diff --git a/python/rapidocr/main.py b/python/rapidocr/main.py
index e17f738..8fb10d3 100644
--- a/python/rapidocr/main.py
+++ b/python/rapidocr/main.py
@@ -133,11 +133,13 @@ class RapidOCR:
                     origin_words_points = self._get_origin_points(
                         [one_word_points], op_record, raw_h, raw_w
                     )
-                    origin_words_points = origin_words_points.astype(np.int32).tolist()[0]
+                    origin_words_points = origin_words_points.astype(np.int32).tolist()[
+                        0
+                    ]
                     origin_words_item.append(
                         (one_word[0], one_word[1], origin_words_points)
                     )
-                
+
                 if origin_words_item:
                     origin_words.append(tuple(origin_words_item))
             rec_res.word_results = tuple(origin_words)
@@ -367,7 +369,7 @@ def main(arg_list: Optional[List[str]] = None):
         cur_dir = args.vis_save_dir
 
         if args.return_word_box:
-            words_results = result.word_results
+            words_results = sum(result.word_results, ())
             words, words_scores, words_boxes = list(zip(*words_results))
             vis_img = vis(args.img_path, words_boxes, words, words_scores)
             save_path = cur_dir / f"{Path(args.img_path).stem}_vis_single.png"
diff --git a/python/rapidocr/utils/output.py b/python/rapidocr/utils/output.py
index d92d31b..c97af9e 100644
--- a/python/rapidocr/utils/output.py
+++ b/python/rapidocr/utils/output.py
@@ -59,7 +59,7 @@ class RapidOCROutput:
             return vis_img
 
         # single word vis
-        words_results = self.word_results
+        words_results = sum(self.word_results, ())
         words, words_scores, words_boxes = list(zip(*words_results))
         vis_img = vis(
             self.img,
diff --git a/python/tests/test_main.py b/python/tests/test_main.py
index 5a7ea05..11a998f 100644
--- a/python/tests/test_main.py
+++ b/python/tests/test_main.py
@@ -406,44 +406,14 @@ def test_input_three_ndim_one_channel(engine):
         ),
         (
             "text_vertical_words.png",
-            (
-                "已",
-                "取",
-                "之",
-                "時",
-                "不",
-                "參",
-                "一",
-                "人",
-                "見",
-                "而",
-                "是",
-                "非",
-                "不",
-                "得",
-                "問",
-                "之",
-                "人",
-                "要",
-                "取",
-                "之",
-                "有",
-                "是",
-                "是",
-                "非",
-                "非",
-                "之",
-                "士",
-                "師",
-                "也",
-            ),
+            ("已", "取", "之", "時", "不", "參", "一", "人", "見", "而"),
         ),
     ],
 )
 def test_cn_word_ocr(engine, img_name: str, words: List[str]):
     img_path = tests_dir / img_name
     result = engine(img_path, return_word_box=True)
-    txts, _, _ = list(zip(*result.word_results))
+    txts, _, _ = list(zip(*result.word_results[0]))
     assert txts == words
 
 
@@ -454,12 +424,12 @@ def test_cn_word_ocr(engine, img_name: str, words: List[str]):
 def test_en_word_ocr(engine, img_name: str, words: str):
     img_path = tests_dir / img_name
     result = engine(img_path, return_word_box=True)
-    txts, _, _ = list(zip(*result.word_results))
+    txts, _, _ = list(zip(*result.word_results[0]))
     assert txts[0] == words
 
 
 def test_en_return_single_char_box(engine):
     img_path = tests_dir / "en.jpg"
     result = engine(img_path, return_word_box=True, return_single_char_box=True)
-    txts, _, _ = list(zip(*result.word_results))
-    assert txts[:3] == ("3", "M", "o")
+    txts, _, _ = list(zip(*result.word_results[0]))
+    assert txts[:3] == ("3",)