search

deezer / spleeter

Deezer source separation library including pretrained models.
https://research.deezer.com/projects/spleeter.html
MIT License
25.59k stars 2.8k forks source link

Why is the audio unchanged after separation? #891

Open Niche180 opened 7 months ago

Niche180 commented 7 months ago

Run successfully： INFO:spleeter:File audio_output/Split_1/vocals.wav written succesfully INFO:spleeter:File audio_output/Split_1/accompaniment.wav written succesfully

but vocals.wav and accompaniment.wav are the same as original audio, no change

qwert1887 commented 7 months ago

me too. and i found the spectrum of vocals.wav and original audio are the same except the volume lower. i wonder waht's the problem.

GORECKIPL commented 7 months ago

same and problem with lenght of file

billyilly commented 4 months ago

vocals.wav and accompaniment.wav are the same as original audio, no change

billyilly commented 4 months ago

vocals.wav and accompaniment.wav are the same as original audio, no change!!! why??

Test-Jim commented 4 months ago

命令在cmd里执行有变化的，但是把命令放在os.popen里执行，两个文件没有变化。 请问现在有解决方案了吗？

m-d-nabeel commented 1 month ago

I had the same issue where vocals.wav and accompaniment.wav were unchanged. I found the pretrained_models/2stems folder was empty. Deleting that folder and rerunning the process fixed it.