Getting "Model name mismatch" when I try to use "eslav_PP-OCRv5_mobile_rec" instead of "PP-OCRv5_server_rec" even though it's the official one

[TryingToMakeDo]

import os
from paddleocr import PaddleOCR
home_dir = os.path.expanduser("~")
det_model_path = os.path.join(home_dir, ".paddlex", "official_models", "PP-OCRv5_server_det")
rec_model_path = os.path.join(home_dir, ".paddlex", "official_models", "PP-OCRv5_server_rec")

ocr = PaddleOCR(
text_detection_model_dir=det_model_path,
text_recognition_model_dir=rec_model_path,
use_doc_orientation_classify=False,
use_doc_unwarping=False,
use_textline_orientation=False
)

result = ocr.predict(
input="4.png")

for res in result:
res.print()
res.save_to_img("output")
res.save_to_json("output")

I'm running the following code and it works but when I change PP-OCRv5_server_rec with eslav_PP-OCRv5_mobile_rec it raises a name mismatch exception. The eslav itself was downloaded when I set lang='ru' so it's the official version. I want to modify eslav to add extra cyrillic characters for my language so any pointers on how to do that in addition to modifying the yaml and character dictionary would be helpful.