# @huggingface/inference

## Namespaces

- [trechos de código](modules/snippets)

## Classes

- [HfInference](classes/HfInference)
- [InferenceClient](classes/InferenceClient)
- [InferenceClientEndpoint](classes/InferenceClientEndpoint)
- [InferenceClientError](classes/InferenceClientError)
- [InferenceClientHubApiError](classes/InferenceClientHubApiError)
- [InferenceClientInputError](classes/InferenceClientInputError)
- [InferenceClientProviderApiError](classes/InferenceClientProviderApiError)
- [InferenceClientProviderOutputError](classes/InferenceClientProviderOutputError)
- [InferenceClientRoutingError](classes/InferenceClientRoutingError)

## Interfaces

- [AudioToAudioOutput](interfaces/AudioToAudioOutput)
- [AudioToAudioOutputElem](interfaces/AudioToAudioOutputElem)
- [BaseArgs](interfaces/BaseArgs)
- [BodyParams](interfaces/BodyParams)
- [HeaderParams](interfaces/HeaderParams)
- [InferenceProviderMappingEntry](interfaces/InferenceProviderMappingEntry)
- [Logger](interfaces/Logger)
- [Opções](interfaces/Options)
- [TextGenerationInput](interfaces/TextGenerationInput)
- [TextGenerationOutput](interfaces/TextGenerationOutput)
- [TextGenerationStreamBestOfSequence](interfaces/TextGenerationStreamBestOfSequence)
- [TextGenerationStreamDetails](interfaces/TextGenerationStreamDetails)
- [TextGenerationStreamOutput](interfaces/TextGenerationStreamOutput)
- [TextGenerationStreamPrefillToken](interfaces/TextGenerationStreamPrefillToken)
- [TextGenerationStreamToken](interfaces/TextGenerationStreamToken)
- [UrlParams](interfaces/UrlParams)

## Aliases de Tipo

### AudioClassificationArgs

Ƭ **AudioClassificationArgs**: [`BaseArgs`](interfaces/BaseArgs) & `AudioClassificationInput` \| `LegacyAudioInput`

#### Definido em[[audioclassificationargs.defined-in]]

[inference/src/tasks/audio/audioClassification.ts:9](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/audio/audioClassification.ts#L9)

___

### AudioToAudioArgs

Ƭ **AudioToAudioArgs**: [`BaseArgs`](interfaces/BaseArgs) & \{ `inputs`: `Blob`  } \| `LegacyAudioInput`

#### Definido em[[audiotoaudioargs.defined-in]]

[inference/src/tasks/audio/audioToAudio.ts:8](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/audio/audioToAudio.ts#L8)

___

### AuthMethod

Ƭ **AuthMethod**: ``"none"`` \| ``"hf-token"`` \| ``"credentials-include"`` \| ``"provider-key"``

#### Definido em[[authmethod.defined-in]]

[inference/src/types.ts:165](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/types.ts#L165)

___

### AutomaticSpeechRecognitionArgs

Ƭ **AutomaticSpeechRecognitionArgs**: [`BaseArgs`](interfaces/BaseArgs) & `AutomaticSpeechRecognitionInput` \| `LegacyAudioInput`

#### Definido em[[automaticspeechrecognitionargs.defined-in]]

[inference/src/tasks/audio/automaticSpeechRecognition.ts:8](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/audio/automaticSpeechRecognition.ts#L8)

___

### DocumentQuestionAnsweringArgs

Ƭ **DocumentQuestionAnsweringArgs**: [`BaseArgs`](interfaces/BaseArgs) & `DocumentQuestionAnsweringInput` & \{ `inputs`: `DocumentQuestionAnsweringInputData` & \{ `image`: `Blob`  }  }

#### Definido em[[documentquestionansweringargs.defined-in]]

[inference/src/tasks/multimodal/documentQuestionAnswering.ts:13](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/multimodal/documentQuestionAnswering.ts#L13)

___

### FeatureExtractionArgs

Ƭ **FeatureExtractionArgs**: [`BaseArgs`](interfaces/BaseArgs) & `FeatureExtractionInput` & `FeatureExtractionOAICompatInput`

#### Definido em[[featureextractionargs.defined-in]]

[inference/src/tasks/nlp/featureExtraction.ts:12](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/nlp/featureExtraction.ts#L12)

___

### FeatureExtractionOutput

Ƭ **FeatureExtractionOutput**: (`number` \| `number`[] \| `number`[][])[]

Os valores retornados são um array multidimensional de floats (a dimensão depende de você ter enviado uma string ou uma lista de strings, e se a redução automática, por exemplo, mean_pooling, foi aplicada para você ou não. Isso deve estar explicado no README do modelo).

#### Definido em[[featureextractionoutput.defined-in]]

[inference/src/tasks/nlp/featureExtraction.ts:17](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/nlp/featureExtraction.ts#L17)

___

### FillMaskArgs

Ƭ **FillMaskArgs**: [`BaseArgs`](interfaces/BaseArgs) & `FillMaskInput`

#### Definido em[[fillmaskargs.defined-in]]

[inference/src/tasks/nlp/fillMask.ts:7](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/nlp/fillMask.ts#L7)

___

### ImageClassificationArgs

Ƭ **ImageClassificationArgs**: [`BaseArgs`](interfaces/BaseArgs) & `ImageClassificationInput` \| `LegacyImageInput`

#### Definido em[[imageclassificationargs.defined-in]]

[inference/src/tasks/cv/imageClassification.ts:8](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/cv/imageClassification.ts#L8)

