Why is the audio unchanged after separation?

[Niche180]

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]

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]

same and problem with lenght of file

[billyilly]

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

[billyilly]

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

[Test-Jim]

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]

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.

[eehoeskrap]

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.

I deleted the folder and ran the code again and it was fixed.
Thank you.

[lym0302]

This is because the model is not downloaded properly. You need to have the decompressed model file https://github.com/deezer/spleeter/releases/download/v1.4.0/2stems.tar.gz under pretrained_models/2stems/