TextRecognition use local model fail

[Mr-Glin]

error info:

�[33mNo model hoster is available! Please check your network connection to one of the following model hosts:
HuggingFace (https://huggingface.co),
ModelScope (https://modelscope.cn),
AIStudio (https://aistudio.baidu.com), or
BOS (https://paddle-model-ecology.bj.bcebos.com).
Otherwise, only local models can be used.�[0m

code :

import time
import os
paddlex_path = os.path.abspath(os.path.join(os.path.dirname(file),".paddlex"))
model_path = os.path.abspath(os.path.join(os.path.dirname(file),".paddlex",'official_models','PP-OCRv4_mobile_rec'))
os.environ["PADDLE_PDX_CACHE_HOME"] = paddlex_path
os.environ["PADDLEOCR_MODEL_HOME"] = model_path

from paddleocr import TextRecognition

class PaddleOCRHelper:

def __init__(self, logger):
    self.logger = logger
    self.logger.info("init ocr>>>")
    self._instance = TextRecognition(
        model_name="PP-OCRv4_mobile_rec", cpu_threads=2,model_dir=model_path
    )
    self.logger.info("init ocr<<<")

cannot goto init ocr<<<

[liuhongen1234567]

Hello, there are some issues with loading a local model by modifying the PaddleX cache path. You can refer to this issue to modify the underlying code to bypass this error: PaddlePaddle/PaddleX#4578 (comment).