search

ppwwyyxx / speaker-recognition

A Speaker Recognition System
Apache License 2.0
675 stars 276 forks source link

Segmentation fault (core dumped) and creating core.13071 file instent of model.out #76

Closed gitrohini closed 5 years ago

gitrohini commented 5 years ago

[root@aio src]# ./speaker-recognition.py -t enroll -i "./train4/" -m model3.out Label train4 has files ./train4/tone-8Khz.wav /root/anaconda2/lib/python2.7/site-packages/scipy/fftpack/basic.py:160: FutureWarning: Using a non-tuple sequence for multidimensional indexing is deprecated; use arr[tuple(seq)] instead of arr[seq]. In the future this will be interpreted as an array index, arr[np.array(seq)], which will result either in an error or a different result. z[index] = x m: <gui.interface.ModelInterface object at 0x7ff30d726050> output_model: model3.out Now speaker-recognition.py/before m.train() Start training...

nr_instance : 499 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 found that fault is in gmm/src/pygmm.cc file in train_model()? why and how to remove it Any suggestion.... and please give me sample input file set and what should be output for that ??

ppwwyyxx commented 5 years ago

Now the C++ implementation of GMM will not be used and segfault should not happen again.