def test_input_to_str_list(self):
# Tuple input but elements are not strings.
out = ModelTrainer._input_to_str_list((121, 122))
self.assertEqual(["121", "122"], out)
# Valid path to file id list.
out = ModelTrainer._input_to_str_list(os.path.join("integration", "fixtures", "file_id_list.txt"))
self.assertEqual(TestModelTrainer._get_id_list(), out)
# Single input id.
out = ModelTrainer._input_to_str_list("121")
self.assertEqual(["121"], out)
# Wrong input.
with self.assertRaises(ValueError):
ModelTrainer._input_to_str_list(numpy.array([1, 2]))
def gen_figure_phrase(self, hparams, ids_input):
id_list = ModelTrainer._input_to_str_list(ids_input)
model_output, model_output_post = self._forward_batched(
hparams,
id_list,
hparams.batch_size_gen_figure,
synth=False,
benchmark=False,
gen_figure=False)
for id_name, outputs_post in model_output_post.items():
if outputs_post.ndim < 2:
outputs_post = np.expand_dims(outputs_post, axis=1)
lf0 = outputs_post[:, 0]
output_lf0, _ = interpolate_lin(lf0)
output_vuv = outputs_post[:, 1]
output_vuv[output_vuv < 0.5] = 0.0
output_vuv[output_vuv >= 0.5] = 1.0
output_vuv = output_vuv.astype(np.bool)
# Load original lf0 and vuv.
world_dir = hparams.world_dir if hasattr(hparams, "world_dir") and hparams.world_dir is not None\
else os.path.join(hparams.out_dir, self.dir_extracted_acoustic_features)
org_labels = WorldFeatLabelGen.load_sample(
id_name,
world_dir,
num_coded_sps=hparams.num_coded_sps,
num_bap=hparams.num_bap)[:len(output_lf0)]
_, original_lf0, original_vuv, _ = WorldFeatLabelGen.convert_to_world_features(
org_labels,
num_coded_sps=hparams.num_coded_sps,
num_bap=hparams.num_bap)
original_lf0, _ = interpolate_lin(original_lf0)
original_vuv = original_vuv.astype(np.bool)
phrase_curve = np.fromfile(os.path.join(
self.flat_trainer.atom_trainer.OutputGen.dir_labels,
id_name + self.OutputGen.ext_phrase),
dtype=np.float32).reshape(
-1, 1)[:len(original_lf0)]
f0_mse = (np.exp(original_lf0.squeeze(-1)) -
np.exp(phrase_curve.squeeze(-1)))**2
f0_rmse = math.sqrt(
(f0_mse * original_vuv[:len(output_lf0)]).sum() /
original_vuv[:len(output_lf0)].sum())
self.logger.info("RMSE of {} phrase curve: {} Hz.".format(
id_name, f0_rmse))
len_diff = len(original_lf0) - len(lf0)
original_lf0 = WorldFeatLabelGen.trim_end_sample(
original_lf0, int(len_diff / 2.0))
original_lf0 = WorldFeatLabelGen.trim_end_sample(
original_lf0, int(len_diff / 2.0) + 1, reverse=True)
# Get a data plotter.
net_name = os.path.basename(hparams.model_name)
filename = str(
os.path.join(hparams.out_dir, id_name + '.' + net_name))
plotter = DataPlotter()
# plotter.set_title(id_name + " - " + net_name)
grid_idx = 0
graphs_lf0 = list()
graphs_lf0.append((original_lf0, "Original"))
graphs_lf0.append((phrase_curve, "Predicted"))
plotter.set_data_list(grid_idx=grid_idx, data_list=graphs_lf0)
plotter.set_area_list(grid_idx=grid_idx,
area_list=[(np.invert(original_vuv), '0.8',
1.0, 'Reference unvoiced')])
plotter.set_label(grid_idx=grid_idx,
xlabel='frames [' + str(hparams.frame_size_ms) +
' ms]',
ylabel='LF0')
# amp_lim = max(np.max(np.abs(wcad_lf0)), np.max(np.abs(output_lf0))) * 1.1
# plotter.set_lim(grid_idx=grid_idx, ymin=-amp_lim, ymax=amp_lim)
plotter.set_lim(grid_idx=grid_idx, ymin=4.2, ymax=5.4)
# plotter.set_linestyles(grid_idx=grid_idx, linestyles=[':', '--', '-'])
# plotter.set_lim(xmin=300, xmax=1100)
plotter.gen_plot()
plotter.save_to_file(filename + ".PHRASE" + hparams.gen_figure_ext)