[Bug] On the latest version of mmocr how do I set statically the model download path?

[R4Ajeti]

Prerequisite

• I have searched Issues and Discussions but cannot get the expected help.
• The bug has not been fixed in the latest version (0.x) or latest version (1.x).

Task

I'm using the official example scripts/configs for the officially supported tasks/models/datasets.

Branch

main branch https://github.com/open-mmlab/mmocr

Environment

This code is working fine for me but how do I define the path of the model where "mmocr" should download the detection model and recognition model because I wanna send it statically on serverless to reduce time consuming?

Reproduces the problem - code sample

import numpy as np
import time
import cv2

from mmocr.apis import MMOCRInferencer
from mmocr.utils import poly2bbox

Load models into memory

ocr = MMOCRInferencer(det='DBNet', rec='SAR', device='cpu')

startTime = time.time()
img = cv2.imread('../mmocr/images/00_04_24_000-00_04_24_375.jpg', cv2.IMREAD_COLOR)

Perform inference

aaa = ocr(img)
print(aaa["predictions"])
print([poly2bbox(poly) for poly in aaa["predictions"][0]["det_polygons"]])
print(f"Time taken: {time.time() - startTime} seconds")

Reproduces the problem - command or script

...

Reproduces the problem - error message

...

Additional information

No response