___

### ImageSegmentationArgs

Ƭ **ImageSegmentationArgs**: [`BaseArgs`](interfaces/BaseArgs) & `ImageSegmentationInput`

#### Definido em[[imagesegmentationargs.defined-in]]

[inference/src/tasks/cv/imageSegmentation.ts:8](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/cv/imageSegmentation.ts#L8)

___

### ImageTextToImageArgs

Ƭ **ImageTextToImageArgs**: [`BaseArgs`](interfaces/BaseArgs) & `ImageTextToImageInput`

#### Definido em[[imagetexttoimageargs.defined-in]]

[inference/src/tasks/cv/imageTextToImage.ts:7](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/cv/imageTextToImage.ts#L7)

___

### ImageTextToVideoArgs

Ƭ **ImageTextToVideoArgs**: [`BaseArgs`](interfaces/BaseArgs) & `ImageTextToVideoInput`

#### Definido em[[imagetexttovideoargs.defined-in]]

[inference/src/tasks/cv/imageTextToVideo.ts:7](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/cv/imageTextToVideo.ts#L7)

___

### ImageToImageArgs

Ƭ **ImageToImageArgs**: [`BaseArgs`](interfaces/BaseArgs) & `ImageToImageInput`

#### Definido em[[imagetoimageargs.defined-in]]

[inference/src/tasks/cv/imageToImage.ts:8](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/cv/imageToImage.ts#L8)

___

### ImageToTextArgs

Ƭ **ImageToTextArgs**: [`BaseArgs`](interfaces/BaseArgs) & `ImageToTextInput` \| `LegacyImageInput`

#### Definido em[[imagetotextargs.defined-in]]

[inference/src/tasks/cv/imageToText.ts:8](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/cv/imageToText.ts#L8)

___

### ImageToVideoArgs

Ƭ **ImageToVideoArgs**: [`BaseArgs`](interfaces/BaseArgs) & `ImageToVideoInput`

#### Definido em[[imagetovideoargs.defined-in]]

[inference/src/tasks/cv/imageToVideo.ts:8](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/cv/imageToVideo.ts#L8)

___

### InferenceProvider

Ƭ **InferenceProvider**: typeof [`INFERENCE_PROVIDERS`](modules#inference_providers)[`number`]

#### Definido em[[inferenceprovider.defined-in]]

[inference/src/types.ts:73](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/types.ts#L73)

___

### InferenceProviderOrPolicy

Ƭ **InferenceProviderOrPolicy**: typeof [`PROVIDERS_OR_POLICIES`](modules#providers_or_policies)[`number`]

#### Definido em[[inferenceproviderorpolicy.defined-in]]

[inference/src/types.ts:75](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/types.ts#L75)

___

### InferenceTask

Ƭ **InferenceTask**: `Exclude`\<`PipelineType`, ``"other"``\> \| ``"conversational"``

#### Definido em[[inferencetask.defined-in]]

[inference/src/types.ts:45](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/types.ts#L45)

___

### ModelId

Ƭ **ModelId**: `string`

ID do modelo do HF, como "meta-llama/Llama-3.3-70B-Instruct"

#### Definido em[[modelid.defined-in]]

[inference/src/types.ts:6](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/types.ts#L6)

___

### ObjectDetectionArgs

Ƭ **ObjectDetectionArgs**: [`BaseArgs`](interfaces/BaseArgs) & `ObjectDetectionInput` \| `LegacyImageInput`

#### Definido em[[objectdetectionargs.defined-in]]

[inference/src/tasks/cv/objectDetection.ts:8](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/cv/objectDetection.ts#L8)

___

### OutputType

Ƭ **OutputType**: ``"url"`` \| ``"dataUrl"`` \| ``"blob"`` \| ``"json"``

#### Definido em[[outputtype.defined-in]]

[inference/src/types.ts:179](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/types.ts#L179)

___

### QuestionAnsweringArgs

Ƭ **QuestionAnsweringArgs**: [`BaseArgs`](interfaces/BaseArgs) & `QuestionAnsweringInput`

#### Definido em[[questionansweringargs.defined-in]]

[inference/src/tasks/nlp/questionAnswering.ts:8](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/nlp/questionAnswering.ts#L8)

___

### RequestArgs

Ƭ **RequestArgs**: [`BaseArgs`](interfaces/BaseArgs) & \{ `data`: `Blob` \| `ArrayBuffer`  } \| \{ `inputs`: `unknown`  } \| \{ `prompt`: `string`  } \| \{ `text`: `string`  } \| \{ `audio_url`: `string`  } \| `ChatCompletionInput` & \{ `parameters?`: `Record`\<`string`, `unknown`\> ; `urlTransform?`: (`url`: `string`) => `string`  }

#### Definido em[[requestargs.defined-in]]

[inference/src/types.ts:152](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/types.ts#L152)

___

### SentenceSimilarityArgs

Ƭ **SentenceSimilarityArgs**: [`BaseArgs`](interfaces/BaseArgs) & `SentenceSimilarityInput`

#### Definido em[[sentencesimilarityargs.defined-in]]

[inference/src/tasks/nlp/sentenceSimilarity.ts:7](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/nlp/sentenceSimilarity.ts#L7)

___

### SummarizationArgs

Ƭ **SummarizationArgs**: [`BaseArgs`](interfaces/BaseArgs) & `SummarizationInput`

#### Definido em[[summarizationargs.defined-in]]

[inference/src/tasks/nlp/summarization.ts:7](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/nlp/summarization.ts#L7)

