Uniformize processor kwargs of siglip

src/transformers/models/siglip/processing_siglip.py

@@ -16,13 +16,30 @@
 Image/Text processor class for SigLIP.
 """
 
+import sys
 from typing import List, Optional, Union
 
 from ...feature_extraction_utils import BatchFeature
 from ...image_utils import ImageInput
-from ...processing_utils import ProcessorMixin
-from ...tokenization_utils_base import PaddingStrategy, PreTokenizedInput, TextInput, TruncationStrategy
-from ...utils import TensorType
+from ...processing_utils import ProcessingKwargs, ProcessorMixin
+from ...tokenization_utils_base import PreTokenizedInput, TextInput
+
+
+if sys.version_info >= (3, 11):
+    from typing import Unpack
+else:
+    from typing_extensions import Unpack
+
+
+class SiglipProcessingKwargs(ProcessingKwargs, total=False):
+    _defaults = {
+        "text_kwargs": {
+            "padding": False,
+        },
+        "common_kwargs": {
+            "return_tensors": "pt",
+        },
+    }
 
 
 class SiglipProcessor(ProcessorMixin):
@@ -48,12 +65,9 @@ def __init__(self, image_processor, tokenizer):
 
     def __call__(
         self,
-        text: Union[TextInput, PreTokenizedInput, List[TextInput], List[PreTokenizedInput]] = None,
-        images: ImageInput = None,
-        padding: Union[bool, str, PaddingStrategy] = False,
-        truncation: Union[bool, str, TruncationStrategy] = None,
-        max_length: int = None,
-        return_tensors: Optional[Union[str, TensorType]] = TensorType.PYTORCH,
+        text: Optional[Union[TextInput, PreTokenizedInput, List[TextInput], List[PreTokenizedInput]]] = None,
+        images: Optional[ImageInput] = None,
+        **kwargs: Unpack[SiglipProcessingKwargs],
     ) -> BatchFeature:
         """
         Main method to prepare for the model one or several sequences(s) and image(s). This method forwards the `text`
@@ -63,33 +77,13 @@ def __call__(
         of the above two methods for more information.
 
         Args:
-            text (`str`, `List[str]`, `List[List[str]]`):
+            text (`str`, `List[str]`, `List[List[str]]`, *optional*):
                 The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings
                 (pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set
                 `is_split_into_words=True` (to lift the ambiguity with a batch of sequences).
-            images (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`, `List[PIL.Image.Image]`, `List[np.ndarray]`, `List[torch.Tensor]`):
+            images (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`, `List[PIL.Image.Image]`, `List[np.ndarray]`, `List[torch.Tensor]`, *optional*):
                 The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch
                 tensor. Both channels-first and channels-last formats are supported.
-            padding (`bool`, `str` or [`~utils.PaddingStrategy`], *optional*, defaults to `False`):
-                Select a strategy to pad the returned sequences (according to the model's padding side and padding
-                index) among:
-                - `True` or `'longest'`: Pad to the longest sequence in the batch (or no padding if only a single
-                  sequence if provided).
-                - `'max_length'`: Pad to a maximum length specified with the argument `max_length` or to the maximum
-                  acceptable input length for the model if that argument is not provided.
-                - `False` or `'do_not_pad'` (default): No padding (i.e., can output a batch with sequences of different
-                  lengths).
-            max_length (`int`, *optional*):
-                Maximum length of the returned list and optionally padding length (see above).
-            truncation (`bool`, *optional*):
-                Activates truncation to cut input sequences longer than `max_length` to `max_length`.
-            return_tensors (`str` or [`~utils.TensorType`], *optional*):
-                If set, will return tensors of a particular framework. Acceptable values are:
-
-                - `'tf'`: Return TensorFlow `tf.constant` objects.
-                - `'pt'`: Return PyTorch `torch.Tensor` objects.
-                - `'np'`: Return NumPy `np.ndarray` objects.
-                - `'jax'`: Return JAX `jnp.ndarray` objects.
 
         Returns:
             [`BatchFeature`]: A [`BatchFeature`] with the following fields:
@@ -104,21 +98,27 @@ def __call__(
         if text is None and images is None:
             raise ValueError("You have to specify either text or images. Both cannot be none.")
 
+        output_kwargs = self._merge_kwargs(
+            SiglipProcessingKwargs,
+            tokenizer_init_kwargs=self.tokenizer.init_kwargs,
+            **kwargs,
+        )
+
         if text is not None:
-            encoding = self.tokenizer(
-                text, return_tensors=return_tensors, padding=padding, truncation=truncation, max_length=max_length
-            )
+            encoding = self.tokenizer(text, output_kwargs["text_kwargs"])
 
         if images is not None:
-            image_features = self.image_processor(images, return_tensors=return_tensors)
+            image_features = self.image_processor(images, output_kwargs["images_kwargs"])
 
         if text is not None and images is not None:
             encoding["pixel_values"] = image_features.pixel_values
             return encoding
         elif text is not None:
             return encoding
         else:
-            return BatchFeature(data=dict(**image_features), tensor_type=return_tensors)
+            return BatchFeature(
+                data=dict(**image_features), tensor_type=output_kwargs["text_kwargs"]["return_tensors"]
+            )
 
     def decode(self, *args, **kwargs):
         """