[Processor classes] Update docs (#29698)

Update docs

src/transformers/models/align/processing_align.py

@@ -57,8 +57,7 @@ class AlignProcessor(ProcessorMixin):
                 `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]`):
                 The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch
-                tensor. In case of a NumPy array/PyTorch tensor, each image should be of shape (C, H, W), where C is a
-                number of channels, H and W are image height and width.
+                tensor. Both channels-first and channels-last formats are supported.
             padding (`bool`, `str` or [`~utils.PaddingStrategy`], *optional*, defaults to `max_length`):
                 Activates and controls padding for tokenization of input text. Choose between [`True` or `'longest'`,
                 `'max_length'`, `False` or `'do_not_pad'`]

src/transformers/models/altclip/processing_altclip.py

@@ -73,8 +73,7 @@ class AltCLIPProcessor(ProcessorMixin):
                 `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]`):
                 The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch
-                tensor. In case of a NumPy array/PyTorch tensor, each image should be of shape (C, H, W), where C is a
-                number of channels, H and W are image height and width.
+                tensor. Both channels-first and channels-last formats are supported.
 
             return_tensors (`str` or [`~utils.TensorType`], *optional*):
                 If set, will return tensors of a particular framework. Acceptable values are:

src/transformers/models/chinese_clip/processing_chinese_clip.py

@@ -75,8 +75,7 @@ class ChineseCLIPProcessor(ProcessorMixin):
                 `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]`):
                 The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch
-                tensor. In case of a NumPy array/PyTorch tensor, each image should be of shape (C, H, W), where C is a
-                number of channels, H and W are image height and width.
+                tensor. Both channels-first and channels-last formats are supported.
 
             return_tensors (`str` or [`~utils.TensorType`], *optional*):
                 If set, will return tensors of a particular framework. Acceptable values are:

src/transformers/models/clip/processing_clip.py

@@ -73,8 +73,7 @@ class CLIPProcessor(ProcessorMixin):
                 `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]`):
                 The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch
-                tensor. In case of a NumPy array/PyTorch tensor, each image should be of shape (C, H, W), where C is a
-                number of channels, H and W are image height and width.
+                tensor. Both channels-first and channels-last formats are supported.
 
             return_tensors (`str` or [`~utils.TensorType`], *optional*):
                 If set, will return tensors of a particular framework. Acceptable values are:

src/transformers/models/clipseg/processing_clipseg.py

@@ -73,8 +73,7 @@ class CLIPSegProcessor(ProcessorMixin):
                 `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]`):
                 The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch
-                tensor. In case of a NumPy array/PyTorch tensor, each image should be of shape (C, H, W), where C is a
-                number of channels, H and W are image height and width.
+                tensor. Both channels-first and channels-last formats are supported.
             visual_prompt (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`, `List[PIL.Image.Image]`, `List[np.ndarray]`, `List[torch.Tensor]`):
                 The visual prompt image or batch of images to be prepared. Each visual prompt image can be a PIL image,
                 NumPy array or PyTorch tensor. In case of a NumPy array/PyTorch tensor, each image should be of shape

src/transformers/models/fuyu/processing_fuyu.py

@@ -482,8 +482,7 @@ class FuyuProcessor(ProcessorMixin):
                 `is_split_into_words=True` (to lift the ambiguity with a batch of sequences).
             images (`PIL.Image.Image`, `List[PIL.Image.Image]`):
                 The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch
-                tensor. In case of a NumPy array/PyTorch tensor, each image should be of shape (C, H, W), where C is a
-                number of channels, H and W are image height and width.
+                tensor. Both channels-first and channels-last formats are supported.
 
