audio_converter.py 文件源码

def generateDatasets(train_files, cut_data, len_mfcc, step_mfcc, hop_len, freq):

    X, Y = [], []

    for tf in train_files:

        train_data, labels = generateSingleDataset(tf, cut_data, len_mfcc, step_mfcc, hop_len, freq)

        X.append(train_data)
        Y.append(labels)

    X = np.concatenate(X)
    Y = np.concatenate(Y)

    if cut_data:
        filename = STORE_DIR + 'dataset_CUT_' + str(freq) + '_' + str(hop_len) + '_' + str(len_mfcc) + '_' + str(step_mfcc) + '_' + str(X.shape[0]) + '_' + str(X.shape[1]) + '_' + str(X.shape[2]) + '.pickle'
    else:
        filename = STORE_DIR + 'dataset_' + str(freq) + '_' + str(hop_len) + '_' + str(len_mfcc) + '_' + str(step_mfcc) + '_' + str(X.shape[0]) + '_' + str(X.shape[1]) + '_' + str(X.shape[2]) + '.pickle'
    print filename
    with open(filename, 'w') as f:
        pickle.dump([X, Y], f)

    return X, Y


# Generate a dataset from all available files