add post_process_image_text_to_text to qwen2_vl and llava_onevision

src/transformers/models/llava_onevision/processing_llava_onevision.py

@@ -266,6 +266,20 @@ def decode(self, *args, **kwargs):
         """
         return self.tokenizer.decode(*args, **kwargs)
 
+    def post_process_image_text_to_text(self, generated_outputs):
+        """
+        Post-process the output of the model to decode the text.
+
+        Args:
+            generated_outputs (`torch.Tensor` or `np.ndarray`):
+                The output of the model `generate` function. The output is expected to be a tensor of shape `(batch_size, sequence_length)`
+                or `(sequence_length,)`.
+
+        Returns:
+            `List[str]`: The decoded text.
+        """
+        return self.tokenizer.batch_decode(generated_outputs, skip_special_tokens=True)
+
     @property
     # Copied from transformers.models.clip.processing_clip.CLIPProcessor.model_input_names
     def model_input_names(self):

src/transformers/models/qwen2_vl/processing_qwen2_vl.py

@@ -176,6 +176,22 @@ def decode(self, *args, **kwargs):
         """
         return self.tokenizer.decode(*args, **kwargs)
 
+    def post_process_image_text_to_text(self, generated_outputs):
+        """
+        Post-process the output of the model to decode the text.
+
+        Args:
+            generated_outputs (`torch.Tensor` or `np.ndarray`):
+                The output of the model `generate` function. The output is expected to be a tensor of shape `(batch_size, sequence_length)`
+                or `(sequence_length,)`.
+
+        Returns:
+            `List[str]`: The decoded text.
+        """
+        return self.tokenizer.batch_decode(
+            generated_outputs, skip_special_tokens=True, clean_up_tokenization_spaces=False
+        )
+
     @property
     def model_input_names(self):
         tokenizer_input_names = self.tokenizer.model_input_names