Unisound / SpeechSeparation

Unisound/SpeechSeparation Issues

ValueError: Cannot feed value of shape (1, 0, 257) for Tensor 'speech_mix_batch_inputs:0', which has shape '(1, 256, 257)'
Updated 6 years ago1
Do you need to normalize the spectrum of the input and target?
Updated 6 years ago1
How to run the project?
Updated 6 years ago
添加 loss 和 audio 到 tensorboard summary
Updated 7 years ago
Support Multiple GPUs
Updated 7 years ago2