# Inference types

This page lists the types (e.g. dataclasses) available for each task supported on the Hugging Face Hub.
Each task is specified using a JSON schema, and the types are generated from these schemas - with some customization
due to Python requirements.
Visit [@huggingface.js/tasks](https://github.com/huggingface/huggingface.js/tree/main/packages/tasks/src/tasks)
to find the JSON schemas for each task.

This part of the lib is still under development and will be improved in future releases.

## audio_classification[[huggingface_hub.AudioClassificationInput]]

#### huggingface_hub.AudioClassificationInput[[huggingface_hub.AudioClassificationInput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/audio_classification.py#L25)

Inputs for Audio Classification inference

#### huggingface_hub.AudioClassificationOutputElement[[huggingface_hub.AudioClassificationOutputElement]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/audio_classification.py#L37)

Outputs for Audio Classification inference

#### huggingface_hub.AudioClassificationParameters[[huggingface_hub.AudioClassificationParameters]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/audio_classification.py#L15)

Additional inference parameters for Audio Classification

## audio_to_audio[[huggingface_hub.AudioToAudioInput]]

#### huggingface_hub.AudioToAudioInput[[huggingface_hub.AudioToAudioInput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/audio_to_audio.py#L12)

Inputs for Audio to Audio inference

#### huggingface_hub.AudioToAudioOutputElement[[huggingface_hub.AudioToAudioOutputElement]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/audio_to_audio.py#L20)

Outputs of inference for the Audio To Audio task
A generated audio file with its label.

## automatic_speech_recognition[[huggingface_hub.AutomaticSpeechRecognitionGenerationParameters]]

#### huggingface_hub.AutomaticSpeechRecognitionGenerationParameters[[huggingface_hub.AutomaticSpeechRecognitionGenerationParameters]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/automatic_speech_recognition.py#L15)

Parametrization of the text generation process

#### huggingface_hub.AutomaticSpeechRecognitionInput[[huggingface_hub.AutomaticSpeechRecognitionInput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/automatic_speech_recognition.py#L85)

Inputs for Automatic Speech Recognition inference

#### huggingface_hub.AutomaticSpeechRecognitionOutput[[huggingface_hub.AutomaticSpeechRecognitionOutput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/automatic_speech_recognition.py#L105)

Outputs of inference for the Automatic Speech Recognition task

#### huggingface_hub.AutomaticSpeechRecognitionOutputChunk[[huggingface_hub.AutomaticSpeechRecognitionOutputChunk]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/automatic_speech_recognition.py#L97)

#### huggingface_hub.AutomaticSpeechRecognitionParameters[[huggingface_hub.AutomaticSpeechRecognitionParameters]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/automatic_speech_recognition.py#L75)

Additional inference parameters for Automatic Speech Recognition

## chat_completion[[huggingface_hub.ChatCompletionInput]]

#### huggingface_hub.ChatCompletionInput[[huggingface_hub.ChatCompletionInput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/chat_completion.py#L125)

Chat Completion Input.
Auto-generated from TGI specs.
For more details, check out
https://github.com/huggingface/huggingface.js/blob/main/packages/tasks/scripts/inference-tgi-import.ts.

#### huggingface_hub.ChatCompletionInputFunctionDefinition[[huggingface_hub.ChatCompletionInputFunctionDefinition]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/chat_completion.py#L27)

#### huggingface_hub.ChatCompletionInputFunctionName[[huggingface_hub.ChatCompletionInputFunctionName]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/chat_completion.py#L106)

#### huggingface_hub.ChatCompletionInputJSONSchema[[huggingface_hub.ChatCompletionInputJSONSchema]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/chat_completion.py#L49)

#### huggingface_hub.ChatCompletionInputMessage[[huggingface_hub.ChatCompletionInputMessage]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/chat_completion.py#L41)

#### huggingface_hub.ChatCompletionInputMessageChunk[[huggingface_hub.ChatCompletionInputMessageChunk]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/chat_completion.py#L20)

