Load tokenizer & processor from preprocessor subfolder

app.py

@@ -6,26 +6,32 @@ from inference import OcrReorderPipeline
 from transformers import (
     AutoProcessor,
     LayoutLMv3Model,
-    T5ForConditionalGeneration,
     AutoTokenizer
 )
 import torch
 
-# Load from your model repo
+# 1) Load from your model repo, pointing at the `preprocessor/` folder
 repo = "Uddipan107/ocr-layoutlmv3-base-t5-small"
 model     = LayoutLMv3Model.from_pretrained(repo)
-tokenizer = AutoTokenizer.from_pretrained(repo)
-processor = AutoProcessor.from_pretrained(repo, apply_ocr=False)
-pipe      = OcrReorderPipeline(model, tokenizer, processor, device=0)
+tokenizer = AutoTokenizer.from_pretrained(repo, subfolder="preprocessor")
+processor = AutoProcessor.from_pretrained(repo, subfolder="preprocessor", apply_ocr=False)
+
+# 2) Instantiate your pipeline
+pipe = OcrReorderPipeline(model, tokenizer, processor, device=0)
 
 def infer(image, words_json, boxes_json):
     words = json.loads(words_json)
     boxes = json.loads(boxes_json)
-    buf = BytesIO(); image.save(buf, "PNG")
+
+    # Encode PIL image → PNG → base64
+    buf = BytesIO()
+    image.save(buf, format="PNG")
     b64 = base64.b64encode(buf.getvalue()).decode()
-    # returns a list of strings; take first
+
+    # Run your custom pipeline and return the first (only) output string
     return pipe(b64, words, boxes)[0]
 
+# 3) Gradio UI
 demo = gr.Interface(
     fn=infer,
     inputs=[