Update files/functions.py

files/functions.py

@@ -137,13 +137,14 @@ langdetect2Tesseract = {v:k for k,v in Tesseract2langdetect.items()}
 
 ## model / feature extractor / tokenizer
 
-from transformers import LayoutLMv2ForTokenClassification # LayoutXLMTokenizerFast, 
-
 import torch
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
 # model
-# tokenizer = LayoutXLMTokenizerFast.from_pretrained(model_id)
+from transformers import LayoutLMv2ForTokenClassification
+
+model_id = "pierreguillou/layout-xlm-base-finetuned-with-DocLayNet-base-at-linelevel-ml384"
+
 model = LayoutLMv2ForTokenClassification.from_pretrained(model_id);
 model.to(device);
 
@@ -153,6 +154,7 @@ feature_extractor = LayoutLMv2FeatureExtractor(apply_ocr=False)
 
 # tokenizer
 from transformers import AutoTokenizer
+tokenizer_id = "xlm-roberta-base"
 tokenizer = AutoTokenizer.from_pretrained(tokenizer_id)
 
 ## General