#### huggingface_hub.ChatCompletionInputResponseFormatJSONObject[[huggingface_hub.ChatCompletionInputResponseFormatJSONObject]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/chat_completion.py#L84)

#### huggingface_hub.ChatCompletionInputResponseFormatJSONSchema[[huggingface_hub.ChatCompletionInputResponseFormatJSONSchema]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/chat_completion.py#L78)

#### huggingface_hub.ChatCompletionInputResponseFormatText[[huggingface_hub.ChatCompletionInputResponseFormatText]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/chat_completion.py#L73)

#### huggingface_hub.ChatCompletionInputStreamOptions[[huggingface_hub.ChatCompletionInputStreamOptions]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/chat_completion.py#L96)

#### huggingface_hub.ChatCompletionInputTool[[huggingface_hub.ChatCompletionInputTool]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/chat_completion.py#L119)

#### huggingface_hub.ChatCompletionInputToolCall[[huggingface_hub.ChatCompletionInputToolCall]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/chat_completion.py#L34)

#### huggingface_hub.ChatCompletionInputToolChoiceClass[[huggingface_hub.ChatCompletionInputToolChoiceClass]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/chat_completion.py#L111)

#### huggingface_hub.ChatCompletionInputURL[[huggingface_hub.ChatCompletionInputURL]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/chat_completion.py#L12)

#### huggingface_hub.ChatCompletionOutput[[huggingface_hub.ChatCompletionOutput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/chat_completion.py#L263)

Chat Completion Output.
Auto-generated from TGI specs.
For more details, check out
https://github.com/huggingface/huggingface.js/blob/main/packages/tasks/scripts/inference-tgi-import.ts.

#### huggingface_hub.ChatCompletionOutputComplete[[huggingface_hub.ChatCompletionOutputComplete]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/chat_completion.py#L248)

#### huggingface_hub.ChatCompletionOutputFunctionDefinition[[huggingface_hub.ChatCompletionOutputFunctionDefinition]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/chat_completion.py#L225)

#### huggingface_hub.ChatCompletionOutputLogprob[[huggingface_hub.ChatCompletionOutputLogprob]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/chat_completion.py#L213)

#### huggingface_hub.ChatCompletionOutputLogprobs[[huggingface_hub.ChatCompletionOutputLogprobs]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/chat_completion.py#L220)

#### huggingface_hub.ChatCompletionOutputMessage[[huggingface_hub.ChatCompletionOutputMessage]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/chat_completion.py#L239)

#### huggingface_hub.ChatCompletionOutputToolCall[[huggingface_hub.ChatCompletionOutputToolCall]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/chat_completion.py#L232)

#### huggingface_hub.ChatCompletionOutputTopLogprob[[huggingface_hub.ChatCompletionOutputTopLogprob]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/chat_completion.py#L207)

#### huggingface_hub.ChatCompletionOutputUsage[[huggingface_hub.ChatCompletionOutputUsage]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/chat_completion.py#L256)

#### huggingface_hub.ChatCompletionStreamOutput[[huggingface_hub.ChatCompletionStreamOutput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/chat_completion.py#L335)

Chat Completion Stream Output.
Auto-generated from TGI specs.
For more details, check out
https://github.com/huggingface/huggingface.js/blob/main/packages/tasks/scripts/inference-tgi-import.ts.

#### huggingface_hub.ChatCompletionStreamOutputChoice[[huggingface_hub.ChatCompletionStreamOutputChoice]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/chat_completion.py#L320)

#### huggingface_hub.ChatCompletionStreamOutputDelta[[huggingface_hub.ChatCompletionStreamOutputDelta]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/chat_completion.py#L293)

#### huggingface_hub.ChatCompletionStreamOutputDeltaToolCall[[huggingface_hub.ChatCompletionStreamOutputDeltaToolCall]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/chat_completion.py#L285)

#### huggingface_hub.ChatCompletionStreamOutputFunction[[huggingface_hub.ChatCompletionStreamOutputFunction]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/chat_completion.py#L279)

