def get_embeddings(self):
X_train, y_train, speaker_train_names = load(
get_speaker_pickle(self.get_validation_data_name() +
'_train_mfcc'))
X_test, y_test, speaker_test_names = load(
get_speaker_pickle(self.get_validation_data_name() + '_test_mfcc'))
model = load(get_experiment_nets(self.name))
set_of_embeddings = []
set_of_speakers = []
set_of_num_embeddings = []
train_outputs = self.generate_outputs(X_train, model)
test_outputs = self.generate_outputs(X_test, model)
set_of_times = [np.zeros((len(y_test) + len(y_train)), dtype=int)]
outputs, y_list, s_list = create_data_lists(False, train_outputs,
test_outputs, y_train,
y_test)
embeddings, speakers, number_embeddings = generate_embeddings(
outputs, y_list, len(model))
set_of_embeddings.append(embeddings)
set_of_speakers.append(speakers)
set_of_num_embeddings.append(number_embeddings)
checkpoints = [self.network_file]
return checkpoints, set_of_embeddings, set_of_speakers, set_of_num_embeddings, set_of_times
def train_network(self):
mixture_count = self.config.getint('gmm', 'mixturecount')
X, y, speaker_names = load(
get_speaker_pickle(self.config.get('train', 'pickle') + '_mfcc'))
model = []
for i in range(len(X)):
features = X[i]
gmm = mixture.GaussianMixture(n_components=mixture_count,
covariance_type='diag',
n_init=1)
gmm.fit(features.transpose())
speaker = {'mfccs': features, 'gmm': gmm}
model.append(speaker)
save(model, get_experiment_nets(self.name))
def train_network(self):
# Get settings
n_epochs = self.config.getint('pairwise_kldiv', 'n_epochs')
batch_size = self.config.getint('pairwise_kldiv', 'batch_size')
epoch_batches = self.config.getint('pairwise_kldiv', 'epoch_batches')
train_filename = self.config.get('train', 'pickle')
n_speakers = self.config.getint('train', 'n_speakers')
# Create network, load path to input and output file
network = create_network_n_speakers(n_speakers, self.config)
train_file = get_speaker_pickle(train_filename)
net_file = get_experiment_nets(self.checkpoints[0])
train_network(network=network,
train_file=train_file,
network_file_out=net_file,
data_generator=self.dg,
num_epochs=n_epochs,
batch_size=batch_size,
epoch_batches=epoch_batches)
def get_validation_test_data(self):
if self.dev_mode:
return get_speaker_pickle(self.dev_val_data + "_test")
else:
return get_speaker_pickle(self.val_data + "_test")
def get_validation_test_data(self):
#self.val_data = "speakers_40_clustering_vs_reynolds"
print("validation_test_data ========>" + self.val_data)
return get_speaker_pickle(self.val_data + "_test")
def get_validation_test_data(self):
return get_speaker_pickle(self.val_data + "_test")
def get_validation_train_data(self):
return get_speaker_pickle(self.val_data + "_train")
