Update app.py

app.py

@@ -1,35 +1,24 @@
 # app.py
 import gradio as gr
-from transformers import AutoTokenizer, AutoModelForTokenClassification, pipeline
+from transformers import TrOCRProcessor, VisionEncoderDecoderModel
 from PIL import Image
-import numpy as np
 
-# Load model and tokenizer
-tokenizer = AutoTokenizer.from_pretrained("microsoft/trocr-base-handwritten")
-model = AutoModelForTokenClassification.from_pretrained("microsoft/trocr-base-handwritten")
-
-# Create OCR pipeline
-ocr_pipeline = pipeline(
-    "image-to-text",
-    model=model,
-    tokenizer=tokenizer,
-    feature_extractor=tokenizer.init_feature_extractor()
-)
+# Load model and processor
+processor = TrOCRProcessor.from_pretrained("microsoft/trocr-base-handwritten")
+model = VisionEncoderDecoderModel.from_pretrained("microsoft/trocr-base-handwritten")
 
 def predict_handwriting(image):
     """
     Function to process handwritten text image and return transcription
     """
     try:
-        # Preprocess image
+        # Preprocess the image
         image = image.convert("RGB")
-        image = np.array(image)
-        
-        # Run OCR
-        result = ocr_pipeline(image)
-        
-        # Extract text from results
-        transcription = " ".join([word["value"] for word in result])
+        # Prepare image pixel values
+        pixel_values = processor(image, return_tensors="pt").pixel_values
+        # Generate text
+        generated_ids = model.generate(pixel_values)
+        transcription = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
         return transcription
     
     except Exception as e: