Docstring check (#26052)

* Fix number of minimal calls to the Hub with peft integration

* Alternate design

* And this way?

* Revert

* Nits to fix

* Add util

* Print when changes are made

* Add list to ignore

* Add more rules

* Manual fixes

* deal with kwargs

* deal with enum defaults

* avoid many digits for floats

* Manual fixes

* Fix regex

* Fix regex

* Auto fix

* Style

* Apply script

* Add ignored list

* Add check that templates are filled

* Adding to CI checks

* Add back semi-fix

* Ignore more objects

* More auto-fixes

* Ignore missing objects

* Remove temp semi-fix

* Fixes

* Update src/transformers/models/pvt/configuration_pvt.py
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

* Update utils/check_docstrings.py
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

* Update src/transformers/utils/quantization_config.py
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

* Deal with float defaults

* Fix small defaults

* Address review comment

* Treat

* Post-rebase cleanup

* Address review comment

* Update src/transformers/models/deprecated/mctct/configuration_mctct.py
Co-authored-by: Lysandre Debut <lysandre.debut@reseau.eseo.fr>

* Address review comment

---------
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
Co-authored-by: Lysandre Debut <lysandre.debut@reseau.eseo.fr>

src/transformers/models/pix2struct/configuration_pix2struct.py

@@ -195,7 +195,7 @@ class Pix2StructVisionConfig(PretrainedConfig):
         dense_act_fn (`str` or `function`, *optional*, defaults to `"gelu_new"`):
             The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
             `"relu"`, `"selu"` and `"gelu_new"` ``"gelu"` are supported.
-        layer_norm_eps (`float`, *optional*, defaults to 1e-6):
+        layer_norm_eps (`float`, *optional*, defaults to 1e-06):
             The epsilon used by the layer normalization layers.
         dropout_rate (`float`, *optional*, defaults to 0.0):
             The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
@@ -203,7 +203,7 @@ class Pix2StructVisionConfig(PretrainedConfig):
             The dropout ratio for the attention probabilities.
         initializer_range (`float`, *optional*, defaults to 1e-10):
             The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
-        initializer_factor (`float``, *optional*, defaults to 1):
+        initializer_factor (`float``, *optional*, defaults to 1.0):
             A factor for initializing all weight matrices (should be kept to 1, used internally for initialization
             testing).
         seq_len (`int`, *optional*, defaults to 4096):

src/transformers/models/poolformer/configuration_poolformer.py

@@ -71,7 +71,7 @@ class PoolFormerConfig(PretrainedConfig):
             The activation function for the hidden layers.
         use_layer_scale (`bool`, *optional*, defaults to `True`):
             Whether to use layer scale.
-        layer_scale_init_value (`float`, *optional*, defaults to 1e-5):
+        layer_scale_init_value (`float`, *optional*, defaults to 1e-05):
             The initial value for the layer scale.
         initializer_range (`float`, *optional*, defaults to 0.02):
             The initializer range for the weights.

src/transformers/models/poolformer/image_processing_poolformer.py

@@ -68,10 +68,10 @@ class PoolFormerImageProcessor(BaseImageProcessor):
               whilst maintaining the aspect ratio.
             - size is `{"shortest_edge": c}`: the shortest edge of the image is resized to `int(floor(c/crop_pct)`
               whilst maintaining the aspect ratio.
-        crop_pct (`float`, *optional*, defaults to `0.9`):
+        crop_pct (`float`, *optional*, defaults to 0.9):
             Percentage of the image to crop from the center. Can be overridden by `crop_pct` in the `preprocess`
             method.
-        resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BICUBIC`):
+        resample (`PILImageResampling`, *optional*, defaults to `Resampling.BICUBIC`):
             Resampling filter to use if resizing the image. Can be overridden by `resample` in the `preprocess` method.
         do_center_crop (`bool`, *optional*, defaults to `True`):
             Whether to center crop the image. If the input size is smaller than `crop_size` along any edge, the image
@@ -80,12 +80,12 @@ class PoolFormerImageProcessor(BaseImageProcessor):
         crop_size (`Dict[str, int]`, *optional*, defaults to `{"height": 224, "width": 224}`):
             Size of the image after applying center crop. Only has an effect if `do_center_crop` is set to `True`. Can
             be overridden by the `crop_size` parameter in the `preprocess` method.
-        do_rescale (`bool`, *optional*, defaults to `True`):
-            Whether to rescale the image by the specified scale `rescale_factor`. Can be overridden by the `do_rescale`
-            parameter in the `preprocess` method.
         rescale_factor (`int` or `float`, *optional*, defaults to `1/255`):
             Scale factor to use if rescaling the image. Can be overridden by the `rescale_factor` parameter in the
             `preprocess` method.
+        do_rescale (`bool`, *optional*, defaults to `True`):
+            Whether to rescale the image by the specified scale `rescale_factor`. Can be overridden by the `do_rescale`
+            parameter in the `preprocess` method.
         do_normalize (`bool`, *optional*, defaults to `True`):
             Controls whether to normalize the image. Can be overridden by the `do_normalize` parameter in the
             `preprocess` method.

src/transformers/models/prophetnet/tokenization_prophetnet.py

@@ -313,9 +313,6 @@ class ProphetNetTokenizer(PreTrainedTokenizer):
             used to separate bullet-point like sentences in summarization, *e.g.*.
         pad_token (`str`, *optional*, defaults to `"[PAD]"`):
             The token used for padding, for example when batching sequences of different lengths.
-        cls_token (`str`, *optional*, defaults to `"[CLS]"`):
-            The classifier token which is used when doing sequence classification (classification of the whole sequence
-            instead of per-token classification). It is the first token of the sequence when built with special tokens.
         mask_token (`str`, *optional*, defaults to `"[MASK]"`):
             The token used for masking values. This is the token used when training this model with masked language
             modeling. This is the token which the model will try to predict.

src/transformers/models/pvt/configuration_pvt.py

@@ -49,7 +49,7 @@ class PvtConfig(PretrainedConfig):
             The input image size
         num_channels (`int`, *optional*, defaults to 3):
             The number of input channels.
-        num_encoder_blocks (`[int]`, *optional*., defaults to 4):
+        num_encoder_blocks (`int`, *optional*, defaults to 4):
             The number of encoder blocks (i.e. stages in the Mix Transformer encoder).
         depths (`List[int]`, *optional*, defaults to `[2, 2, 2, 2]`):
             The number of layers in each encoder block.
@@ -77,11 +77,11 @@ class PvtConfig(PretrainedConfig):
             The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
         drop_path_rate (`float`, *optional*, defaults to 0.0):
             The dropout probability for stochastic depth, used in the blocks of the Transformer encoder.
-        layer_norm_eps (`float`, *optional*, defaults to 1e-6):
+        layer_norm_eps (`float`, *optional*, defaults to 1e-06):
             The epsilon used by the layer normalization layers.
         qkv_bias (`bool`, *optional*, defaults to `True`):
             Whether or not a learnable bias should be added to the queries, keys and values.
-        num_labels ('int', *optional*, defaults to 1000)
+        num_labels ('int', *optional*, defaults to 1000):
             The number of classes.
     Example:
 

src/transformers/models/pvt/image_processing_pvt.py

@@ -49,7 +49,7 @@ class PvtImageProcessor(BaseImageProcessor):
         size (`dict`, *optional*, defaults to `{"height": 224, "width": 224}`):
             Size of the output image after resizing. Can be overridden by the `size` parameter in the `preprocess`
             method.
-        resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BILINEAR`):
+        resample (`PILImageResampling`, *optional*, defaults to `Resampling.BILINEAR`):
             Resampling filter to use if resizing the image. Can be overridden by the `resample` parameter in the
             `preprocess` method.
         do_rescale (`bool`, *optional*, defaults to `True`):
@@ -58,7 +58,7 @@ class PvtImageProcessor(BaseImageProcessor):
         rescale_factor (`int` or `float`, *optional*, defaults to `1/255`):
             Scale factor to use if rescaling the image. Can be overridden by the `rescale_factor` parameter in the
             `preprocess` method.
-        do_normalize (`bool`, *optional*, defaults to `True):
+        do_normalize (`bool`, *optional*, defaults to `True`):
             Whether to normalize the image. Can be overridden by the `do_normalize` parameter in the `preprocess`
             method.
         image_mean (`float` or `List[float]`, *optional*, defaults to `IMAGENET_DEFAULT_MEAN`):

