多行数据怎么标注呢？识别结果解码出来怎么分开呢

[cqray1990]

    for index, (pred, prob, img_name) in enumerate(zip(outputs[:, 1:], probs, file_names)):
        predict_text = ""
        # pred_list = []
        pred_score_list = []
        for i in range(len(pred)):  # decode one sample
            if pred[i] == LabelTransformer.EOS:
                pred_score_list.append(prob[i])
                break
            if pred[i] == LabelTransformer.UNK:
                continue
            decoded_char = LabelTransformer.decode(pred[i])
            predict_text += decoded_char
            # pred_list.append(decoded_char)
            pred_score_list.append(prob[i])
        pred_score = sum(pred_score_list) / len(pred_score_list)
        pred_item = {"filename": Path(img_name).name,
                     "result": predict_text,
                     "pred_score": pred_score.cpu().item()}
        pred_results.append(pred_item)

这段代码多行数据直接合成一条后怎么分开呢，标注的时候多行用特殊符号隔开，解码的时候怎么把两行数据分开呢，会预测出特殊符号？