bhavik-Ardeshna commented 1 year ago

When I tried to do the inference/test on my sample audio (.wav) file it getting killed.

Screenshot from 2023-02-01 22-04-59

My Directory Structure image

Executing Command

python3 -m speech_enhance.tools.inference  / 
       -C config/inference.toml   -M /home/arvik/Desktop/ParadisoAI/FullSubNet-plus/best_model.tar  /
       -I /home/arvik/Desktop/ParadisoAI/FullSubNet-plus/input  / 
       -O /home/arvik/Desktop/ParadisoAI/FullSubNet-plus/output
RookieJunChen commented 1 year ago

Sorry, I have not encountered this situation. Is this "Killed" because your operating system has killed your process?

Bhavik-Ardeshna commented 1 year ago

I guess that would be the reason. My input file structure is right?

Or do I have to use any scaled audio file for inferencing?

RookieJunChen commented 1 year ago

The operation of the input file can be found in this issue. It should not be necessary to use scaled audio file to inference.