#### huggingface_hub.ChatCompletionStreamOutputLogprob[[huggingface_hub.ChatCompletionStreamOutputLogprob]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/chat_completion.py#L308)

#### huggingface_hub.ChatCompletionStreamOutputLogprobs[[huggingface_hub.ChatCompletionStreamOutputLogprobs]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/chat_completion.py#L315)

#### huggingface_hub.ChatCompletionStreamOutputTopLogprob[[huggingface_hub.ChatCompletionStreamOutputTopLogprob]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/chat_completion.py#L302)

#### huggingface_hub.ChatCompletionStreamOutputUsage[[huggingface_hub.ChatCompletionStreamOutputUsage]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/chat_completion.py#L328)

## depth_estimation[[huggingface_hub.DepthEstimationInput]]

#### huggingface_hub.DepthEstimationInput[[huggingface_hub.DepthEstimationInput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/depth_estimation.py#L12)

Inputs for Depth Estimation inference

#### huggingface_hub.DepthEstimationOutput[[huggingface_hub.DepthEstimationOutput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/depth_estimation.py#L22)

Outputs of inference for the Depth Estimation task

## document_question_answering[[huggingface_hub.DocumentQuestionAnsweringInput]]

#### huggingface_hub.DocumentQuestionAnsweringInput[[huggingface_hub.DocumentQuestionAnsweringInput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/document_question_answering.py#L56)

Inputs for Document Question Answering inference

#### huggingface_hub.DocumentQuestionAnsweringInputData[[huggingface_hub.DocumentQuestionAnsweringInputData]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/document_question_answering.py#L12)

One (document, question) pair to answer

#### huggingface_hub.DocumentQuestionAnsweringOutputElement[[huggingface_hub.DocumentQuestionAnsweringOutputElement]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/document_question_answering.py#L66)

Outputs of inference for the Document Question Answering task

#### huggingface_hub.DocumentQuestionAnsweringParameters[[huggingface_hub.DocumentQuestionAnsweringParameters]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/document_question_answering.py#L22)

Additional inference parameters for Document Question Answering

## feature_extraction[[huggingface_hub.FeatureExtractionInput]]

#### huggingface_hub.FeatureExtractionInput[[huggingface_hub.FeatureExtractionInput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/feature_extraction.py#L15)

Feature Extraction Input.
Auto-generated from TEI specs.
For more details, check out
https://github.com/huggingface/huggingface.js/blob/main/packages/tasks/scripts/inference-tei-import.ts.

## fill_mask[[huggingface_hub.FillMaskInput]]

#### huggingface_hub.FillMaskInput[[huggingface_hub.FillMaskInput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/fill_mask.py#L26)

Inputs for Fill Mask inference

#### huggingface_hub.FillMaskOutputElement[[huggingface_hub.FillMaskOutputElement]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/fill_mask.py#L36)

Outputs of inference for the Fill Mask task

#### huggingface_hub.FillMaskParameters[[huggingface_hub.FillMaskParameters]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/fill_mask.py#L12)

Additional inference parameters for Fill Mask

## image_classification[[huggingface_hub.ImageClassificationInput]]

#### huggingface_hub.ImageClassificationInput[[huggingface_hub.ImageClassificationInput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/image_classification.py#L25)

Inputs for Image Classification inference

#### huggingface_hub.ImageClassificationOutputElement[[huggingface_hub.ImageClassificationOutputElement]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/image_classification.py#L37)

Outputs of inference for the Image Classification task

#### huggingface_hub.ImageClassificationParameters[[huggingface_hub.ImageClassificationParameters]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/image_classification.py#L15)

Additional inference parameters for Image Classification

## image_segmentation[[huggingface_hub.ImageSegmentationInput]]

#### huggingface_hub.ImageSegmentationInput[[huggingface_hub.ImageSegmentationInput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/image_segmentation.py#L29)

