# for filename, lbl, features in X_test_transformed:
# if features is not None:
# X_total = np.vstack([ X_total, features ])
# else:
# print "Null test", filename
X_total = np.vstack([X_total, X_test])
print X_total.shape
print "Ready with test"
print "Loading voxforge features"
if VOX_FEATURES:
if LIMIT is None:
vox_limit = 4000
else:
vox_limit = LIMIT
voxforge_features = load_vox_forge_files(
"/store/egor/voxforge", vox_limit, "bow_voxfeatures.pcl", extract_mfcc_features
)
vox_features = np.vstack([f for (_, _, f) in voxforge_features if f is not None])
X_total = np.vstack([X_total, vox_features])
else:
voxforge_features = []
print "Transformed everyting for dictionary learning", X_total.shape
dictionary = learn_dictionary(sofia_path, X_total, "dictionary.pcl", DICTIONARY_SIZE)
X = np.array(
[
features
for (_, _, features) in itertools.chain(X_train_transformed, voxforge_features)
if features is not None
X_train_transformed = load_train_features('gmm_train_features.pcl', extract_gmm_feature, limit = LIMIT )
print "Loaded train"
test_data = get_all_test_data()
filename_by_path = {path : filename for (path, filename) in test_data }
X_test_transformed = load_test_features('gmm_test_features.pcl', extract_gmm_feature, limit = LIMIT)
print "Loaded test"
if VOX_FEATURES:
print "Loading voxforge features"
if LIMIT is None:
vox_limit = 4000
else:
vox_limit = LIMIT
voxforge_features = load_vox_forge_files('/store/egor/voxforge', vox_limit, 'gmm_voxfeatures.pcl', extract_gmm_feature )
else:
voxforge_features = []
#X = np.array([features for (_,_, features) in itertools.chain(X_train_transformed, voxforge_features)])
X = np.array([features for (_,_, features) in itertools.chain(X_train_transformed, voxforge_features) if features is not None ])
y = np.array([lbl for (_,lbl, _) in itertools.chain(X_train_transformed, voxforge_features) if lbl is not None ])
print "X = ", X.shape, "y=", y.shape
print "Loaded X", X.shape
#shuffle
X, y = shuffle_in_unison_inplace(X,y)
#X = StandardScaler().fit_transform(X)
#binarizer.fit( y )
#y = binarizer.transform( y )
print "Preprocessed data"
if VALIDATE:
