def __getitem__(self, index):
(seq, _) = load(self.file_names[index], sr=None, mono=True)
return torch.cat([
torch.LongTensor(self.overlap_len) \
.fill_(utils.q_zero(self.q_levels)),
utils.linear_quantize(
torch.from_numpy(seq), self.q_levels
)
])
def __getitem__(self, index):
file_path, class_label = self.file_names[index]
(seq, _) = load(file_path, sr=self.sample_rate, mono=True)
seq = fix_length(seq, size=self.audio_length, mode='edge')
return torch.cat((
torch.LongTensor([class_label]),
# torch.LongTensor(self.overlap_len)
# .fill_(utils.q_zero(self.q_levels)),
utils.linear_quantize(torch.from_numpy(seq), self.q_levels)))
def __getitem__(self, index):
label = int(self.file_names[index].split("/")
[-2]) # label associated with file_name
(seq, _) = load(self.file_names[index], sr=None, mono=True)
return torch.cat([
torch.LongTensor(self.overlap_len) \
.fill_(utils.q_zero(self.q_levels)),
utils.linear_quantize(
torch.from_numpy(seq), self.q_levels
),
torch.LongTensor([label])
])
def __getitem__(self, index):
seq = self.audio_samples[index]
hsl_data = self.hsl_data_samples[index]
emotion = self.emotion_samples[index]
text = self.text_samples[index]
text = text.decode('utf-8') if isinstance(text, bytes) else text
return torch.cat([
torch.LongTensor(self.overlap_len) \
.fill_(utils.q_zero(self.q_levels)),
utils.linear_quantize(
torch.from_numpy(seq), self.q_levels
)
]), seq, hsl_data, emotion, text
def __getitem__(self, index):
# Try to load using librosa
try:
(seq, _) = load(self.file_names[index], sr=None, mono=True)
except audioread.NoBackendError:
# Use scipy if librosa didn't work
_, seq = scipy.io.wavfile.read(self.file_names[index])
return torch.cat([
torch.LongTensor(self.overlap_len) \
.fill_(utils.q_zero(self.q_levels)),
utils.linear_quantize(
torch.from_numpy(seq), self.q_levels
)
])
dataset_filenames = get_test_data(model, params)
# Gets initial samples form 1 test sample and check if it re-generates it
audio_filename = dataset_filenames[0]
from librosa.core import load
sr = params['sample_rate']
seq, sr = load(audio_filename, sr=sr, mono=True)
print("Sample rate: {}".format(sr))
# Generate Plugin
num_samples = 6 # params['n_samples']
initial_seq_size = 64 * 100 # has to be multiple of rnn.n_frame_samples ???
initial_seq = None
if initial_seq_size > 1:
init = utils.linear_quantize(torch.from_numpy(seq[0:initial_seq_size]), params['q_levels'])
# init = seq[0:initial_seed_size]
init = np.tile(init, (num_samples, 1))
initial_seq = torch.LongTensor(init)
# initial_seed = utils.linear_quantize(initial_seed, params['q_levels'])
sample_length = params['sample_length']
sample_rate = params['sample_rate']
print("Number samples: {}, sample_length: {}, sample_rate: {}".format(num_samples, sample_length, sample_rate))
generator = GeneratorPlugin(GENERATED_PATH, num_samples, sample_length, sample_rate)
# Overloads register function to accept the trained model and the cuda setting
generator.register_generate(model.cuda(), params['cuda'])
# Generate new audio
generator.epoch('Test19_{}'.format(initial_seq_size), initial_seed=initial_seq)
def __call__(self, n_seqs, seq_len, class_label=0, data_seed=None):
# generation doesn't work with CUDNN for some reason
torch.backends.cudnn.enabled = False
label_tensor = torch.LongTensor([class_label])
with torch.no_grad():
self.reset_hidden_states()
# bottom_frame_size = self.model.frame_level_rnns[0].n_frame_samples
bottom_frame_size = 16
sequences = torch.LongTensor(n_seqs, self.model.lookback + seq_len) \
.fill_(utils.q_zero(self.model.q_levels))
if data_seed is not None:
seeds = []
for _ in range(n_seqs):
seeds.append(
utils.linear_quantize(
torch.from_numpy(
data_seed.getClassSplit(
class_num=class_label,
seq_len=self.model.lookback)),
self.model.q_levels))
seed = torch.stack(seeds)
sequences[:, :self.model.lookback] = seed
frame_level_outputs = [None for _ in self.model.frame_level_rnns]
for i in range(self.model.lookback, self.model.lookback + seq_len):
for (tier_index, rnn) in \
reversed(list(enumerate(self.model.frame_level_rnns))):
# if i % rnn.n_frame_samples != 0:
# continue
prev_samples = sequences[:, i - 16:i]
prev_samples = torch.autograd.Variable(
2 * utils.linear_dequantize(
prev_samples, self.model.q_levels).unsqueeze(1))
if self.cuda:
prev_samples = prev_samples.cuda()
label_tensor = label_tensor.cuda()
if tier_index == len(self.model.frame_level_rnns) - 1:
upper_tier_conditioning = None
# if self.model.num_classes > 1:
# upper_tier_conditioning = self.model.class_embedding(label_tensor) + self.model.class_bias.cuda()
# if self.cuda:
# upper_tier_conditioning = upper_tier_conditioning.cuda()
else:
frame_index = (i // rnn.n_frame_samples) % \
self.model.frame_level_rnns[tier_index + 1].frame_size
upper_tier_conditioning = \
frame_level_outputs[tier_index + 1][:, frame_index, :] \
.unsqueeze(1)
if isinstance(class_label, int):
class_label = torch.Tensor([class_label])
frame_level_outputs[tier_index] = self.run_rnn(
rnn, prev_samples, upper_tier_conditioning,
class_label)
prev_samples = torch.autograd.Variable(
sequences[:, i - bottom_frame_size:i])
if self.cuda:
prev_samples = prev_samples.cuda()
frame_level_outputs[0] = frame_level_outputs[0].view(
n_seqs, bottom_frame_size, -1)
upper_tier_conditioning = \
frame_level_outputs[0][:, i % bottom_frame_size, :].unsqueeze(1)
sample_dist = self.model.sample_level_mlp(
prev_samples,
upper_tier_conditioning).squeeze(1).exp_().data
sequences[:, i] = sample_dist.multinomial(1).squeeze(1)
torch.backends.cudnn.enabled = True
return sequences[:, self.model.lookback:]