jcsilva / deep-clustering Goto Github PK

Hi Eduardo,

What are your plans for this code? It is described as unfinished and has not been updated lately.

I am interested in working on this, and even more interested in code for this subsequent paper that extends the technique to get much better results.

https://arxiv.org/abs/1607.02173

File "/home/janhavi/Documents/Deep_Clustering/keras_code/deep-clustering-master/feats.py", line 186, in
x, y = next(get_egs('train.txt', batch_size=50))
File "/home/janhavi/Documents/Deep_Clustering/keras_code/deep-clustering-master/feats.py", line 139, in get_egs
X = get_logspec(wavsum)
File "/home/janhavi/Documents/Deep_Clustering/keras_code/deep-clustering-master/feats.py", line 137, in get_logspec
return np.log10(np.absolute(stft(sig)) + 1e-7)
File "/home/janhavi/Documents/Deep_Clustering/keras_code/deep-clustering-master/feats.py", line 43, in stft
for i in range(0, len(x)-fftsize, hop)])
ValueError: operands could not be broadcast together with shapes (512,) (512,2)
[Finished in 0.8s with exit code 1]
[shell_cmd: python -u "/home/janhavi/Documents/Deep_Clustering/keras_code/deep-clustering-master/feats.py"]
[dir: /home/janhavi/Documents/Deep_Clustering/keras_code/deep-clustering-master]
[path:/home/janhavi/bin:/home/janhavi/.local/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/cuda-9.1/bin:/snap/bin]
can anyone please help me solve this error

Can this script be used for multi-speaker separation like three to five