search

ppwwyyxx / speaker-recognition

A Speaker Recognition System
Apache License 2.0
675 stars 274 forks source link

Segmentation Fault : 11, while running enroll on OSX #6

Closed sanjayshreedharan closed 7 years ago

sanjayshreedharan commented 8 years ago

Running the following command python speaker-recognition.py -t enroll -i "./ ./sanjay" -m model.out gives the following output.

Start training...
nr_instance   :   94
nr_dim        :   28
nr_mixture    :   32
min_covar     :   0.001000
threshold     :   0.010000
nr_iteration  :   200
init_with_kmeans: 0
concurrency   :   4
verbosity     :   0
Segmentation fault: 11

The program closes saying Segmentation fault : 11. Can you please help me with it?

ppwwyyxx commented 8 years ago

The problems seem to be in fast-gmm. @zxytim may have a better idea on what's happening. Meanwhile, you may choose not to compile the gmm code, then GMM from sklearn will be used instead.

sanjayshreedharan commented 8 years ago

I figured that out and used the gmm sklearn. Is there a way to do continuous speaker recognition in command line ? And not GUI?

ppwwyyxx commented 8 years ago

Unfortunately there isn't.

stanleyguan commented 7 years ago

This doesn't seem to be resolved yet. I ran into the same probelm on macOS. I'm currently falling back to the GMM implementation in sklearn. But it's nice to have the C implementation if that's faster.

gitrohini commented 6 years ago

nr_instance : 1030 nr_dim : 28 nr_mixture : 32 min_covar : 0.001000 threshold : 0.010000 nr_iteration : 200 init_with_kmeans: 0 concurrency : 4 verbosity : 0 Segmentation fault (core dumped) I have also same problem ? can anyone help me for resolve it?

gitrohini commented 6 years ago

Is there any installation problem ??