type=int,
default=5,
help='Number of hidden layers')
parser.add_argument('--learning_rate',
type=float,
default=0.001,
help='learning rate')
parser.add_argument('--stopping_loss',
type=float,
default=0.1,
help='loss at which training stops')
FLAGS, unparsed = parser.parse_known_args()
SAMPLE_RATE = 24000
inputs, targets = make_batch('assets/SMvocals.wav')
num_time_samples = inputs.shape[1]
num_channels = 1
gpu_fraction = 1
model = Model(num_time_samples=num_time_samples,
num_channels=num_channels,
gpu_fraction=gpu_fraction,
num_layers=FLAGS.num_layers or 5,
learning_rate=FLAGS.learning_rate,
stopping_loss=FLAGS.stopping_loss)
tic = time()
model.train(inputs, targets)
toc = time()
from time import time
from wavenet.utils import make_batch
from wavenet.models import Model, Generator
from IPython.display import Audio
#get_ipython().magic(u'matplotlib inline')
# In[ ]:
inputs, targets = make_batch('assets/voice.wav')
num_time_samples = inputs.shape[1]
num_channels = 1
gpu_fraction = 1.0
model = Model(num_time_samples=num_time_samples,
num_channels=num_channels,
gpu_fraction=gpu_fraction)
Audio(inputs.reshape(inputs.shape[1]), rate=44100)
# In[ ]:
tic = time()
from time import time
from wavenet.utils import make_batch
from wavenet.models import Model, Generator
num_channels = 1
gpu_fraction = 1.0
num_classes = 2048
inputs, targets = make_batch('assets/voice.wav', num_classes)
num_time_samples = inputs.shape[1]
print inputs.shape, targets.shape, num_time_samples
model = Model( #num_time_samples=num_time_samples,
num_channels=num_channels,
gpu_fraction=gpu_fraction,
num_classes=num_classes,
prob_model_type='softmax')
tic = time()
model.train(inputs, targets)
toc = time()
print('Training took {} seconds.'.format(toc - tic))
model = Model(num_time_samples=num_time_samples,
num_channels=num_channels,
gpu_fraction=gpu_fraction,
num_classes=num_classes,
num_blocks=num_blocks,
num_layers=num_layers,
num_hidden=num_hidden)
inputlist = []
targetlist = []
for w in WavList:
path = 'assets/' + w + '.wav'
inputs, targets = make_batch(path, sample_rate, duration=duration)
inputlist.append(inputs)
targetlist.append(targets)
inputlist = np.stack(inputlist)
targetlist = np.stack(targetlist)
print(inputlist.shape, targetlist.shape)
train_step, losses = model.train(
inputlist.reshape((inputlist.shape[0], inputlist.shape[2], 1)),
targetlist.reshape((targetlist.shape[0], -1)))
generator = Generator(model)
new_pred = generator.run([[np.random.randn()]], num_time_samples * 2)