magphase
magphase copied to clipboard
run copy_syn error
when I run demo_copy_synthesis_lossless.py or demo_copy_synthesis_low_dim.py or 2_batch_wave_generation.py I always get the following error: A value in x_new is above the interpolation range
Analysing.....................................................
Extracting epochs with REAPER...
Residual symmetry: P:2120.314453 N:1149.693604 MEAN:0.606241
Inverting signal
Synthesising.................................................
Traceback (most recent call last):
File "./demo_copy_synthesis_low_dim.py", line 74, in
and I found that labs_var_rate/ file is always empty, can you give me some help? ^_^
Hi, I am not having any problems. I think that you are using an old version of MagPhase. So, please download the current version from the master branch.
Also, upgrade the required python packages to their latest versions, just in case.
Let me know how it goes. Thanks
Hi Felipe, I hit the same problem. I have absolutely the latest MagPhase from master, and all my packages appear to be up-to-date.
Happy to help look into this. Let me know what I can do.
BTW the lossless synthesis ran without a problem
If I hack around this by editing magphase.py
, it runs to completion with no obvious harm to the synthesized file
- f_intrp_real = interpolate.interp1d(np.arange(ncoeffs_comp), m_real_mel, kind='nearest', fill_value='extrapolate')
- f_intrp_imag = interpolate.interp1d(np.arange(ncoeffs_comp), m_imag_mel, kind='nearest', fill_value='extrapolate')
-
+ f_intrp_real = interpolate.interp1d(np.arange(ncoeffs_comp), m_real_mel, kind='nearest', fill_value=0.0, bounds_error=False)
+ f_intrp_imag = interpolate.interp1d(np.arange(ncoeffs_comp), m_imag_mel, kind='nearest', fill_value=0.0, bounds_error=False)
+
Hi Mike,
I am pretty sure that it is because your SciPy package is not updated. Update it with pip install scipy --upgrade
Let me know how it goes. Thanks
Sorry, that does not fix it (though you are right I did not have the latest version) I tried the same with the other packages and still no luck.
FYI I was able to make this error go away by running on a (different) machine, that was configured for building with Merlin (in particular after running pip install -r requirements.txt
in the merlin
directory, but also other stuff)
But I don't know which package did the trick....
@mikenewman1 , I think it is any of these ones: numpy, scipy, or scikit-learn. Try updating (pip install <package> --ugrade
) each of these.