Update app.py

app.py

@@ -62,7 +62,7 @@ def predict_nougat(img, model_name="facebook/nougat-small"):
     processor = NougatProcessor.from_pretrained(model_name)
     model = VisionEncoderDecoderModel.from_pretrained(model_name)
     image = img.convert("RGB")
-    pixel_values = processor(image, return_tensors="pt").pixel_values
+    pixel_values = processor(image, return_tensors="pt", data_format="channels_first").pixel_values
     
     # generate transcription (here we only generate 30 tokens)
     outputs = model.generate(