___

### TableQuestionAnsweringArgs

Ƭ **TableQuestionAnsweringArgs**: [`BaseArgs`](interfaces/BaseArgs) & `TableQuestionAnsweringInput`

#### Definido em[[tablequestionansweringargs.defined-in]]

[inference/src/tasks/nlp/tableQuestionAnswering.ts:7](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/nlp/tableQuestionAnswering.ts#L7)

___

### TabularClassificationArgs

Ƭ **TabularClassificationArgs**: [`BaseArgs`](interfaces/BaseArgs) & \{ `inputs`: \{ `data`: `Record`\<`string`, `string`[]\>  }  }

#### Definido em[[tabularclassificationargs.defined-in]]

[inference/src/tasks/tabular/tabularClassification.ts:6](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/tabular/tabularClassification.ts#L6)

___

### TabularClassificationOutput

Ƭ **TabularClassificationOutput**: `number`[]

Uma lista de rótulos previstos para cada linha

#### Definido em[[tabularclassificationoutput.defined-in]]

[inference/src/tasks/tabular/tabularClassification.ts:18](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/tabular/tabularClassification.ts#L18)

___

### TabularRegressionArgs

Ƭ **TabularRegressionArgs**: [`BaseArgs`](interfaces/BaseArgs) & \{ `inputs`: \{ `data`: `Record`\<`string`, `string`[]\>  }  }

#### Definido em[[tabularregressionargs.defined-in]]

[inference/src/tasks/tabular/tabularRegression.ts:6](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/tabular/tabularRegression.ts#L6)

___

### TabularRegressionOutput

Ƭ **TabularRegressionOutput**: `number`[]

uma lista de valores previstos para cada linha

#### Definido em[[tabularregressionoutput.defined-in]]

[inference/src/tasks/tabular/tabularRegression.ts:18](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/tabular/tabularRegression.ts#L18)

___

### TextClassificationArgs

Ƭ **TextClassificationArgs**: [`BaseArgs`](interfaces/BaseArgs) & `TextClassificationInput`

#### Definido em[[textclassificationargs.defined-in]]

[inference/src/tasks/nlp/textClassification.ts:7](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/nlp/textClassification.ts#L7)

___

### TextGenerationStreamFinishReason

Ƭ **TextGenerationStreamFinishReason**: ``"length"`` \| ``"eos_token"`` \| ``"stop_sequence"``

#### Definido em[[textgenerationstreamfinishreason.defined-in]]

[inference/src/tasks/nlp/textGenerationStream.ts:48](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/nlp/textGenerationStream.ts#L48)

___

### TextRankingArgs

Ƭ **TextRankingArgs**: [`BaseArgs`](interfaces/BaseArgs) & `TextRankingInput`

#### Definido em[[textrankingargs.defined-in]]

[inference/src/tasks/nlp/textRanking.ts:7](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/nlp/textRanking.ts#L7)

___

### TextToAudioArgs

Ƭ **TextToAudioArgs**: [`BaseArgs`](interfaces/BaseArgs) & `TextToAudioInput`

#### Definido em[[texttoaudioargs.defined-in]]

[inference/src/tasks/audio/textToAudio.ts:8](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/audio/textToAudio.ts#L8)

___

### TextToImageArgs

Ƭ **TextToImageArgs**: [`BaseArgs`](interfaces/BaseArgs) & `TextToImageInput`

#### Definido em[[texttoimageargs.defined-in]]

[inference/src/tasks/cv/textToImage.ts:8](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/cv/textToImage.ts#L8)

___

### TextToVideoArgs

Ƭ **TextToVideoArgs**: [`BaseArgs`](interfaces/BaseArgs) & `TextToVideoInput`

#### Definido em[[texttovideoargs.defined-in]]

[inference/src/tasks/cv/textToVideo.ts:11](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/cv/textToVideo.ts#L11)

___

### TextToVideoOutput

Ƭ **TextToVideoOutput**: `Blob`

#### Definido em[[texttovideooutput.defined-in]]

[inference/src/tasks/cv/textToVideo.ts:13](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/cv/textToVideo.ts#L13)

___

### TokenClassificationArgs

Ƭ **TokenClassificationArgs**: [`BaseArgs`](interfaces/BaseArgs) & `TokenClassificationInput`

#### Definido em[[tokenclassificationargs.defined-in]]

[inference/src/tasks/nlp/tokenClassification.ts:7](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/nlp/tokenClassification.ts#L7)

___

### TranslationArgs

Ƭ **TranslationArgs**: [`BaseArgs`](interfaces/BaseArgs) & `TranslationInput`

#### Definido em[[translationargs.defined-in]]

[inference/src/tasks/nlp/translation.ts:7](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/nlp/translation.ts#L7)

___

### VisualQuestionAnsweringArgs

Ƭ **VisualQuestionAnsweringArgs**: [`BaseArgs`](interfaces/BaseArgs) & `VisualQuestionAnsweringInput` & \{ `inputs`: `VisualQuestionAnsweringInputData` & \{ `image`: `Blob`  }  }

#### Definido em[[visualquestionansweringargs.defined-in]]

[inference/src/tasks/multimodal/visualQuestionAnswering.ts:13](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/multimodal/visualQuestionAnswering.ts#L13)

___

### ZeroShotClassificationArgs

Ƭ **ZeroShotClassificationArgs**: [`BaseArgs`](interfaces/BaseArgs) & `ZeroShotClassificationInput`

#### Definido em[[zeroshotclassificationargs.defined-in]]

[inference/src/tasks/nlp/zeroShotClassification.ts:7](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/nlp/zeroShotClassification.ts#L7)

