###################
# Create datasets #
###################
# TODO replace with Kaldi
data_dir = '/home/vano/wrkdir/datasets/LibriSpeech'
# data_dir = '/home/vano/wrkdir/projects_data/sre_2019/toy_dataset'
train = LibriSpeechDataset(data_dir, training_set, n_seconds, pad=pad)
valid = LibriSpeechDataset(data_dir,
validation_set,
n_seconds,
stochastic=False,
pad=pad)
batch_preprocessor = BatchPreProcessor('siamese',
preprocess_instances(downsampling))
train_generator = (batch_preprocessor(batch)
for batch in train.yield_verification_batches(batchsize))
valid_generator = (batch_preprocessor(batch)
for batch in valid.yield_verification_batches(batchsize))
################
# Define model #
################
encoder = get_baseline_convolutional_encoder(filters,
embedding_dimension,
dropout=dropout)
siamese = build_siamese_net(encoder, (input_length, 1),
distance_metric='uniform_euclidean')
opt = Adam(clipnorm=1.)
siamese.compile(loss='binary_crossentropy',
self.batch_to_index = {
i: self.underlying_indexes[i * batchsize:(i + 1) * batchsize]
for i in range(len(self))
}
def label_preprocessor(num_classes, speaker_id_mapping):
def label_preprocessor_(y):
y = np.array([speaker_id_mapping[i] for i in y[:, 0]])[:, np.newaxis]
return to_categorical(y, num_classes)
return label_preprocessor_
batch_preprocessor = BatchPreProcessor(
'classifier', preprocess_instances(downsampling),
label_preprocessor(train.num_classes(), speaker_id_mapping))
train_generator = BatchedSequence(train, batch_preprocessor, batchsize)
################
# Define model #
################
classifier = get_baseline_convolutional_encoder(filters, embedding_dimension,
(input_length, 1))
# Add output classification layer
classifier.add(Dense(train.num_classes(), activation='softmax'))
opt = Adam(clipnorm=1.)
classifier.compile(loss='categorical_crossentropy',
optimizer=opt,
#################
# Training Loop #
#################
for fragment_length in n_seconds:
print('*' * 23)
print('***** {:.1f} seconds *****'.format(fragment_length))
print('*' * 23)
input_length = int(LIBRISPEECH_SAMPLING_RATE * fragment_length / downsampling)
# Create datasets
train = LibriSpeechDataset(training_set, fragment_length, pad=True)
valid = LibriSpeechDataset(validation_set, fragment_length, stochastic=False, pad=True)
batch_preprocessor = BatchPreProcessor('siamese', preprocess_instances(downsampling))
train_generator = (batch_preprocessor(batch) for batch in train.yield_verification_batches(batchsize))
valid_generator = (batch_preprocessor(batch) for batch in valid.yield_verification_batches(batchsize))
for repeat in range(n_repeats):
# Define model
encoder = get_baseline_convolutional_encoder(model_n_filters, model_embedding_dimension, dropout=model_dropout)
siamese = build_siamese_net(encoder, (input_length, 1), distance_metric='uniform_euclidean')
opt = Adam(clipnorm=1.)
siamese.compile(loss='binary_crossentropy', optimizer=opt, metrics=['accuracy'])
# Train
param_str = 'siamese__nseconds_{}__filters_{}__embed_{}__drop_{}__r_{}'.format(fragment_length, model_n_filters,
model_embedding_dimension,
model_dropout, repeat)
print(param_str)
def on_epoch_end(self):
# Shuffle the indexes
np.random.shuffle(self.underlying_indexes)
self.batch_to_index = {i: self.underlying_indexes[i * batchsize:(i + 1) * batchsize] for i in range(len(self))}
def label_preprocessor(num_classes, speaker_id_mapping):
def label_preprocessor_(y):
y = np.array([speaker_id_mapping[i] for i in y[:, 0]])[:, np.newaxis]
return to_categorical(y, num_classes)
return label_preprocessor_
batch_preprocessor = BatchPreProcessor('classifier', preprocess_instances(downsampling),
label_preprocessor(train.num_classes(), speaker_id_mapping))
train_generator = BatchedSequence(train, batch_preprocessor, batchsize)
################
# Define model #
################
classifier = get_baseline_convolutional_encoder(filters, embedding_dimension, (input_length, 1))
# Add output classification layer
classifier.add(Dense(train.num_classes(), activation='softmax'))
opt = Adam(clipnorm=1.)
classifier.compile(loss='categorical_crossentropy', optimizer=opt, metrics=['accuracy'])
plot_model(classifier, show_shapes=True, to_file=PATH + '/plots/classifier.png')