Inputs for Image Segmentation inference

#### huggingface_hub.ImageSegmentationOutputElement[[huggingface_hub.ImageSegmentationOutputElement]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/image_segmentation.py#L41)

Outputs of inference for the Image Segmentation task
A predicted mask / segment

#### huggingface_hub.ImageSegmentationParameters[[huggingface_hub.ImageSegmentationParameters]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/image_segmentation.py#L15)

Additional inference parameters for Image Segmentation

## image_text_to_image[[huggingface_hub.ImageTextToImageInput]]

#### huggingface_hub.ImageTextToImageInput[[huggingface_hub.ImageTextToImageInput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/image_text_to_image.py#L48)

Inputs for Image Text To Image inference. Either inputs (image) or prompt (in parameters)
must be provided, or both.

#### huggingface_hub.ImageTextToImageOutput[[huggingface_hub.ImageTextToImageOutput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/image_text_to_image.py#L63)

Outputs of inference for the Image Text To Image task

#### huggingface_hub.ImageTextToImageParameters[[huggingface_hub.ImageTextToImageParameters]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/image_text_to_image.py#L22)

Additional inference parameters for Image Text To Image

#### huggingface_hub.ImageTextToImageTargetSize[[huggingface_hub.ImageTextToImageTargetSize]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/image_text_to_image.py#L12)

The size in pixels of the output image. This parameter is only supported by some
providers and for specific models. It will be ignored when unsupported.

## image_text_to_video[[huggingface_hub.ImageTextToVideoInput]]

#### huggingface_hub.ImageTextToVideoInput[[huggingface_hub.ImageTextToVideoInput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/image_text_to_video.py#L46)

Inputs for Image Text To Video inference. Either inputs (image) or prompt (in parameters)
must be provided, or both.

#### huggingface_hub.ImageTextToVideoOutput[[huggingface_hub.ImageTextToVideoOutput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/image_text_to_video.py#L61)

Outputs of inference for the Image Text To Video task

#### huggingface_hub.ImageTextToVideoParameters[[huggingface_hub.ImageTextToVideoParameters]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/image_text_to_video.py#L20)

Additional inference parameters for Image Text To Video

#### huggingface_hub.ImageTextToVideoTargetSize[[huggingface_hub.ImageTextToVideoTargetSize]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/image_text_to_video.py#L12)

The size in pixel of the output video frames.

## image_to_image[[huggingface_hub.ImageToImageInput]]

#### huggingface_hub.ImageToImageInput[[huggingface_hub.ImageToImageInput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/image_to_image.py#L44)

Inputs for Image To Image inference

#### huggingface_hub.ImageToImageOutput[[huggingface_hub.ImageToImageOutput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/image_to_image.py#L56)

Outputs of inference for the Image To Image task

#### huggingface_hub.ImageToImageParameters[[huggingface_hub.ImageToImageParameters]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/image_to_image.py#L22)

Additional inference parameters for Image To Image

#### huggingface_hub.ImageToImageTargetSize[[huggingface_hub.ImageToImageTargetSize]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/image_to_image.py#L12)

The size in pixels of the output image. This parameter is only supported by some
providers and for specific models. It will be ignored when unsupported.

## image_to_text[[huggingface_hub.ImageToTextGenerationParameters]]

#### huggingface_hub.ImageToTextGenerationParameters[[huggingface_hub.ImageToTextGenerationParameters]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/image_to_text.py#L15)

Parametrization of the text generation process

#### huggingface_hub.ImageToTextInput[[huggingface_hub.ImageToTextInput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/image_to_text.py#L85)

Inputs for Image To Text inference

#### huggingface_hub.ImageToTextOutput[[huggingface_hub.ImageToTextOutput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/image_to_text.py#L95)

Outputs of inference for the Image To Text task

#### huggingface_hub.ImageToTextParameters[[huggingface_hub.ImageToTextParameters]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/image_to_text.py#L75)