___

### ZeroShotImageClassificationArgs

Ƭ **ZeroShotImageClassificationArgs**: [`BaseArgs`](interfaces/BaseArgs) & `ZeroShotImageClassificationInput` \| `LegacyZeroShotImageClassificationInput`

#### Definido em[[zeroshotimageclassificationargs.defined-in]]

[inference/src/tasks/cv/zeroShotImageClassification.ts:15](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/cv/zeroShotImageClassification.ts#L15)

## Variáveis

### INFERENCE\_PROVIDERS

• `Const` **INFERENCE\_PROVIDERS**: somente leitura [``"baseten"``, ``"cerebras"``, ``"cohere"``, ``"deepinfra"``, ``"fal-ai"``, ``"featherless-ai"``, ``"fireworks-ai"``, ``"groq"``, ``"hf-inference"``, ``"humain-ai"``, ``"novita"``, ``"nscale"``, ``"openai"``, ``"openrouter"``, ``"ovhcloud"``, ``"publicai"``, ``"replicate"``, ``"scaleway"``, ``"together"``, ``"wavespeed"``, ``"zai-org"``]

#### Definido em[[inferenceproviders.defined-in]]

[inference/src/types.ts:47](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/types.ts#L47)

___

### PROVEDORES

• `Const` **PROVIDERS**: `Record`\<[`InferenceProvider`](modules#inferenceprovider), `Partial`\<`Record`\<[`InferenceTask`](modules#inferencetask), `TaskProviderHelper`\>\>\>

#### Definido em[[providers.defined-in]]

[inference/src/lib/getProviderHelper.ts:61](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/getProviderHelper.ts#L61)

___

### PROVIDERS\_HUB\_ORGS

• `Const` **PROVIDERS\_HUB\_ORGS**: `Record`\<[`InferenceProvider`](modules#inferenceprovider), `string`\>

O namespace de organização no HF Hub, ou seja, hf.co/…

Sempre que possível, InferenceProvider deve == namespace da organização

#### Definido em[[providershuborgs.defined-in]]

[inference/src/types.ts:82](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/types.ts#L82)

___

### PROVEDORES\_OU\_POLÍTICAS

• `Const` **PROVIDERS\_OR\_POLICIES**: somente leitura [``"baseten"``, ``"cerebras"``, ``"cohere"``, ``"deepinfra"``, ``"fal-ai"``, ``"featherless-ai"``, ``"fireworks-ai"``, ``"groq"``, ``"hf-inference"``, ``"humain-ai"``, ``"novita"``, ``"nscale"``, ``"openai"``, ``"openrouter"``, ``"ovhcloud"``, ``"publicai"``, ``"replicate"``, ``"scaleway"``, ``"together"``, ``"wavespeed"``, ``"zai-org"``, ``"auto"``]

#### Definido em[[providersorpolicies.defined-in]]

[inference/src/types.ts:71](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/types.ts#L71)

## Funções

### audioClassification

▸ **audioClassification**(`args`, `options?`): `Promise`\<`AudioClassificationOutput`\>

Esta tarefa lê uma entrada de áudio e produz a probabilidade de classes. Modelo recomendado: superb/hubert-large-superb-er

#### Parâmetros[[audioclassification.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`AudioClassificationArgs`](modules#audioclassificationargs) |
| `options?` | [`Options`](interfaces/Options) |

#### Retorna[[audioclassification.returns]]

`Promise`\<`AudioClassificationOutput`\>

#### Definido em[[audioclassification.defined-in]]

[inference/src/tasks/audio/audioClassification.ts:15](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/audio/audioClassification.ts#L15)

___

### audioToAudio

▸ **audioToAudio**(`args`, `options?`): `Promise`\<[`AudioToAudioOutput`](interfaces/AudioToAudioOutput)[]\>

Esta tarefa lê uma entrada de áudio e gera um ou vários arquivos de áudio. Modelo de exemplo: speechbrain/sepformer-wham realiza separação de fontes de áudio.

#### Parâmetros[[audiotoaudio.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`AudioToAudioArgs`](modules#audiotoaudioargs) |
| `options?` | [`Options`](interfaces/Options) |

#### Retorna[[audiotoaudio.returns]]

`Promise`\<[`AudioToAudioOutput`](interfaces/AudioToAudioOutput)[]\>

#### Definido em[[audiotoaudio.defined-in]]

[inference/src/tasks/audio/audioToAudio.ts:41](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/audio/audioToAudio.ts#L41)

___

### automaticSpeechRecognition

▸ **automaticSpeechRecognition**(`args`, `options?`): `Promise`\<`AutomaticSpeechRecognitionOutput`\>

Esta tarefa lê uma entrada de áudio e produz as palavras ditas nos arquivos de áudio. Modelo recomendado (idioma inglês): facebook/wav2vec2-large-960h-lv60-self

#### Parâmetros[[automaticspeechrecognition.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`AutomaticSpeechRecognitionArgs`](modules#automaticspeechrecognitionargs) |
| `options?` | [`Options`](interfaces/Options) |

#### Retorna[[automaticspeechrecognition.returns]]

`Promise`\<`AutomaticSpeechRecognitionOutput`\>

#### Definido em[[automaticspeechrecognition.defined-in]]

[inference/src/tasks/audio/automaticSpeechRecognition.ts:13](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/audio/automaticSpeechRecognition.ts#L13)

___

### chatCompletion

▸ **chatCompletion**(`args`, `options?`): `Promise`\<`ChatCompletionOutput`\>

Use o endpoint de conclusão de chat para gerar uma resposta a um prompt, usando a API de conclusão de mensagens da OpenAI sem stream

