acousticModelTraining.py 文件源码

def trainValidationSplit(dic_pho_feature_train,validation_size=0.2):
    '''
    split the feature in dic_pho_feature_train into train and validation set
    :param dic_pho_feature_train: input dictionary, key: phoneme, value: feature vectors
    :return:
    '''
    feature_all = []
    label_all = []
    for key in dic_pho_feature_train:
        feature = dic_pho_feature_train[key]
        label = [dic_pho_label[key]] * len(feature)

        if len(feature):
            if not len(feature_all):
                feature_all = feature
            else:
                feature_all = np.vstack((feature_all, feature))
            label_all += label
    label_all = np.array(label_all,dtype='int64')

    feature_all = preprocessing.StandardScaler().fit_transform(feature_all)
    feature_train, feature_validation, label_train, label_validation = \
        train_test_split(feature_all, label_all, test_size=validation_size, stratify=label_all)

    return feature_train, feature_validation, label_train, label_validation