hi I am trying to run this model on the Voxceleb dataset. I am mixing the audio and giving a 1-sec speech to the model.
But its been 1000 epochs. 1 epoch runs over 5000 speakers and selects audios randomly. I don't see the results yet . Can you let me know why this is happening?
hi I am trying to run this model on the Voxceleb dataset. I am mixing the audio and giving a 1-sec speech to the model. But its been 1000 epochs. 1 epoch runs over 5000 speakers and selects audios randomly. I don't see the results yet . Can you let me know why this is happening?