#### Parâmetros[[chatcompletion.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`BaseArgs`](interfaces/BaseArgs) & `ChatCompletionInput` |
| `options?` | [`Options`](interfaces/Options) |

#### Retorna[[chatcompletion.returns]]

`Promise`\<`ChatCompletionOutput`\>

#### Definido em[[chatcompletion.defined-in]]

[inference/src/tasks/nlp/chatCompletion.ts:12](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/nlp/chatCompletion.ts#L12)

___

### chatCompletionStream

▸ **chatCompletionStream**(`args`, `options?`): `AsyncGenerator`\<`ChatCompletionStreamOutput`\>

Use para continuar um texto a partir de um prompt. Igual a `textGeneration`, mas retorna um gerador que pode ser lido um token de cada vez

#### Parâmetros[[chatcompletionstream.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`BaseArgs`](interfaces/BaseArgs) & `ChatCompletionInput` |
| `options?` | [`Options`](interfaces/Options) |

#### Retorna[[chatcompletionstream.returns]]

`AsyncGenerator`\<`ChatCompletionStreamOutput`\>

#### Definido em[[chatcompletionstream.defined-in]]

[inference/src/tasks/nlp/chatCompletionStream.ts:12](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/nlp/chatCompletionStream.ts#L12)

___

### documentQuestionAnswering

▸ **documentQuestionAnswering**(`args`, `options?`): `Promise`\<`DocumentQuestionAnsweringOutput`[`number`]\>

Responde a uma pergunta em uma imagem de documento. Modelo recomendado: impira/layoutlm-document-qa.

#### Parâmetros[[documentquestionanswering.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`DocumentQuestionAnsweringArgs`](modules#documentquestionansweringargs) |
| `options?` | [`Options`](interfaces/Options) |

#### Retorna[[documentquestionanswering.returns]]

`Promise`\<`DocumentQuestionAnsweringOutput`[`number`]\>

#### Definido em[[documentquestionanswering.defined-in]]

[inference/src/tasks/multimodal/documentQuestionAnswering.ts:19](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/multimodal/documentQuestionAnswering.ts#L19)

___

### featureExtraction

▸ **featureExtraction**(`args`, `options?`): `Promise`\<[`FeatureExtractionOutput`](modules#featureextractionoutput)\>

Esta tarefa lê algum texto e produz valores float brutos, que geralmente são consumidos como parte de um banco de dados semântico/busca semântica.

#### Parâmetros[[featureextraction.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`FeatureExtractionArgs`](modules#featureextractionargs) |
| `options?` | [`Options`](interfaces/Options) |

#### Retorna[[featureextraction.returns]]

`Promise`\<[`FeatureExtractionOutput`](modules#featureextractionoutput)\>

#### Definido em[[featureextraction.defined-in]]

[inference/src/tasks/nlp/featureExtraction.ts:22](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/nlp/featureExtraction.ts#L22)

___

### fillMask

▸ **fillMask**(`args`, `options?`): `Promise`\<`FillMaskOutput`\>

Tenta preencher um buraco com uma palavra ausente (mais precisamente, um token). Essa é a tarefa base para os modelos BERT.

#### Parâmetros[[fillmask.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`FillMaskArgs`](modules#fillmaskargs) |
| `options?` | [`Options`](interfaces/Options) |

#### Retorna[[fillmask.returns]]

`Promise`\<`FillMaskOutput`\>

#### Definido em[[fillmask.defined-in]]

[inference/src/tasks/nlp/fillMask.ts:12](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/nlp/fillMask.ts#L12)

___

### getProviderHelper

▸ **getProviderHelper**(`provider`, `task`): `TextToImageTaskHelper` & `TaskProviderHelper`

Obter instância de helper de provedor por nome e tarefa

#### Parâmetros[[getproviderhelper.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `provider` | ``"baseten"`` \| ``"cerebras"`` \| ``"cohere"`` \| ``"deepinfra"`` \| ``"fal-ai"`` \| ``"featherless-ai"`` \| ``"fireworks-ai"`` \| ``"groq"`` \| ``"hf-inference"`` \| ``"humain-ai"`` \| ``"novita"`` \| ``"nscale"`` \| ``"openai"`` \| ``"openrouter"`` \| ``"ovhcloud"`` \| ``"publicai"`` \| ``"replicate"`` \| ``"scaleway"`` \| ``"together"`` \| ``"wavespeed"`` \| ``"zai-org"`` \| ``"auto"`` |
| `task` | ``"text-to-image"`` |

#### Retorna[[getproviderhelper.returns]]

`TextToImageTaskHelper` & `TaskProviderHelper`

#### Definido em[[getproviderhelper.defined-in]]

[inference/src/lib/getProviderHelper.ts:201](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/getProviderHelper.ts#L201)

▸ **getProviderHelper**(`provider`, `task`): `ConversationalTaskHelper` & `TaskProviderHelper`

#### Parâmetros[[getproviderhelper.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `provider` | ``"baseten"`` \| ``"cerebras"`` \| ``"cohere"`` \| ``"deepinfra"`` \| ``"fal-ai"`` \| ``"featherless-ai"`` \| ``"fireworks-ai"`` \| ``"groq"`` \| ``"hf-inference"`` \| ``"humain-ai"`` \| ``"novita"`` \| ``"nscale"`` \| ``"openai"`` \| ``"openrouter"`` \| ``"ovhcloud"`` \| ``"publicai"`` \| ``"replicate"`` \| ``"scaleway"`` \| ``"together"`` \| ``"wavespeed"`` \| ``"zai-org"`` \| ``"auto"`` |
| `task` | ``"conversational"`` |