src/transformers/models/reformer/tokenization_reformer.py

@@ -69,9 +69,7 @@ class ReformerTokenizer(PreTrainedTokenizer):
         unk_token (`str`, *optional*, defaults to `"<unk>"`):
             The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this
             token instead.
-        pad_token (`str`, *optional*, defaults to `"<pad>"`):
-            The token used for padding, for example when batching sequences of different lengths.
-        additional_special_tokens (`List[str]`, *optional*):
+        additional_special_tokens (`List[str]`, *optional*, defaults to `[]`):
             Additional special tokens used by the tokenizer.
         sp_model_kwargs (`dict`, *optional*):
             Will be passed to the `SentencePieceProcessor.__init__()` method. The [Python wrapper for

src/transformers/models/sam/configuration_sam.py

@@ -104,7 +104,7 @@ class SamMaskDecoderConfig(PretrainedConfig):
             The number of layers in the IoU head module.
         iou_head_hidden_dim (`int`, *optional*, defaults to 256):
             The dimensionality of the hidden states in the IoU head module.
-        layer_norm_eps (`float`, *optional*, defaults to 1e-6):
+        layer_norm_eps (`float`, *optional*, defaults to 1e-06):
             The epsilon used by the layer normalization layers.
 
     """
@@ -163,7 +163,7 @@ class SamVisionConfig(PretrainedConfig):
             Size of the patches to be extracted from the input image.
         hidden_act (`str`, *optional*, defaults to `"gelu"`):
             The non-linear activation function (function or string)
-        layer_norm_eps (`float`, *optional*, defaults to 1e-6):
+        layer_norm_eps (`float`, *optional*, defaults to 1e-06):
             The epsilon used by the layer normalization layers.
         attention_dropout (`float`, *optional*, defaults to 0.0):
             The dropout ratio for the attention probabilities.
@@ -173,9 +173,9 @@ class SamVisionConfig(PretrainedConfig):
             Whether to add a bias to query, key, value projections.
         mlp_ratio (`float`, *optional*, defaults to 4.0):
             Ratio of mlp hidden dim to embedding dim.
-        use_abs_pos (`bool`, *optional*, defaults to True):
+        use_abs_pos (`bool`, *optional*, defaults to `True`):
             Whether to use absolute position embedding.
-        use_rel_pos (`bool`, *optional*, defaults to True):
+        use_rel_pos (`bool`, *optional*, defaults to `True`):
             Whether to use relative position embedding.
         window_size (`int`, *optional*, defaults to 14):
             Window size for relative position.
@@ -183,7 +183,7 @@ class SamVisionConfig(PretrainedConfig):
             The indexes of the global attention layers.
         num_pos_feats (`int`, *optional*, defaults to 128):
             The dimensionality of the position embedding.
-        mlp_dim (`int`, *optional*, defaults to None):
+        mlp_dim (`int`, *optional*):
             The dimensionality of the MLP layer in the Transformer encoder. If `None`, defaults to `mlp_ratio *
             hidden_size`.
     """

src/transformers/models/sam/image_processing_sam.py

@@ -73,7 +73,7 @@ class SamImageProcessor(BaseImageProcessor):
             Size of the output image after resizing. Resizes the longest edge of the image to match
             `size["longest_edge"]` while maintaining the aspect ratio. Can be overridden by the `size` parameter in the
             `preprocess` method.
-        resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BICUBIC`):
+        resample (`PILImageResampling`, *optional*, defaults to `Resampling.BILINEAR`):
             Resampling filter to use if resizing the image. Can be overridden by the `resample` parameter in the
             `preprocess` method.
         do_rescale (`bool`, *optional*, defaults to `True`):

