Update app.py

app.py

@@ -12,7 +12,7 @@ tokenizer = AutoTokenizer.from_pretrained(decoder_checkpoint)
 model = VisionEncoderDecoderModel.from_pretrained(model_checkpoint).to(device)
 
 
-def predict(image,max_length=64, num_beams=4):
+def predict(image,max_length=64, num_beams=3):
   image = image.convert('RGB')
   image = feature_extractor(image, return_tensors="pt").pixel_values.to(device)
   clean_text = lambda x: x.replace('<|endoftext|>','').split('\n')[0]