Update inference types (automated commit)

docs/source/en/package_reference/inference_types.md

@@ -369,8 +369,6 @@ This part of the lib is still under development and will be improved in future r
 
 [[autodoc]] huggingface_hub.ZeroShotClassificationInput
 
-[[autodoc]] huggingface_hub.ZeroShotClassificationInputData
-
 [[autodoc]] huggingface_hub.ZeroShotClassificationOutputElement
 
 [[autodoc]] huggingface_hub.ZeroShotClassificationParameters
@@ -381,8 +379,6 @@ This part of the lib is still under development and will be improved in future r
 
 [[autodoc]] huggingface_hub.ZeroShotImageClassificationInput
 
-[[autodoc]] huggingface_hub.ZeroShotImageClassificationInputData
-
 [[autodoc]] huggingface_hub.ZeroShotImageClassificationOutputElement
 
 [[autodoc]] huggingface_hub.ZeroShotImageClassificationParameters
@@ -395,6 +391,6 @@ This part of the lib is still under development and will be improved in future r
 
 [[autodoc]] huggingface_hub.ZeroShotObjectDetectionInput
 
-[[autodoc]] huggingface_hub.ZeroShotObjectDetectionInputData
-
 [[autodoc]] huggingface_hub.ZeroShotObjectDetectionOutputElement
+
+[[autodoc]] huggingface_hub.ZeroShotObjectDetectionParameters

docs/source/ko/package_reference/inference_types.md

@@ -368,8 +368,6 @@ rendered properly in your Markdown viewer.
 
 [[autodoc]] huggingface_hub.ZeroShotClassificationInput
 
-[[autodoc]] huggingface_hub.ZeroShotClassificationInputData
-
 [[autodoc]] huggingface_hub.ZeroShotClassificationOutputElement
 
 [[autodoc]] huggingface_hub.ZeroShotClassificationParameters
@@ -380,8 +378,6 @@ rendered properly in your Markdown viewer.
 
 [[autodoc]] huggingface_hub.ZeroShotImageClassificationInput
 
-[[autodoc]] huggingface_hub.ZeroShotImageClassificationInputData
-
 [[autodoc]] huggingface_hub.ZeroShotImageClassificationOutputElement
 
 [[autodoc]] huggingface_hub.ZeroShotImageClassificationParameters
@@ -394,6 +390,6 @@ rendered properly in your Markdown viewer.
 
 [[autodoc]] huggingface_hub.ZeroShotObjectDetectionInput
 
-[[autodoc]] huggingface_hub.ZeroShotObjectDetectionInputData
-
 [[autodoc]] huggingface_hub.ZeroShotObjectDetectionOutputElement
+
+[[autodoc]] huggingface_hub.ZeroShotObjectDetectionParameters

src/huggingface_hub/inference/_client.py

@@ -348,7 +348,7 @@ def audio_classification(
             top_k (`int`, *optional*):
                 When specified, limits the output to the top K most probable classes.
             function_to_apply (`"AudioClassificationOutputTransform"`, *optional*):
-                The function to apply to the output.
+                The function to apply to the model outputs in order to retrieve the scores.
 
         Returns:
             `List[AudioClassificationOutputElement]`: List of [`AudioClassificationOutputElement`] items containing the predicted labels and their confidence.
@@ -1131,7 +1131,7 @@ def image_classification(
                 The model to use for image classification. Can be a model ID hosted on the Hugging Face Hub or a URL to a
                 deployed Inference Endpoint. If not provided, the default recommended model for image classification will be used.
             function_to_apply (`"ImageClassificationOutputTransform"`, *optional*):
-                The function to apply to the output.
+                The function to apply to the model outputs in order to retrieve the scores.
             top_k (`int`, *optional*):
                 When specified, limits the output to the top K most probable classes.
         Returns:
@@ -1814,7 +1814,7 @@ def text_classification(
             top_k (`int`, *optional*):
                 When specified, limits the output to the top K most probable classes.
             function_to_apply (`"TextClassificationOutputTransform"`, *optional*):
-                The function to apply to the output.
+                The function to apply to the model outputs in order to retrieve the scores.
 