#### Retorna[[getproviderhelper.returns]]

`ConversationalTaskHelper` & `TaskProviderHelper`

#### Definido em[[getproviderhelper.defined-in]]

[inference/src/lib/getProviderHelper.ts:205](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/getProviderHelper.ts#L205)

▸ **getProviderHelper**(`provider`, `task`): `TextGenerationTaskHelper` & `TaskProviderHelper`

#### Parâmetros[[getproviderhelper.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `provider` | ``"baseten"`` \| ``"cerebras"`` \| ``"cohere"`` \| ``"deepinfra"`` \| ``"fal-ai"`` \| ``"featherless-ai"`` \| ``"fireworks-ai"`` \| ``"groq"`` \| ``"hf-inference"`` \| ``"humain-ai"`` \| ``"novita"`` \| ``"nscale"`` \| ``"openai"`` \| ``"openrouter"`` \| ``"ovhcloud"`` \| ``"publicai"`` \| ``"replicate"`` \| ``"scaleway"`` \| ``"together"`` \| ``"wavespeed"`` \| ``"zai-org"`` \| ``"auto"`` |
| `task` | ``"text-generation"`` |

#### Retorna[[getproviderhelper.returns]]

`TextGenerationTaskHelper` & `TaskProviderHelper`

#### Definido em[[getproviderhelper.defined-in]]

[inference/src/lib/getProviderHelper.ts:209](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/getProviderHelper.ts#L209)

▸ **getProviderHelper**(`provider`, `task`): `TextToSpeechTaskHelper` & `TaskProviderHelper`

#### Parâmetros[[getproviderhelper.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `provider` | ``"baseten"`` \| ``"cerebras"`` \| ``"cohere"`` \| ``"deepinfra"`` \| ``"fal-ai"`` \| ``"featherless-ai"`` \| ``"fireworks-ai"`` \| ``"groq"`` \| ``"hf-inference"`` \| ``"humain-ai"`` \| ``"novita"`` \| ``"nscale"`` \| ``"openai"`` \| ``"openrouter"`` \| ``"ovhcloud"`` \| ``"publicai"`` \| ``"replicate"`` \| ``"scaleway"`` \| ``"together"`` \| ``"wavespeed"`` \| ``"zai-org"`` \| ``"auto"`` |
| `task` | ``"text-to-speech"`` |

#### Retorna[[getproviderhelper.returns]]

`TextToSpeechTaskHelper` & `TaskProviderHelper`

#### Definido em[[getproviderhelper.defined-in]]

[inference/src/lib/getProviderHelper.ts:213](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/getProviderHelper.ts#L213)

▸ **getProviderHelper**(`provider`, `task`): `TextToAudioTaskHelper` & `TaskProviderHelper`

#### Parâmetros[[getproviderhelper.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `provider` | ``"baseten"`` \| ``"cerebras"`` \| ``"cohere"`` \| ``"deepinfra"`` \| ``"fal-ai"`` \| ``"featherless-ai"`` \| ``"fireworks-ai"`` \| ``"groq"`` \| ``"hf-inference"`` \| ``"humain-ai"`` \| ``"novita"`` \| ``"nscale"`` \| ``"openai"`` \| ``"openrouter"`` \| ``"ovhcloud"`` \| ``"publicai"`` \| ``"replicate"`` \| ``"scaleway"`` \| ``"together"`` \| ``"wavespeed"`` \| ``"zai-org"`` \| ``"auto"`` |
| `task` | ``"text-to-audio"`` |

#### Retorna[[getproviderhelper.returns]]

`TextToAudioTaskHelper` & `TaskProviderHelper`

#### Definido em[[getproviderhelper.defined-in]]

[inference/src/lib/getProviderHelper.ts:217](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/getProviderHelper.ts#L217)

▸ **getProviderHelper**(`provider`, `task`): `AutomaticSpeechRecognitionTaskHelper` & `TaskProviderHelper`

#### Parâmetros[[getproviderhelper.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `provider` | ``"baseten"`` \| ``"cerebras"`` \| ``"cohere"`` \| ``"deepinfra"`` \| ``"fal-ai"`` \| ``"featherless-ai"`` \| ``"fireworks-ai"`` \| ``"groq"`` \| ``"hf-inference"`` \| ``"humain-ai"`` \| ``"novita"`` \| ``"nscale"`` \| ``"openai"`` \| ``"openrouter"`` \| ``"ovhcloud"`` \| ``"publicai"`` \| ``"replicate"`` \| ``"scaleway"`` \| ``"together"`` \| ``"wavespeed"`` \| ``"zai-org"`` \| ``"auto"`` |
| `task` | ``"automatic-speech-recognition"`` |

#### Retorna[[getproviderhelper.returns]]

`AutomaticSpeechRecognitionTaskHelper` & `TaskProviderHelper`

#### Definido em[[getproviderhelper.defined-in]]

[inference/src/lib/getProviderHelper.ts:221](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/getProviderHelper.ts#L221)

▸ **getProviderHelper**(`provider`, `task`): `TextToVideoTaskHelper` & `TaskProviderHelper`

#### Parâmetros[[getproviderhelper.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `provider` | ``"baseten"`` \| ``"cerebras"`` \| ``"cohere"`` \| ``"deepinfra"`` \| ``"fal-ai"`` \| ``"featherless-ai"`` \| ``"fireworks-ai"`` \| ``"groq"`` \| ``"hf-inference"`` \| ``"humain-ai"`` \| ``"novita"`` \| ``"nscale"`` \| ``"openai"`` \| ``"openrouter"`` \| ``"ovhcloud"`` \| ``"publicai"`` \| ``"replicate"`` \| ``"scaleway"`` \| ``"together"`` \| ``"wavespeed"`` \| ``"zai-org"`` \| ``"auto"`` |
| `task` | ``"text-to-video"`` |

