Update app.py

app.py

@@ -1,6 +1,7 @@
-import gradio as gr
+import gradio as gr 
 from transformers import TrOCRProcessor, VisionEncoderDecoderModel
 from PIL import Image
+import numpy as np
 import requests
 
 # Load your model from Hugging Face
@@ -9,7 +10,11 @@ model = VisionEncoderDecoderModel.from_pretrained("DeepDiveDev/transformodocs-oc
 
 # Function to extract text
 def extract_text(image):
-    image = Image.open(image).convert("RGB")
+    if isinstance(image, np.ndarray):  # Check if input is a NumPy array
+        image = Image.fromarray(image)  # Convert NumPy array to PIL Image
+    else:
+        image = Image.open(image).convert("RGB")  # Open normally if not a NumPy array
+
     pixel_values = processor(images=image, return_tensors="pt").pixel_values
     generated_ids = model.generate(pixel_values)
     extracted_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]