         Returns:
             `List[TextClassificationOutputElement]`: a list of [`TextClassificationOutputElement`] items containing the predicted label and associated probability.
@@ -2494,11 +2494,11 @@ def text_to_speech(
             max_length (`int`, *optional*):
                 The maximum length (in tokens) of the generated text, including the input.
             max_new_tokens (`int`, *optional*):
-                The maximum number of tokens to generate. Takes precedence over maxLength.
+                The maximum number of tokens to generate. Takes precedence over max_length.
             min_length (`int`, *optional*):
                 The minimum length (in tokens) of the generated text, including the input.
             min_new_tokens (`int`, *optional*):
-                The minimum number of tokens to generate. Takes precedence over maxLength.
+                The minimum number of tokens to generate. Takes precedence over min_length.
             num_beam_groups (`int`, *optional*):
                 Number of groups to divide num_beams into in order to ensure diversity among different groups of beams.
                 See [this paper](https://hf.co/papers/1610.02424) for more details.
@@ -2801,8 +2801,8 @@ def zero_shot_classification(
                 the label likelihoods for each sequence is 1. If true, the labels are considered independent and
                 probabilities are normalized for each candidate.
             hypothesis_template (`str`, *optional*):
-                The sentence used in conjunction with candidateLabels to attempt the text classification by replacing
-                the placeholder with the candidate labels.
+                The sentence used in conjunction with `candidate_labels` to attempt the text classification by
+                replacing the placeholder with the candidate labels.
             model (`str`, *optional*):
                 The model to use for inference. Can be a model ID hosted on the Hugging Face Hub or a URL to a deployed
                 Inference Endpoint. This parameter overrides the model defined at the instance level. If not provided, the default recommended zero-shot classification model will be used.
@@ -2918,8 +2918,8 @@ def zero_shot_image_classification(
                 The model to use for inference. Can be a model ID hosted on the Hugging Face Hub or a URL to a deployed
                 Inference Endpoint. This parameter overrides the model defined at the instance level. If not provided, the default recommended zero-shot image classification model will be used.
             hypothesis_template (`str`, *optional*):
-                The sentence used in conjunction with candidateLabels to attempt the text classification by replacing
-                the placeholder with the candidate labels.
+                The sentence used in conjunction with `candidate_labels` to attempt the image classification by
+                replacing the placeholder with the candidate labels.
 
         Returns:
             `List[ZeroShotImageClassificationOutputElement]`: List of [`ZeroShotImageClassificationOutputElement`] items containing the predicted labels and their confidence.

src/huggingface_hub/inference/_generated/_async_client.py

@@ -381,7 +381,7 @@ async def audio_classification(
             top_k (`int`, *optional*):
                 When specified, limits the output to the top K most probable classes.
             function_to_apply (`"AudioClassificationOutputTransform"`, *optional*):
-                The function to apply to the output.
+                The function to apply to the model outputs in order to retrieve the scores.
 
         Returns:
             `List[AudioClassificationOutputElement]`: List of [`AudioClassificationOutputElement`] items containing the predicted labels and their confidence.
@@ -1176,7 +1176,7 @@ async def image_classification(
                 The model to use for image classification. Can be a model ID hosted on the Hugging Face Hub or a URL to a
                 deployed Inference Endpoint. If not provided, the default recommended model for image classification will be used.
             function_to_apply (`"ImageClassificationOutputTransform"`, *optional*):
-                The function to apply to the output.
+                The function to apply to the model outputs in order to retrieve the scores.
             top_k (`int`, *optional*):
                 When specified, limits the output to the top K most probable classes.
         Returns:
@@ -1876,7 +1876,7 @@ async def text_classification(
             top_k (`int`, *optional*):
                 When specified, limits the output to the top K most probable classes.
             function_to_apply (`"TextClassificationOutputTransform"`, *optional*):
-                The function to apply to the output.
+                The function to apply to the model outputs in order to retrieve the scores.
 
         Returns:
             `List[TextClassificationOutputElement]`: a list of [`TextClassificationOutputElement`] items containing the predicted label and associated probability.
@@ -2559,11 +2559,11 @@ async def text_to_speech(
             max_length (`int`, *optional*):
                 The maximum length (in tokens) of the generated text, including the input.
             max_new_tokens (`int`, *optional*):
-                The maximum number of tokens to generate. Takes precedence over maxLength.
+                The maximum number of tokens to generate. Takes precedence over max_length.
             min_length (`int`, *optional*):
                 The minimum length (in tokens) of the generated text, including the input.
             min_new_tokens (`int`, *optional*):
-                The minimum number of tokens to generate. Takes precedence over maxLength.
+                The minimum number of tokens to generate. Takes precedence over min_length.
             num_beam_groups (`int`, *optional*):
                 Number of groups to divide num_beams into in order to ensure diversity among different groups of beams.
                 See [this paper](https://hf.co/papers/1610.02424) for more details.
@@ -2870,8 +2870,8 @@ async def zero_shot_classification(
                 the label likelihoods for each sequence is 1. If true, the labels are considered independent and
                 probabilities are normalized for each candidate.
             hypothesis_template (`str`, *optional*):
-                The sentence used in conjunction with candidateLabels to attempt the text classification by replacing
-                the placeholder with the candidate labels.
+                The sentence used in conjunction with `candidate_labels` to attempt the text classification by
+                replacing the placeholder with the candidate labels.
             model (`str`, *optional*):
                 The model to use for inference. Can be a model ID hosted on the Hugging Face Hub or a URL to a deployed
                 Inference Endpoint. This parameter overrides the model defined at the instance level. If not provided, the default recommended zero-shot classification model will be used.
@@ -2989,8 +2989,8 @@ async def zero_shot_image_classification(
                 The model to use for inference. Can be a model ID hosted on the Hugging Face Hub or a URL to a deployed
                 Inference Endpoint. This parameter overrides the model defined at the instance level. If not provided, the default recommended zero-shot image classification model will be used.
             hypothesis_template (`str`, *optional*):
-                The sentence used in conjunction with candidateLabels to attempt the text classification by replacing
-                the placeholder with the candidate labels.
+                The sentence used in conjunction with `candidate_labels` to attempt the image classification by
+                replacing the placeholder with the candidate labels.
 