#### Retorna[[getproviderhelper.returns]]

`TextToVideoTaskHelper` & `TaskProviderHelper`

#### Definido em[[getproviderhelper.defined-in]]

[inference/src/lib/getProviderHelper.ts:225](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/getProviderHelper.ts#L225)

▸ **getProviderHelper**(`provider`, `task`): `TextClassificationTaskHelper` & `TaskProviderHelper`

#### Parâmetros[[getproviderhelper.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `provider` | ``"baseten"`` \| ``"cerebras"`` \| ``"cohere"`` \| ``"deepinfra"`` \| ``"fal-ai"`` \| ``"featherless-ai"`` \| ``"fireworks-ai"`` \| ``"groq"`` \| ``"hf-inference"`` \| ``"humain-ai"`` \| ``"novita"`` \| ``"nscale"`` \| ``"openai"`` \| ``"openrouter"`` \| ``"ovhcloud"`` \| ``"publicai"`` \| ``"replicate"`` \| ``"scaleway"`` \| ``"together"`` \| ``"wavespeed"`` \| ``"zai-org"`` \| ``"auto"`` |
| `task` | ``"text-classification"`` |

#### Retorna[[getproviderhelper.returns]]

`TextClassificationTaskHelper` & `TaskProviderHelper`

#### Definido em[[getproviderhelper.defined-in]]

[inference/src/lib/getProviderHelper.ts:229](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/getProviderHelper.ts#L229)

▸ **getProviderHelper**(`provider`, `task`): `QuestionAnsweringTaskHelper` & `TaskProviderHelper`

#### Parâmetros[[getproviderhelper.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `provider` | ``"baseten"`` \| ``"cerebras"`` \| ``"cohere"`` \| ``"deepinfra"`` \| ``"fal-ai"`` \| ``"featherless-ai"`` \| ``"fireworks-ai"`` \| ``"groq"`` \| ``"hf-inference"`` \| ``"humain-ai"`` \| ``"novita"`` \| ``"nscale"`` \| ``"openai"`` \| ``"openrouter"`` \| ``"ovhcloud"`` \| ``"publicai"`` \| ``"replicate"`` \| ``"scaleway"`` \| ``"together"`` \| ``"wavespeed"`` \| ``"zai-org"`` \| ``"auto"`` |
| `task` | ``"question-answering"`` |

#### Retorna[[getproviderhelper.returns]]

`QuestionAnsweringTaskHelper` & `TaskProviderHelper`

#### Definido em[[getproviderhelper.defined-in]]

[inference/src/lib/getProviderHelper.ts:233](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/getProviderHelper.ts#L233)

▸ **getProviderHelper**(`provider`, `task`): `AudioClassificationTaskHelper` & `TaskProviderHelper`

#### Parâmetros[[getproviderhelper.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `provider` | ``"baseten"`` \| ``"cerebras"`` \| ``"cohere"`` \| ``"deepinfra"`` \| ``"fal-ai"`` \| ``"featherless-ai"`` \| ``"fireworks-ai"`` \| ``"groq"`` \| ``"hf-inference"`` \| ``"humain-ai"`` \| ``"novita"`` \| ``"nscale"`` \| ``"openai"`` \| ``"openrouter"`` \| ``"ovhcloud"`` \| ``"publicai"`` \| ``"replicate"`` \| ``"scaleway"`` \| ``"together"`` \| ``"wavespeed"`` \| ``"zai-org"`` \| ``"auto"`` |
| `task` | ``"audio-classification"`` |

#### Retorna[[getproviderhelper.returns]]

`AudioClassificationTaskHelper` & `TaskProviderHelper`

#### Definido em[[getproviderhelper.defined-in]]

[inference/src/lib/getProviderHelper.ts:237](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/getProviderHelper.ts#L237)

▸ **getProviderHelper**(`provider`, `task`): `AudioToAudioTaskHelper` & `TaskProviderHelper`

#### Parâmetros[[getproviderhelper.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `provider` | ``"baseten"`` \| ``"cerebras"`` \| ``"cohere"`` \| ``"deepinfra"`` \| ``"fal-ai"`` \| ``"featherless-ai"`` \| ``"fireworks-ai"`` \| ``"groq"`` \| ``"hf-inference"`` \| ``"humain-ai"`` \| ``"novita"`` \| ``"nscale"`` \| ``"openai"`` \| ``"openrouter"`` \| ``"ovhcloud"`` \| ``"publicai"`` \| ``"replicate"`` \| ``"scaleway"`` \| ``"together"`` \| ``"wavespeed"`` \| ``"zai-org"`` \| ``"auto"`` |
| `task` | ``"audio-to-audio"`` |

#### Retorna[[getproviderhelper.returns]]

`AudioToAudioTaskHelper` & `TaskProviderHelper`

#### Definido em[[getproviderhelper.defined-in]]

[inference/src/lib/getProviderHelper.ts:241](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/getProviderHelper.ts#L241)

▸ **getProviderHelper**(`provider`, `task`): `FillMaskTaskHelper` & `TaskProviderHelper`