src/transformers/models/segformer/configuration_segformer.py

@@ -51,19 +51,19 @@ class SegformerConfig(PretrainedConfig):
             The number of input channels.
         num_encoder_blocks (`int`, *optional*, defaults to 4):
             The number of encoder blocks (i.e. stages in the Mix Transformer encoder).
-        depths (`List[int]`, *optional*, defaults to [2, 2, 2, 2]):
+        depths (`List[int]`, *optional*, defaults to `[2, 2, 2, 2]`):
             The number of layers in each encoder block.
-        sr_ratios (`List[int]`, *optional*, defaults to [8, 4, 2, 1]):
+        sr_ratios (`List[int]`, *optional*, defaults to `[8, 4, 2, 1]`):
             Sequence reduction ratios in each encoder block.
-        hidden_sizes (`List[int]`, *optional*, defaults to [32, 64, 160, 256]):
+        hidden_sizes (`List[int]`, *optional*, defaults to `[32, 64, 160, 256]`):
             Dimension of each of the encoder blocks.
-        patch_sizes (`List[int]`, *optional*, defaults to [7, 3, 3, 3]):
+        patch_sizes (`List[int]`, *optional*, defaults to `[7, 3, 3, 3]`):
             Patch size before each encoder block.
-        strides (`List[int]`, *optional*, defaults to [4, 2, 2, 2]):
+        strides (`List[int]`, *optional*, defaults to `[4, 2, 2, 2]`):
             Stride before each encoder block.
-        num_attention_heads (`List[int]`, *optional*, defaults to [1, 2, 5, 8]):
+        num_attention_heads (`List[int]`, *optional*, defaults to `[1, 2, 5, 8]`):
             Number of attention heads for each attention layer in each block of the Transformer encoder.
-        mlp_ratios (`List[int]`, *optional*, defaults to [4, 4, 4, 4]):
+        mlp_ratios (`List[int]`, *optional*, defaults to `[4, 4, 4, 4]`):
             Ratio of the size of the hidden layer compared to the size of the input layer of the Mix FFNs in the
             encoder blocks.
         hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`):
@@ -79,7 +79,7 @@ class SegformerConfig(PretrainedConfig):
             The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
         drop_path_rate (`float`, *optional*, defaults to 0.1):
             The dropout probability for stochastic depth, used in the blocks of the Transformer encoder.
-        layer_norm_eps (`float`, *optional*, defaults to 1e-6):
+        layer_norm_eps (`float`, *optional*, defaults to 1e-06):
             The epsilon used by the layer normalization layers.
         decoder_hidden_size (`int`, *optional*, defaults to 256):
             The dimension of the all-MLP decode head.

src/transformers/models/segformer/image_processing_segformer.py

@@ -57,7 +57,7 @@ class SegformerImageProcessor(BaseImageProcessor):
         size (`Dict[str, int]` *optional*, defaults to `{"height": 512, "width": 512}`):
             Size of the output image after resizing. Can be overridden by the `size` parameter in the `preprocess`
             method.
-        resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BILINEAR`):
+        resample (`PILImageResampling`, *optional*, defaults to `Resampling.BILINEAR`):
             Resampling filter to use if resizing the image. Can be overridden by the `resample` parameter in the
             `preprocess` method.
         do_rescale (`bool`, *optional*, defaults to `True`):

src/transformers/models/speech_to_text/feature_extraction_speech_to_text.py

@@ -41,13 +41,13 @@ class Speech2TextFeatureExtractor(SequenceFeatureExtractor):
     mean and variance normalization to the extracted features.
 
     Args:
-        feature_size (`int`, defaults to 80):
+        feature_size (`int`, *optional*, defaults to 80):
             The feature dimension of the extracted features.
-        sampling_rate (`int`, defaults to 16000):
+        sampling_rate (`int`, *optional*, defaults to 16000):
             The sampling rate at which the audio files should be digitalized expressed in hertz (Hz).
-        num_mel_bins (`int`, defaults to 80):
+        num_mel_bins (`int`, *optional*, defaults to 80):
             Number of Mel-frequency bins.
-        padding_value (`float`, defaults to 0.0):
+        padding_value (`float`, *optional*, defaults to 0.0):
             The value that is used to fill the padding vectors.
         do_ceptral_normalize (`bool`, *optional*, defaults to `True`):
             Whether or not to apply utterance-level cepstral mean and variance normalization to extracted features.