         Returns:
             `List[ZeroShotImageClassificationOutputElement]`: List of [`ZeroShotImageClassificationOutputElement`] items containing the predicted labels and their confidence.

src/huggingface_hub/inference/_generated/types/__init__.py

@@ -167,19 +167,17 @@
 )
 from .zero_shot_classification import (
     ZeroShotClassificationInput,
-    ZeroShotClassificationInputData,
     ZeroShotClassificationOutputElement,
     ZeroShotClassificationParameters,
 )
 from .zero_shot_image_classification import (
     ZeroShotImageClassificationInput,
-    ZeroShotImageClassificationInputData,
     ZeroShotImageClassificationOutputElement,
     ZeroShotImageClassificationParameters,
 )
 from .zero_shot_object_detection import (
     ZeroShotObjectDetectionBoundingBox,
     ZeroShotObjectDetectionInput,
-    ZeroShotObjectDetectionInputData,
     ZeroShotObjectDetectionOutputElement,
+    ZeroShotObjectDetectionParameters,
 )

src/huggingface_hub/inference/_generated/types/audio_classification.py

@@ -14,12 +14,10 @@
 
 @dataclass
 class AudioClassificationParameters(BaseInferenceType):
-    """Additional inference parameters
-    Additional inference parameters for Audio Classification
-    """
+    """Additional inference parameters for Audio Classification"""
 
     function_to_apply: Optional["AudioClassificationOutputTransform"] = None
-    """The function to apply to the output."""
+    """The function to apply to the model outputs in order to retrieve the scores."""
     top_k: Optional[int] = None
     """When specified, limits the output to the top K most probable classes."""
 
@@ -33,7 +31,7 @@ class AudioClassificationInput(BaseInferenceType):
     also provide the audio data as a raw bytes payload.
     """
     parameters: Optional[AudioClassificationParameters] = None
-    """Additional inference parameters"""
+    """Additional inference parameters for Audio Classification"""
 
 
 @dataclass

src/huggingface_hub/inference/_generated/types/automatic_speech_recognition.py

@@ -14,9 +14,7 @@
 
 @dataclass
 class AutomaticSpeechRecognitionGenerationParameters(BaseInferenceType):
-    """Parametrization of the text generation process
-    Ad-hoc parametrization of the text generation process
-    """
+    """Parametrization of the text generation process"""
 
     do_sample: Optional[bool] = None
     """Whether to use sampling instead of greedy decoding when generating new tokens."""
@@ -76,11 +74,9 @@ class AutomaticSpeechRecognitionGenerationParameters(BaseInferenceType):
 
 @dataclass
 class AutomaticSpeechRecognitionParameters(BaseInferenceType):
-    """Additional inference parameters
-    Additional inference parameters for Automatic Speech Recognition
-    """
+    """Additional inference parameters for Automatic Speech Recognition"""
 
-    generate: Optional[AutomaticSpeechRecognitionGenerationParameters] = None
+    generation_parameters: Optional[AutomaticSpeechRecognitionGenerationParameters] = None
     """Parametrization of the text generation process"""
     return_timestamps: Optional[bool] = None
     """Whether to output corresponding timestamps with the generated text"""
@@ -95,7 +91,7 @@ class AutomaticSpeechRecognitionInput(BaseInferenceType):
     also provide the audio data as a raw bytes payload.
     """
     parameters: Optional[AutomaticSpeechRecognitionParameters] = None
-    """Additional inference parameters"""
+    """Additional inference parameters for Automatic Speech Recognition"""
 