Additional inference parameters for Image To Text

## image_to_video[[huggingface_hub.ImageToVideoInput]]

#### huggingface_hub.ImageToVideoInput[[huggingface_hub.ImageToVideoInput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/image_to_video.py#L44)

Inputs for Image To Video inference

#### huggingface_hub.ImageToVideoOutput[[huggingface_hub.ImageToVideoOutput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/image_to_video.py#L56)

Outputs of inference for the Image To Video task

#### huggingface_hub.ImageToVideoParameters[[huggingface_hub.ImageToVideoParameters]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/image_to_video.py#L20)

Additional inference parameters for Image To Video

#### huggingface_hub.ImageToVideoTargetSize[[huggingface_hub.ImageToVideoTargetSize]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/image_to_video.py#L12)

The size in pixel of the output video frames.

## object_detection[[huggingface_hub.ObjectDetectionBoundingBox]]

#### huggingface_hub.ObjectDetectionBoundingBox[[huggingface_hub.ObjectDetectionBoundingBox]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/object_detection.py#L30)

The predicted bounding box. Coordinates are relative to the top left corner of the input
image.

#### huggingface_hub.ObjectDetectionInput[[huggingface_hub.ObjectDetectionInput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/object_detection.py#L18)

Inputs for Object Detection inference

#### huggingface_hub.ObjectDetectionOutputElement[[huggingface_hub.ObjectDetectionOutputElement]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/object_detection.py#L46)

Outputs of inference for the Object Detection task

#### huggingface_hub.ObjectDetectionParameters[[huggingface_hub.ObjectDetectionParameters]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/object_detection.py#L10)

Additional inference parameters for Object Detection

## question_answering[[huggingface_hub.QuestionAnsweringInput]]

#### huggingface_hub.QuestionAnsweringInput[[huggingface_hub.QuestionAnsweringInput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/question_answering.py#L52)

Inputs for Question Answering inference

#### huggingface_hub.QuestionAnsweringInputData[[huggingface_hub.QuestionAnsweringInputData]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/question_answering.py#L10)

One (context, question) pair to answer

#### huggingface_hub.QuestionAnsweringOutputElement[[huggingface_hub.QuestionAnsweringOutputElement]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/question_answering.py#L62)

Outputs of inference for the Question Answering task

#### huggingface_hub.QuestionAnsweringParameters[[huggingface_hub.QuestionAnsweringParameters]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/question_answering.py#L20)

Additional inference parameters for Question Answering

## sentence_similarity[[huggingface_hub.SentenceSimilarityInput]]

#### huggingface_hub.SentenceSimilarityInput[[huggingface_hub.SentenceSimilarityInput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/sentence_similarity.py#L22)

Inputs for Sentence similarity inference

#### huggingface_hub.SentenceSimilarityInputData[[huggingface_hub.SentenceSimilarityInputData]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/sentence_similarity.py#L12)

## summarization[[huggingface_hub.SummarizationInput]]

#### huggingface_hub.SummarizationInput[[huggingface_hub.SummarizationInput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/summarization.py#L27)

Inputs for Summarization inference

#### huggingface_hub.SummarizationOutput[[huggingface_hub.SummarizationOutput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/summarization.py#L37)

Outputs of inference for the Summarization task

#### huggingface_hub.SummarizationParameters[[huggingface_hub.SummarizationParameters]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/summarization.py#L15)

Additional inference parameters for summarization.

## table_question_answering[[huggingface_hub.TableQuestionAnsweringInput]]

#### huggingface_hub.TableQuestionAnsweringInput[[huggingface_hub.TableQuestionAnsweringInput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/table_question_answering.py#L40)

Inputs for Table Question Answering inference

#### huggingface_hub.TableQuestionAnsweringInputData[[huggingface_hub.TableQuestionAnsweringInputData]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/table_question_answering.py#L12)

One (table, question) pair to answer

#### huggingface_hub.TableQuestionAnsweringOutputElement[[huggingface_hub.TableQuestionAnsweringOutputElement]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/table_question_answering.py#L50)