src/transformers/models/speecht5/tokenization_speecht5.py

@@ -56,10 +56,10 @@ class SpeechT5Tokenizer(PreTrainedTokenizer):
         vocab_file (`str`):
             [SentencePiece](https://github.com/google/sentencepiece) file (generally has a *.spm* extension) that
             contains the vocabulary necessary to instantiate a tokenizer.
-        eos_token (`str`, *optional*, defaults to `"</s>"`):
-            The end of sequence token.
         bos_token (`str`, *optional*, defaults to `"<s>"`):
             The begin of sequence token.
+        eos_token (`str`, *optional*, defaults to `"</s>"`):
+            The end of sequence token.
         unk_token (`str`, *optional*, defaults to `"<unk>"`):
             The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this
             token instead.

src/transformers/models/swiftformer/configuration_swiftformer.py

@@ -51,7 +51,7 @@ class SwiftFormerConfig(PretrainedConfig):
             The embedding dimension at each stage
         mlp_ratio (`int`, *optional*, defaults to 4):
             Ratio of size of the hidden dimensionality of an MLP to the dimensionality of its input.
-        downsamples (`List[bool]`, *optional*, defaults to `[True, True, True, True]`)
+        downsamples (`List[bool]`, *optional*, defaults to `[True, True, True, True]`):
             Whether or not to downsample inputs between two stages.
         hidden_act (`str`, *optional*, defaults to `"gelu"`):
             The non-linear activation function (string). `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` are supported.
@@ -61,13 +61,13 @@ class SwiftFormerConfig(PretrainedConfig):
             The stride of convolution kernels in downsampling layers.
         down_pad (`int`, *optional*, defaults to 1):
             Padding in downsampling layers.
-        drop_path_rate (`float`, *optional*, defaults to 0.):
+        drop_path_rate (`float`, *optional*, defaults to 0.0):
             Rate at which to increase dropout probability in DropPath.
         use_layer_scale (`bool`, *optional*, defaults to `True`):
             Whether to scale outputs from token mixers.
-        layer_scale_init_value (`float`, *optional*, defaults to 1e-5):
+        layer_scale_init_value (`float`, *optional*, defaults to 1e-05):
             Factor by which outputs from token mixers are scaled.
-        batch_norm_eps (`float`, *optional*, defaults to 1e-5):
+        batch_norm_eps (`float`, *optional*, defaults to 1e-05):
             The epsilon used by the batch normalization layers.
 
 

src/transformers/models/swin/configuration_swin.py

@@ -55,15 +55,15 @@ class SwinConfig(BackboneConfigMixin, PretrainedConfig):
             The number of input channels.
         embed_dim (`int`, *optional*, defaults to 96):
             Dimensionality of patch embedding.
-        depths (`list(int)`, *optional*, defaults to [2, 2, 6, 2]):
+        depths (`list(int)`, *optional*, defaults to `[2, 2, 6, 2]`):
             Depth of each layer in the Transformer encoder.
-        num_heads (`list(int)`, *optional*, defaults to [3, 6, 12, 24]):
+        num_heads (`list(int)`, *optional*, defaults to `[3, 6, 12, 24]`):
             Number of attention heads in each layer of the Transformer encoder.
         window_size (`int`, *optional*, defaults to 7):
             Size of windows.
         mlp_ratio (`float`, *optional*, defaults to 4.0):
             Ratio of MLP hidden dimensionality to embedding dimensionality.
-        qkv_bias (`bool`, *optional*, defaults to True):
+        qkv_bias (`bool`, *optional*, defaults to `True`):
             Whether or not a learnable bias should be added to the queries, keys and values.
         hidden_dropout_prob (`float`, *optional*, defaults to 0.0):
             The dropout probability for all fully connected layers in the embeddings and encoder.
@@ -74,13 +74,13 @@ class SwinConfig(BackboneConfigMixin, PretrainedConfig):
         hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`):
             The non-linear activation function (function or string) in the encoder. If string, `"gelu"`, `"relu"`,
             `"selu"` and `"gelu_new"` are supported.
-        use_absolute_embeddings (`bool`, *optional*, defaults to False):
+        use_absolute_embeddings (`bool`, *optional*, defaults to `False`):
             Whether or not to add absolute position embeddings to the patch embeddings.
         initializer_range (`float`, *optional*, defaults to 0.02):
             The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
-        layer_norm_eps (`float`, *optional*, defaults to 1e-12):
+        layer_norm_eps (`float`, *optional*, defaults to 1e-05):
             The epsilon used by the layer normalization layers.
-        encoder_stride (`int`, `optional`, defaults to 32):
+        encoder_stride (`int`, *optional*, defaults to 32):
             Factor to increase the spatial resolution by in the decoder head for masked image modeling.
         out_features (`List[str]`, *optional*):
             If used as backbone, list of features to output. Can be any of `"stem"`, `"stage1"`, `"stage2"`, etc.

src/transformers/models/swin2sr/configuration_swin2sr.py

@@ -69,12 +69,12 @@ class Swin2SRConfig(PretrainedConfig):
             Whether or not to add absolute position embeddings to the patch embeddings.
         initializer_range (`float`, *optional*, defaults to 0.02):
             The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
-        layer_norm_eps (`float`, *optional*, defaults to 1e-12):
+        layer_norm_eps (`float`, *optional*, defaults to 1e-05):
             The epsilon used by the layer normalization layers.
         upscale (`int`, *optional*, defaults to 2):
             The upscale factor for the image. 2/3/4/8 for image super resolution, 1 for denoising and compress artifact
             reduction
-        img_range (`float`, *optional*, defaults to 1.):
+        img_range (`float`, *optional*, defaults to 1.0):
             The range of the values of the input image.
         resi_connection (`str`, *optional*, defaults to `"1conv"`):
             The convolutional block to use before the residual connection in each stage.

src/transformers/models/swinv2/configuration_swinv2.py

@@ -70,9 +70,9 @@ class Swinv2Config(PretrainedConfig):
             Whether or not to add absolute position embeddings to the patch embeddings.
         initializer_range (`float`, *optional*, defaults to 0.02):
             The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
-        layer_norm_eps (`float`, *optional*, defaults to 1e-12):
+        layer_norm_eps (`float`, *optional*, defaults to 1e-05):
             The epsilon used by the layer normalization layers.
-        encoder_stride (`int`, `optional`, defaults to 32):
+        encoder_stride (`int`, *optional*, defaults to 32):
             Factor to increase the spatial resolution by in the decoder head for masked image modeling.
 
     Example:

src/transformers/models/timesformer/configuration_timesformer.py

@@ -62,7 +62,7 @@ class TimesformerConfig(PretrainedConfig):
             The dropout ratio for the attention probabilities.
         initializer_range (`float`, *optional*, defaults to 0.02):
             The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
-        layer_norm_eps (`float`, *optional*, defaults to 1e-6):
+        layer_norm_eps (`float`, *optional*, defaults to 1e-06):
             The epsilon used by the layer normalization layers.
         qkv_bias (`bool`, *optional*, defaults to `True`):
             Whether to add a bias to the queries, keys and values.

src/transformers/models/transfo_xl/tokenization_transfo_xl.py

@@ -154,7 +154,7 @@ class TransfoXLTokenizer(PreTrainedTokenizer):
             token instead.
         eos_token (`str`, *optional*, defaults to `"<eos>"`):
             The end of sequence token.
-        additional_special_tokens (`List[str]`, *optional*, defaults to `["<formula>"]`):
+        additional_special_tokens (`List[str]`, *optional*, defaults to `['<formula>']`):
             A list of additional special tokens (for the HuggingFace functionality).
         language (`str`, *optional*, defaults to `"en"`):
             The language of this tokenizer (used for mose preprocessing).

src/transformers/models/trocr/processing_trocr.py

@@ -30,9 +30,9 @@ class TrOCRProcessor(ProcessorMixin):
     more information.
 
     Args:
-        image_processor ([`ViTImageProcessor`/`DeiTImageProcessor`]):
+        image_processor ([`ViTImageProcessor`/`DeiTImageProcessor`], *optional*):
             An instance of [`ViTImageProcessor`/`DeiTImageProcessor`]. The image processor is a required input.
-        tokenizer ([`RobertaTokenizer`/`XLMRobertaTokenizer`]):
+        tokenizer ([`RobertaTokenizer`/`XLMRobertaTokenizer`], *optional*):
             An instance of [`RobertaTokenizer`/`XLMRobertaTokenizer`]. The tokenizer is a required input.
     """
     attributes = ["image_processor", "tokenizer"]