 
 @dataclass

src/huggingface_hub/inference/_generated/types/depth_estimation.py

@@ -16,7 +16,7 @@ class DepthEstimationInput(BaseInferenceType):
     inputs: Any
     """The input image data"""
     parameters: Optional[Dict[str, Any]] = None
-    """Additional inference parameters"""
+    """Additional inference parameters for Depth Estimation"""
 
 
 @dataclass

src/huggingface_hub/inference/_generated/types/document_question_answering.py

@@ -21,9 +21,7 @@ class DocumentQuestionAnsweringInputData(BaseInferenceType):
 
 @dataclass
 class DocumentQuestionAnsweringParameters(BaseInferenceType):
-    """Additional inference parameters
-    Additional inference parameters for Document Question Answering
-    """
+    """Additional inference parameters for Document Question Answering"""
 
     doc_stride: Optional[int] = None
     """If the words in the document are too long to fit with the question for the model, it will
@@ -62,7 +60,7 @@ class DocumentQuestionAnsweringInput(BaseInferenceType):
     inputs: DocumentQuestionAnsweringInputData
     """One (document, question) pair to answer"""
     parameters: Optional[DocumentQuestionAnsweringParameters] = None
-    """Additional inference parameters"""
+    """Additional inference parameters for Document Question Answering"""
 
 
 @dataclass
@@ -81,5 +79,3 @@ class DocumentQuestionAnsweringOutputElement(BaseInferenceType):
     """The start word index of the answer (in the OCR’d version of the input or provided word
     boxes).
     """
-    words: List[int]
-    """The index of each word/box pair that is in the answer"""

src/huggingface_hub/inference/_generated/types/fill_mask.py

@@ -11,9 +11,7 @@
 
 @dataclass
 class FillMaskParameters(BaseInferenceType):
-    """Additional inference parameters
-    Additional inference parameters for Fill Mask
-    """
+    """Additional inference parameters for Fill Mask"""
 
     targets: Optional[List[str]] = None
     """When passed, the model will limit the scores to the passed targets instead of looking up
@@ -32,7 +30,7 @@ class FillMaskInput(BaseInferenceType):
     inputs: str
     """The text with masked tokens"""
     parameters: Optional[FillMaskParameters] = None
-    """Additional inference parameters"""
+    """Additional inference parameters for Fill Mask"""
 
 
 @dataclass

src/huggingface_hub/inference/_generated/types/image_classification.py

@@ -14,12 +14,10 @@
 
 @dataclass
 class ImageClassificationParameters(BaseInferenceType):
-    """Additional inference parameters
-    Additional inference parameters for Image Classification
-    """
+    """Additional inference parameters for Image Classification"""
 
     function_to_apply: Optional["ImageClassificationOutputTransform"] = None
-    """The function to apply to the output."""
+    """The function to apply to the model outputs in order to retrieve the scores."""
     top_k: Optional[int] = None
     """When specified, limits the output to the top K most probable classes."""
 
@@ -33,7 +31,7 @@ class ImageClassificationInput(BaseInferenceType):
     also provide the image data as a raw bytes payload.
     """
     parameters: Optional[ImageClassificationParameters] = None
-    """Additional inference parameters"""
+    """Additional inference parameters for Image Classification"""
 
 
 @dataclass

src/huggingface_hub/inference/_generated/types/image_segmentation.py

@@ -14,9 +14,7 @@
 
 @dataclass
 class ImageSegmentationParameters(BaseInferenceType):
-    """Additional inference parameters
-    Additional inference parameters for Image Segmentation
-    """
+    """Additional inference parameters for Image Segmentation"""
 
     mask_threshold: Optional[float] = None
     """Threshold to use when turning the predicted masks into binary values."""
@@ -37,7 +35,7 @@ class ImageSegmentationInput(BaseInferenceType):
     also provide the image data as a raw bytes payload.
     """
     parameters: Optional[ImageSegmentationParameters] = None
-    """Additional inference parameters"""
+    """Additional inference parameters for Image Segmentation"""
 
 
 @dataclass

src/huggingface_hub/inference/_generated/types/image_to_image.py

@@ -19,9 +19,7 @@ class ImageToImageTargetSize(BaseInferenceType):
 
 @dataclass
 class ImageToImageParameters(BaseInferenceType):
-    """Additional inference parameters
-    Additional inference parameters for Image To Image
-    """
+    """Additional inference parameters for Image To Image"""
 
     guidance_scale: Optional[float] = None
     """For diffusion models. A higher guidance scale value encourages the model to generate
@@ -46,7 +44,7 @@ class ImageToImageInput(BaseInferenceType):
     also provide the image data as a raw bytes payload.
     """
     parameters: Optional[ImageToImageParameters] = None
-    """Additional inference parameters"""
+    """Additional inference parameters for Image To Image"""
 
 
 @dataclass