         Returns:
             [`FuyuBatchEncoding`]: A [`FuyuBatchEncoding`] with the following fields:

src/transformers/models/git/processing_git.py

@@ -57,8 +57,7 @@ class GitProcessor(ProcessorMixin):
                 `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]`):
                 The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch
-                tensor. In case of a NumPy array/PyTorch tensor, each image should be of shape (C, H, W), where C is a
-                number of channels, H and W are image height and width.
+                tensor. Both channels-first and channels-last formats are supported.
 
             return_tensors (`str` or [`~utils.TensorType`], *optional*):
                 If set, will return tensors of a particular framework. Acceptable values are:

src/transformers/models/llava/processing_llava.py

@@ -70,8 +70,7 @@ class LlavaProcessor(ProcessorMixin):
                 `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]`):
                 The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch
-                tensor. In case of a NumPy array/PyTorch tensor, each image should be of shape (C, H, W), where C is a
-                number of channels, H and W are image height and width.
+                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:

src/transformers/models/oneformer/processing_oneformer.py

@@ -91,8 +91,7 @@ class OneFormerProcessor(ProcessorMixin):
             images (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`, `List[PIL.Image.Image]`, `List[np.ndarray]`,
             `List[torch.Tensor]`):
                 The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch
-                tensor. In case of a NumPy array/PyTorch tensor, each image should be of shape (C, H, W), where C is a
-                number of channels, H and W are image height and width.
+                tensor. Both channels-first and channels-last formats are supported.
             segmentation_maps (`ImageInput`, *optional*):
                 The corresponding semantic segmentation maps with the pixel-wise annotations.
 

src/transformers/models/owlv2/processing_owlv2.py

@@ -62,8 +62,7 @@ class Owlv2Processor(ProcessorMixin):
             images (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`, `List[PIL.Image.Image]`, `List[np.ndarray]`,
             `List[torch.Tensor]`):
                 The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch
-                tensor. In case of a NumPy array/PyTorch tensor, each image should be of shape (C, H, W), where C is a
-                number of channels, H and W are image height and width.
+                tensor. Both channels-first and channels-last formats are supported.
             query_images (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`, `List[PIL.Image.Image]`, `List[np.ndarray]`, `List[torch.Tensor]`):
                 The query image to be prepared, one query image is expected per target image to be queried. Each image
                 can be a PIL image, NumPy array or PyTorch tensor. In case of a NumPy array/PyTorch tensor, each image

src/transformers/models/owlvit/processing_owlvit.py

@@ -77,8 +77,7 @@ class OwlViTProcessor(ProcessorMixin):
             images (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`, `List[PIL.Image.Image]`, `List[np.ndarray]`,
             `List[torch.Tensor]`):
                 The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch
-                tensor. In case of a NumPy array/PyTorch tensor, each image should be of shape (C, H, W), where C is a
-                number of channels, H and W are image height and width.
+                tensor. Both channels-first and channels-last formats are supported.
             query_images (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`, `List[PIL.Image.Image]`, `List[np.ndarray]`, `List[torch.Tensor]`):
                 The query image to be prepared, one query image is expected per target image to be queried. Each image
                 can be a PIL image, NumPy array or PyTorch tensor. In case of a NumPy array/PyTorch tensor, each image

src/transformers/models/siglip/processing_siglip.py

@@ -69,8 +69,7 @@ class SiglipProcessor(ProcessorMixin):
                 `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]`):
                 The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch
-                tensor. In case of a NumPy array/PyTorch tensor, each image should be of shape (C, H, W), where C is a
-                number of channels, H and W are image height and width.
+                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:

src/transformers/models/vision_text_dual_encoder/processing_vision_text_dual_encoder.py

@@ -76,8 +76,7 @@ class VisionTextDualEncoderProcessor(ProcessorMixin):
                 `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]`):
                 The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch
-                tensor. In case of a NumPy array/PyTorch tensor, each image should be of shape (C, H, W), where C is a
-                number of channels, H and W are image height and width.
+                tensor. Both channels-first and channels-last formats are supported.
 
             return_tensors (`str` or [`~utils.TensorType`], *optional*):
                 If set, will return tensors of a particular framework. Acceptable values are: