Update app.py

app.py

@@ -11,7 +11,13 @@ translation_model_name = "Helsinki-NLP/opus-mt-en-es"
 translator_model = MarianMTModel.from_pretrained(translation_model_name)
 translator_tokenizer = MarianTokenizer.from_pretrained(translation_model_name)
 
+from PIL import Image
+
 def generate_caption(image):
+    # Ensure the image is in PIL format (Gradio should handle this, but let's explicitly ensure it)
+    if isinstance(image, Image.Image) is False:
+        image = Image.open(image)
+    
     # Generate caption from image
     inputs = processor(images=image, return_tensors="pt", padding=True)  # Added padding=True
     out = model.generate(**inputs)