docx文档解析报错：RecursionError: maximum recursion depth exceeded

[sqsa110]

环境：python3.11
cuda: 12.12
paddlepaddle-gpu: 3.0.0
显卡: T4
系统：rocky9.5
尝试解析一个docx的文档出现以下报错

Traceback (most recent call last):
  File "/root/output/test.py", line 8, in <module>
    output = pipeline.predict(input_file)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/base_paddleOCR/lib64/python3.11/site-packages/paddleocr/_pipelines/pp_structurev3.py", line 207, in predict
    return list(
           ^^^^^
  File "/root/base_paddleOCR/lib64/python3.11/site-packages/paddlex/inference/pipelines/_parallel.py", line 129, in predict
    yield from self._pipeline.predict(
  File "/root/base_paddleOCR/lib64/python3.11/site-packages/paddlex/inference/pipelines/layout_parsing/pipeline_v2.py", line 1041, in predict
    for batch_data in self.batch_sampler(input):
  File "/root/base_paddleOCR/lib64/python3.11/site-packages/paddlex/inference/common/batch_sampler/base_batch_sampler.py", line 80, in __call__
    yield from self.sample(input)
  File "/root/base_paddleOCR/lib64/python3.11/site-packages/paddlex/inference/common/batch_sampler/image_batch_sampler.py", line 115, in sample
    yield from self.sample(file_list)
  File "/root/base_paddleOCR/lib64/python3.11/site-packages/paddlex/inference/common/batch_sampler/image_batch_sampler.py", line 115, in sample
    yield from self.sample(file_list)
  File "/root/base_paddleOCR/lib64/python3.11/site-packages/paddlex/inference/common/batch_sampler/image_batch_sampler.py", line 115, in sample
    yield from self.sample(file_list)
  [Previous line repeated 989 more times]
  File "/root/base_paddleOCR/lib64/python3.11/site-packages/paddlex/inference/common/batch_sampler/image_batch_sampler.py", line 81, in sample
    batch = ImgBatch()
            ^^^^^^^^^^
  File "/root/base_paddleOCR/lib64/python3.11/site-packages/paddlex/inference/common/batch_sampler/image_batch_sampler.py", line 29, in __init__
    super().__init__()
RecursionError: maximum recursion depth exceeded

[liuhongen1234567]

您好，当前版本paddleocr暂不支持传入docx，只支持pdf格式，可以另存为pdf试试

[sqsa110]

好的

[TingquanGao]

呃，是什么场景需要对docx文档进行解析呢？是需要把word文档转为markdown格式吗？

[sqsa110]

是的