def test_load(sample_list, sample_annotation, sample_scores):
coParser = CoParser(uris=sample_list,
annotation=sample_annotation,
scores=sample_scores)
for uri, annotation, scores in coParser.iter('uris', 'annotation',
'scores'):
break
assert uri == 'uri1'
assert list(annotation.itertracks(label=True)) == [
(Segment(1, 3.5), 0, 'alice'), (Segment(3, 7.5), 1, 'barbara'),
(Segment(6, 9), 2, 'chris')
]
assert list(scores.itervalues()) == [(Segment(1, 3.5), 0, 'alice', 0.8),
(Segment(1, 3.5), 1, 'barbara', 0.1),
(Segment(1, 3.5), 2, 'chris', 0.1),
(Segment(3, 7.5), 3, 'barbara', 0.5),
(Segment(3, 7.5), 4, 'chris', 0.4),
(Segment(6, 9), 5, 'alice', 0.1),
(Segment(6, 9), 6, 'barbara', 0.2),
(Segment(6, 9), 7, 'chris', 0.7)]
def do_train(
uris_lst,
references_mdtm,
features_pkl,
model_pkl,
n_components=16,
covariance_type='diag',
min_duration=0.250,
):
hmm = ViterbiHMM(n_components=n_components,
covariance_type=covariance_type,
random_state=None,
thresh=1e-2,
min_covar=1e-3,
n_iter=10,
disturb=0.05,
sampling=1000,
min_duration=min_duration)
# iterate over all uris in a synchronous manner
coParser = CoParser(uris=uris_lst,
reference=references_mdtm,
features=features_pkl)
references, features = coParser.generators('reference', 'features')
hmm.fit(references, features)
with open(model_pkl, 'wb') as f:
pickle.dump(hmm, f)
