Update ultravox_processing.py

ultravox_processing.py

@@ -185,7 +185,7 @@ class UltravoxProcessor(transformers.ProcessorMixin):
             text = [t.replace(self.audio_placeholder, self.audio_token_replacement * data["audio_token_len"][i]) for i, t in enumerate(text)]
 
             # Special tokens like BOS should already have been added by the caller.
-            data.update(self.tokenizer(text, add_special_tokens=False, **kwargs))
+            data.update(self.tokenizer(text, add_special_tokens=False, padding=True, **kwargs))
 
         return transformers.BatchFeature(data=data, tensor_type=return_tensors)