Outputs of inference for the Table Question Answering task

#### huggingface_hub.TableQuestionAnsweringParameters[[huggingface_hub.TableQuestionAnsweringParameters]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/table_question_answering.py#L25)

Additional inference parameters for Table Question Answering

## text2text_generation[[huggingface_hub.Text2TextGenerationInput]]

#### huggingface_hub.Text2TextGenerationInput[[huggingface_hub.Text2TextGenerationInput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/text2text_generation.py#L27)

Inputs for Text2text Generation inference

#### huggingface_hub.Text2TextGenerationOutput[[huggingface_hub.Text2TextGenerationOutput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/text2text_generation.py#L37)

Outputs of inference for the Text2text Generation task

#### huggingface_hub.Text2TextGenerationParameters[[huggingface_hub.Text2TextGenerationParameters]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/text2text_generation.py#L15)

Additional inference parameters for Text2text Generation

## text_classification[[huggingface_hub.TextClassificationInput]]

#### huggingface_hub.TextClassificationInput[[huggingface_hub.TextClassificationInput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/text_classification.py#L25)

Inputs for Text Classification inference

#### huggingface_hub.TextClassificationOutputElement[[huggingface_hub.TextClassificationOutputElement]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/text_classification.py#L35)

Outputs of inference for the Text Classification task

#### huggingface_hub.TextClassificationParameters[[huggingface_hub.TextClassificationParameters]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/text_classification.py#L15)

Additional inference parameters for Text Classification

## text_generation[[huggingface_hub.TextGenerationInput]]

#### huggingface_hub.TextGenerationInput[[huggingface_hub.TextGenerationInput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/text_generation.py#L76)

Text Generation Input.
Auto-generated from TGI specs.
For more details, check out
https://github.com/huggingface/huggingface.js/blob/main/packages/tasks/scripts/inference-tgi-import.ts.

#### huggingface_hub.TextGenerationInputGenerateParameters[[huggingface_hub.TextGenerationInputGenerateParameters]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/text_generation.py#L25)

#### huggingface_hub.TextGenerationInputGrammarType[[huggingface_hub.TextGenerationInputGrammarType]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/text_generation.py#L15)

#### huggingface_hub.TextGenerationOutput[[huggingface_hub.TextGenerationOutput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/text_generation.py#L129)

Text Generation Output.
Auto-generated from TGI specs.
For more details, check out
https://github.com/huggingface/huggingface.js/blob/main/packages/tasks/scripts/inference-tgi-import.ts.

#### huggingface_hub.TextGenerationOutputBestOfSequence[[huggingface_hub.TextGenerationOutputBestOfSequence]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/text_generation.py#L107)

#### huggingface_hub.TextGenerationOutputDetails[[huggingface_hub.TextGenerationOutputDetails]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/text_generation.py#L118)

#### huggingface_hub.TextGenerationOutputPrefillToken[[huggingface_hub.TextGenerationOutputPrefillToken]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/text_generation.py#L92)

#### huggingface_hub.TextGenerationOutputToken[[huggingface_hub.TextGenerationOutputToken]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/text_generation.py#L99)

#### huggingface_hub.TextGenerationStreamOutput[[huggingface_hub.TextGenerationStreamOutput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/text_generation.py#L157)

Text Generation Stream Output.
Auto-generated from TGI specs.
For more details, check out
https://github.com/huggingface/huggingface.js/blob/main/packages/tasks/scripts/inference-tgi-import.ts.

