AssertionError: Model name mismatch，please input the correct model dir.

[o0ii0o]

AssertionError: Model name mismatch，please input the correct model dir.
这个报错是怎么回事，把v5的模型下载到本地然后指定了模型的路径，进行预测时出现的报错

[o0ii0o]

是在服务器上不是在本地
./models/config/paddleocr/rec/ch/PP-OCRv5_server_rec/这是模型的路径

[o0ii0o]

还有一条这个信息Creating model: ('PP-OCRv5_mobile_det', './models/config/paddleocr/det/ch/PP-OCRv5_server_det')

[yangoono]

这个是个bug，你看前面是mobile后面是server，你实际上用的是server。
https://github.com/PaddlePaddle/PaddleOCR/issues/15481，可以参考这个。
总而言之，我的解决办法就是在https://github.com/PaddlePaddle/PaddleOCR/tree/main/paddleocr/_pipelines/ocr.py代码的if text_detection_model_dir is None and text_recognition_model_dir is None:
if lang is not None or ocr_version is not None:
det_model_name, rec_model_name = self._get_ocr_model_names(
lang, ocr_version
)
if det_model_name is None or rec_model_name is None:
raise ValueError(
f"No models are available for the language {repr(lang)} and OCR version {repr(ocr_version)}."
)
text_detection_model_name = det_model_name
text_recognition_model_name = rec_model_name改成这样