search

GauravWaghmare / Speaker-Identification

A program for automatic speaker identification using deep learning techniques.
84 stars 26 forks source link

regarding dataset #2

Open abhishekkritarth opened 6 years ago

abhishekkritarth commented 6 years ago

Hi @GauravWaghmare,

I have gone through your code.I didn't find the data which is required to run this code. Can you please send me the links of Data-set or at-least please specify the format of sample Data-set applicable for this code.

Thanks and Regards

GauravWaghmare commented 6 years ago

Unfortunately, we don't have the dataset with us. The structure of the training data is

TrainRoot | _ User1

It can be any number of wav files in a directory, and any number of users. You can configure that in the code.

abhishekkritarth commented 6 years ago

while running the code by giving sample .wav files, I am getting the following error. Can you please give me any suggestion to resolve this,

Speaker No. = 1 /home/mcis-lap-23/PycharmProjects/Text2Speech/Speaker-Identification-master/data/1/ ('fname :', '/home/mcis-lap-23/PycharmProjects/Text2Speech/Speaker-Identification-master/data/1/a0053.wav') 512.0 single column Traceback (most recent call last): File "/home/mcis-lap-23/PycharmProjects/Text2Speech/Speaker-Identification-master/runMode_1.py", line 216, in tot_positives = t.test(testdirec) File "/home/mcis-lap-23/PycharmProjects/Text2Speech/Speaker-Identification-master/runMode_1.py", line 151, in test pca = self.train() File "/home/mcis-lap-23/PycharmProjects/Text2Speech/Speaker-Identification-master/runMode_1.py", line 123, in train train_data = self.featuresObj.load_data() File "/home/mcis-lap-23/PycharmProjects/Text2Speech/Speaker-Identification-master/runMode_1.py", line 80, in load_data X, Y = self.getTrainingMatrix() File "/home/mcis-lap-23/PycharmProjects/Text2Speech/Speaker-Identification-master/runMode_1.py", line 41, in getTrainingMatrix featuresT = self.getFeaturesFromWave(fname) File "/home/mcis-lap-23/PycharmProjects/Text2Speech/Speaker-Identification-master/runMode_1.py", line 68, in getFeaturesFromWave segmentLimits = rs.silenceRemoval(signal, fs, self.frame_size, self.frame_shift) File "/home/mcis-lap-23/PycharmProjects/Text2Speech/Speaker-Identification-master/Removesilence.py", line 159, in silenceRemoval SVM = trainSVM(featuresNormSS, 1.0) # train the respective SVM probabilistic model (ONSET vs SILENCE) File "/home/mcis-lap-23/PycharmProjects/Text2Speech/Speaker-Identification-master/Removesilence.py", line 70, in trainSVM svmm = mlpy.LibSvm(svm_type='c_svc', kernel_type='linear', eps=0.0000001, C=Cparam, probability=True) AttributeError: 'module' object has no attribute 'LibSvm'

dalmam11 commented 6 years ago

same error with abhishekkritarth

joony0123 commented 6 years ago

I had that one too but I was able to fix it by downloading mlpy 3.4 version using setup.py after downloading from SourceForge on Linux. For some reason pip install mlpy is not compatible with the code's mlpy

Aurora11111 commented 5 years ago

@GauravWaghmare how to set the epoch when I trianing about 300 speaker,and how much speech per person need?