# X_train = np.reshape(X_train, ( len(X_train_transformed), num_features ) )
print X_train.shape
# for filename, lbl, features in X_train_transformed:
# if features is None:
# print "Train",filename, "is none"
# continue
# if X_total is not None:
# X_total = np.vstack([ X_total, features ])
# else:
# X_total = features
X_total = X_train
print "Ready with train"
print "Starting train"
test_data = get_all_test_data()
filename_by_path = {path: filename for (path, filename) in test_data}
X_test_transformed = load_test_features("bow_test_features.pcl", extract_mfcc_features, limit=LIMIT)
X_test = np.vstack([f for (_, _, f) in X_test_transformed if f is not None])
# 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:
__author__ = 'egor'
VALIDATE = True
np.random.seed(100500)
VOX_FEATURES = True
LIMIT = 5000
print "Using Vox features", VOX_FEATURES
print "LIMIT", LIMIT
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 ])