#### huggingface_hub.TextGenerationStreamOutputStreamDetails[[huggingface_hub.TextGenerationStreamOutputStreamDetails]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/text_generation.py#L141)

#### huggingface_hub.TextGenerationStreamOutputToken[[huggingface_hub.TextGenerationStreamOutputToken]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/text_generation.py#L149)

## text_to_audio[[huggingface_hub.TextToAudioGenerationParameters]]

#### huggingface_hub.TextToAudioGenerationParameters[[huggingface_hub.TextToAudioGenerationParameters]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/text_to_audio.py#L15)

Parametrization of the text generation process

#### huggingface_hub.TextToAudioInput[[huggingface_hub.TextToAudioInput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/text_to_audio.py#L83)

Inputs for Text To Audio inference

#### huggingface_hub.TextToAudioOutput[[huggingface_hub.TextToAudioOutput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/text_to_audio.py#L93)

Outputs of inference for the Text To Audio task

#### huggingface_hub.TextToAudioParameters[[huggingface_hub.TextToAudioParameters]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/text_to_audio.py#L75)

Additional inference parameters for Text To Audio

## text_to_image[[huggingface_hub.TextToImageInput]]

#### huggingface_hub.TextToImageInput[[huggingface_hub.TextToImageInput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/text_to_image.py#L36)

Inputs for Text To Image inference

#### huggingface_hub.TextToImageOutput[[huggingface_hub.TextToImageOutput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/text_to_image.py#L46)

Outputs of inference for the Text To Image task

#### huggingface_hub.TextToImageParameters[[huggingface_hub.TextToImageParameters]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/text_to_image.py#L12)

Additional inference parameters for Text To Image

## text_to_speech[[huggingface_hub.TextToSpeechGenerationParameters]]

#### huggingface_hub.TextToSpeechGenerationParameters[[huggingface_hub.TextToSpeechGenerationParameters]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/text_to_speech.py#L15)

Parametrization of the text generation process

#### huggingface_hub.TextToSpeechInput[[huggingface_hub.TextToSpeechInput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/text_to_speech.py#L83)

Inputs for Text To Speech inference

#### huggingface_hub.TextToSpeechOutput[[huggingface_hub.TextToSpeechOutput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/text_to_speech.py#L93)

Outputs of inference for the Text To Speech task

#### huggingface_hub.TextToSpeechParameters[[huggingface_hub.TextToSpeechParameters]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/text_to_speech.py#L75)

Additional inference parameters for Text To Speech

## text_to_video[[huggingface_hub.TextToVideoInput]]

#### huggingface_hub.TextToVideoInput[[huggingface_hub.TextToVideoInput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/text_to_video.py#L32)

Inputs for Text To Video inference

#### huggingface_hub.TextToVideoOutput[[huggingface_hub.TextToVideoOutput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/text_to_video.py#L42)

Outputs of inference for the Text To Video task

#### huggingface_hub.TextToVideoParameters[[huggingface_hub.TextToVideoParameters]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/text_to_video.py#L12)

Additional inference parameters for Text To Video

## token_classification[[huggingface_hub.TokenClassificationInput]]

#### huggingface_hub.TokenClassificationInput[[huggingface_hub.TokenClassificationInput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/token_classification.py#L27)

Inputs for Token Classification inference

#### huggingface_hub.TokenClassificationOutputElement[[huggingface_hub.TokenClassificationOutputElement]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/token_classification.py#L37)

Outputs of inference for the Token Classification task

#### huggingface_hub.TokenClassificationParameters[[huggingface_hub.TokenClassificationParameters]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/token_classification.py#L15)

Additional inference parameters for Token Classification

## translation[[huggingface_hub.TranslationInput]]

#### huggingface_hub.TranslationInput[[huggingface_hub.TranslationInput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/translation.py#L35)

Inputs for Translation inference

#### huggingface_hub.TranslationOutput[[huggingface_hub.TranslationOutput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/translation.py#L45)

Outputs of inference for the Translation task

#### huggingface_hub.TranslationParameters[[huggingface_hub.TranslationParameters]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/translation.py#L15)

Additional inference parameters for Translation

## video_classification[[huggingface_hub.VideoClassificationInput]]

#### huggingface_hub.VideoClassificationInput[[huggingface_hub.VideoClassificationInput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/video_classification.py#L29)

