paths = sorted([
str(path) for path in pathlib.Path(args.dataset).glob('wav48/*/*.wav')])
preprocess = Preprocess(
sr=16000, n_fft=1024, hop_length=256, n_mels=128, top_db=20,
length=args.length, quantize=args.a_channels)
dataset = chainer.datasets.TransformDataset(paths, preprocess)
train, valid = chainer.datasets.split_dataset_random(
dataset, int(len(dataset) * 0.9), args.seed)
# Networks
encoder = UpsampleNet(args.n_loop * args.n_layer, args.r_channels)
decoder = WaveNet(
args.n_loop, args.n_layer,
args.a_channels, args.r_channels, args.s_channels,
args.use_embed_tanh)
model = chainer.links.Classifier(EncoderDecoderModel(encoder, decoder))
# Optimizer
optimizer = chainer.optimizers.Adam(1e-4)
optimizer.setup(model)
# Iterators
train_iter = chainer.iterators.MultiprocessIterator(
train, args.batchsize,
n_processes=args.process, n_prefetch=args.prefetch)
valid_iter = chainer.iterators.MultiprocessIterator(
valid, args.batchsize, repeat=False, shuffle=False,
n_processes=args.process, n_prefetch=args.prefetch)
# Updater and Trainer
updater = chainer.training.StandardUpdater(
decoder = WaveNet(params.n_loop, params.n_layer, params.filter_size,
params.residual_channels, params.dilated_channels,
params.skip_channels, params.output_dim, params.quantize,
params.log_scale_min, params.condition_dim,
params.dropout_zero_rate)
if params.distribution_type == 'gaussian':
loss_fun = decoder.calculate_gaussian_loss
acc_fun = None
elif params.distribution_type == 'logistic':
loss_fun = decoder.calculate_logistic_loss
acc_fun = None
elif params.distribution_type == 'softmax':
loss_fun = chainer.functions.softmax_cross_entropy
acc_fun = chainer.functions.accuracy
model = EncoderDecoderModel(encoder, decoder, loss_fun, acc_fun)
# Optimizer
optimizer = chainer.optimizers.Adam(params.lr / len(args.gpus))
optimizer.setup(model)
optimizer.add_hook(chainer.optimizer.GradientClipping(10))
# Iterator
if args.process * args.prefetch > 1:
train_iter = chainer.iterators.MultiprocessIterator(
train,
params.batchsize,
n_processes=args.process,
n_prefetch=args.prefetch)
valid_iter = chainer.iterators.MultiprocessIterator(
valid,