Update app.py

app.py

@@ -7,7 +7,7 @@ from ultralytics import YOLO
 from PIL import Image
 import torch
 
-def greet(name):
+def process(path):
     LINE_MODEL_PATH = "Kansallisarkisto/multicentury-textline-detection"
     #OCR_MODEL_PATH = "Kansallisarkisto/multicentury-htr-model"
     OCR_MODEL_PATH = "microsoft/trocr-large-handwritten"
@@ -17,7 +17,7 @@ def greet(name):
     model = VisionEncoderDecoderModel.from_pretrained(OCR_MODEL_PATH)
 
     # Open an image of handwritten text
-    image = Image.open("/content/drive/My Dive/ocr/img/hhhhhh-x595.jpeg").convert("RGB")
+    image = Image.open(path).convert("RGB")
 
     try:
         # Load the trained line detection model
@@ -34,21 +34,16 @@ def greet(name):
     for box in boxes:
         #box = box + torch.tensor([-10,0, 10, 0])
         box = [tensor.item() for tensor in box]
-        #print(box)
         lineImg = image.crop(tuple(list(box)))
-        #plt.imshow(lineImg)
-        #plt.show()
 
         # Preprocess and predict
         pixel_values = processor(lineImg, return_tensors="pt").pixel_values
         generated_ids = model.generate(pixel_values)
         generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
-        #print(generated_text)
         full_text += generated_text
-        #print("--------------------------------------------")
 
     return full_text
-    #print("--------------------------------------------")
 
-demo = gr.Interface(fn=greet, inputs="image", outputs="text")
-demo.launch()
+if __name__ == "__main__"
+    demo = gr.Interface(fn=process, inputs=gr.Image(type="filepath", outputs="text")
+    demo.launch()