Inputs for Video Classification inference

#### huggingface_hub.VideoClassificationOutputElement[[huggingface_hub.VideoClassificationOutputElement]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/video_classification.py#L39)

Outputs of inference for the Video Classification task

#### huggingface_hub.VideoClassificationParameters[[huggingface_hub.VideoClassificationParameters]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/video_classification.py#L15)

Additional inference parameters for Video Classification

## visual_question_answering[[huggingface_hub.VisualQuestionAnsweringInput]]

#### huggingface_hub.VisualQuestionAnsweringInput[[huggingface_hub.VisualQuestionAnsweringInput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/visual_question_answering.py#L33)

Inputs for Visual Question Answering inference

#### huggingface_hub.VisualQuestionAnsweringInputData[[huggingface_hub.VisualQuestionAnsweringInputData]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/visual_question_answering.py#L12)

One (image, question) pair to answer

#### huggingface_hub.VisualQuestionAnsweringOutputElement[[huggingface_hub.VisualQuestionAnsweringOutputElement]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/visual_question_answering.py#L43)

Outputs of inference for the Visual Question Answering task

#### huggingface_hub.VisualQuestionAnsweringParameters[[huggingface_hub.VisualQuestionAnsweringParameters]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/visual_question_answering.py#L22)

Additional inference parameters for Visual Question Answering

## zero_shot_classification[[huggingface_hub.ZeroShotClassificationInput]]

#### huggingface_hub.ZeroShotClassificationInput[[huggingface_hub.ZeroShotClassificationInput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/zero_shot_classification.py#L27)

Inputs for Zero Shot Classification inference

#### huggingface_hub.ZeroShotClassificationOutputElement[[huggingface_hub.ZeroShotClassificationOutputElement]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/zero_shot_classification.py#L37)

Outputs of inference for the Zero Shot Classification task

#### huggingface_hub.ZeroShotClassificationParameters[[huggingface_hub.ZeroShotClassificationParameters]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/zero_shot_classification.py#L10)

Additional inference parameters for Zero Shot Classification

## zero_shot_image_classification[[huggingface_hub.ZeroShotImageClassificationInput]]

#### huggingface_hub.ZeroShotImageClassificationInput[[huggingface_hub.ZeroShotImageClassificationInput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/zero_shot_image_classification.py#L22)

Inputs for Zero Shot Image Classification inference

#### huggingface_hub.ZeroShotImageClassificationOutputElement[[huggingface_hub.ZeroShotImageClassificationOutputElement]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/zero_shot_image_classification.py#L32)

Outputs of inference for the Zero Shot Image Classification task

#### huggingface_hub.ZeroShotImageClassificationParameters[[huggingface_hub.ZeroShotImageClassificationParameters]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/zero_shot_image_classification.py#L10)

Additional inference parameters for Zero Shot Image Classification

## zero_shot_object_detection[[huggingface_hub.ZeroShotObjectDetectionBoundingBox]]

#### huggingface_hub.ZeroShotObjectDetectionBoundingBox[[huggingface_hub.ZeroShotObjectDetectionBoundingBox]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/zero_shot_object_detection.py#L28)

The predicted bounding box. Coordinates are relative to the top left corner of the input
image.

#### huggingface_hub.ZeroShotObjectDetectionInput[[huggingface_hub.ZeroShotObjectDetectionInput]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/zero_shot_object_detection.py#L18)

Inputs for Zero Shot Object Detection inference

#### huggingface_hub.ZeroShotObjectDetectionOutputElement[[huggingface_hub.ZeroShotObjectDetectionOutputElement]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/zero_shot_object_detection.py#L40)

Outputs of inference for the Zero Shot Object Detection task

#### huggingface_hub.ZeroShotObjectDetectionParameters[[huggingface_hub.ZeroShotObjectDetectionParameters]]

[Source](https://github.com/huggingface/huggingface_hub/blob/v1.12.1/src/huggingface_hub/inference/_generated/types/zero_shot_object_detection.py#L10)

Additional inference parameters for Zero Shot Object Detection