phoneme_ctc.py 文件源码

def train(ENV, args):
    processed_train_data_path = os.path.join(ENV.processed_data_path, 'processed_train.pkl')
    processed_test_data_path = os.path.join(ENV.processed_data_path, 'processed_test.pkl')
    if os.path.exists(processed_train_data_path) and os.path.exists(processed_test_data_path):
        processed_train_data = pickle.load(open(processed_train_data_path, 'r'))
        processed_test_data = pickle.load(open(processed_test_data_path, 'r'))
    else:
        train_wav_files, train_phn_files = load_data(ENV.train_data)
        print('Process train data...')
        processed_train_data = process_data(train_wav_files, train_phn_files)
        test_wav_files, test_phn_files = load_data(ENV.test_data)
        print('Process test data...')
        processed_test_data = process_data(test_wav_files, test_phn_files)
        pickle.dump(processed_train_data, open(processed_train_data_path, 'w'))
        pickle.dump(processed_test_data, open(processed_test_data_path, 'w'))
    # print(processed_train_data[0][1])
    print("Define graph...")
    train_model(ENV, processed_train_data, processed_test_data)