iKala is amplifying my results to the point of distortion

MTG / DeepConvSep

Deep Convolutional Neural Networks for Musical Source Separation

GNU Affero General Public License v3.0

472 stars 110 forks source link

iKala is amplifying my results to the point of distortion #23

Closed ghost closed 6 years ago

ghost commented 6 years ago

Hello. I'm running the iKala script on recordings and I like the results: However, it is amplifying my results considerably when they're done processing! They clip very bad. I've tried to normalize to -4 dB via Audacity prior to processing and that doesn't fix it... It also complains about Theano but seems to work regradless.

iGerman00 commented 6 years ago

Experiencing the same issue. Any solutions?

nkundiushuti commented 6 years ago

You can divide the audio_out by it's maximum audio_out = audio_out / audio_out.amax() audio_out2 = audio_out2 / audio_out2.amax()