PaliGemma - fix processor with no input text (#30916)

Update processing_paligemma.py

src/transformers/models/paligemma/processing_paligemma.py

@@ -177,6 +177,7 @@ class PaliGemmaProcessor(ProcessorMixin):
             logger.warning_once(
                 "You are using PaliGemma without a text prefix. It will perform as a picture-captioning model."
             )
+            text = ""
 
         if isinstance(text, List) and isinstance(images, List):
             if len(images) < len(text):