#### Parâmetros[[getproviderhelper.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `provider` | ``"baseten"`` \| ``"cerebras"`` \| ``"cohere"`` \| ``"deepinfra"`` \| ``"fal-ai"`` \| ``"featherless-ai"`` \| ``"fireworks-ai"`` \| ``"groq"`` \| ``"hf-inference"`` \| ``"humain-ai"`` \| ``"novita"`` \| ``"nscale"`` \| ``"openai"`` \| ``"openrouter"`` \| ``"ovhcloud"`` \| ``"publicai"`` \| ``"replicate"`` \| ``"scaleway"`` \| ``"together"`` \| ``"wavespeed"`` \| ``"zai-org"`` \| ``"auto"`` |
| `task` | ``"fill-mask"`` |

#### Retorna[[getproviderhelper.returns]]

`FillMaskTaskHelper` & `TaskProviderHelper`

#### Definido em[[getproviderhelper.defined-in]]

[inference/src/lib/getProviderHelper.ts:245](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/getProviderHelper.ts#L245)

▸ **getProviderHelper**(`provider`, `task`): `FeatureExtractionTaskHelper` & `TaskProviderHelper`

#### Parâmetros[[getproviderhelper.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `provider` | ``"baseten"`` \| ``"cerebras"`` \| ``"cohere"`` \| ``"deepinfra"`` \| ``"fal-ai"`` \| ``"featherless-ai"`` \| ``"fireworks-ai"`` \| ``"groq"`` \| ``"hf-inference"`` \| ``"humain-ai"`` \| ``"novita"`` \| ``"nscale"`` \| ``"openai"`` \| ``"openrouter"`` \| ``"ovhcloud"`` \| ``"publicai"`` \| ``"replicate"`` \| ``"scaleway"`` \| ``"together"`` \| ``"wavespeed"`` \| ``"zai-org"`` \| ``"auto"`` |
| `task` | ``"feature-extraction"`` |

#### Retorna[[getproviderhelper.returns]]

`FeatureExtractionTaskHelper` & `TaskProviderHelper`

#### Definido em[[getproviderhelper.defined-in]]

[inference/src/lib/getProviderHelper.ts:249](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/getProviderHelper.ts#L249)

▸ **getProviderHelper**(`provider`, `task`): `ImageClassificationTaskHelper` & `TaskProviderHelper`

#### Parâmetros[[getproviderhelper.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `provider` | ``"baseten"`` \| ``"cerebras"`` \| ``"cohere"`` \| ``"deepinfra"`` \| ``"fal-ai"`` \| ``"featherless-ai"`` \| ``"fireworks-ai"`` \| ``"groq"`` \| ``"hf-inference"`` \| ``"humain-ai"`` \| ``"novita"`` \| ``"nscale"`` \| ``"openai"`` \| ``"openrouter"`` \| ``"ovhcloud"`` \| ``"publicai"`` \| ``"replicate"`` \| ``"scaleway"`` \| ``"together"`` \| ``"wavespeed"`` \| ``"zai-org"`` \| ``"auto"`` |
| `task` | ``"image-classification"`` |

#### Retorna[[getproviderhelper.returns]]

`ImageClassificationTaskHelper` & `TaskProviderHelper`

#### Definido em[[getproviderhelper.defined-in]]

[inference/src/lib/getProviderHelper.ts:253](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/getProviderHelper.ts#L253)

▸ **getProviderHelper**(`provider`, `task`): `ImageSegmentationTaskHelper` & `TaskProviderHelper`

#### Parâmetros[[getproviderhelper.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `provider` | ``"baseten"`` \| ``"cerebras"`` \| ``"cohere"`` \| ``"deepinfra"`` \| ``"fal-ai"`` \| ``"featherless-ai"`` \| ``"fireworks-ai"`` \| ``"groq"`` \| ``"hf-inference"`` \| ``"humain-ai"`` \| ``"novita"`` \| ``"nscale"`` \| ``"openai"`` \| ``"openrouter"`` \| ``"ovhcloud"`` \| ``"publicai"`` \| ``"replicate"`` \| ``"scaleway"`` \| ``"together"`` \| ``"wavespeed"`` \| ``"zai-org"`` \| ``"auto"`` |
| `task` | ``"image-segmentation"`` |

#### Retorna[[getproviderhelper.returns]]

`ImageSegmentationTaskHelper` & `TaskProviderHelper`

#### Definido em[[getproviderhelper.defined-in]]

[inference/src/lib/getProviderHelper.ts:257](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/getProviderHelper.ts#L257)

▸ **getProviderHelper**(`provider`, `task`): `DocumentQuestionAnsweringTaskHelper` & `TaskProviderHelper`

#### Parâmetros[[getproviderhelper.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `provider` | ``"baseten"`` \| ``"cerebras"`` \| ``"cohere"`` \| ``"deepinfra"`` \| ``"fal-ai"`` \| ``"featherless-ai"`` \| ``"fireworks-ai"`` \| ``"groq"`` \| ``"hf-inference"`` \| ``"humain-ai"`` \| ``"novita"`` \| ``"nscale"`` \| ``"openai"`` \| ``"openrouter"`` \| ``"ovhcloud"`` \| ``"publicai"`` \| ``"replicate"`` \| ``"scaleway"`` \| ``"together"`` \| ``"wavespeed"`` \| ``"zai-org"`` \| ``"auto"`` |
| `task` | ``"document-question-answering"`` |

#### Retorna[[getproviderhelper.returns]]

`DocumentQuestionAnsweringTaskHelper` & `TaskProviderHelper`

#### Definido em[[getproviderhelper.defined-in]]

[inference/src/lib/getProviderHelper.ts:261](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/getProviderHelper.ts#L261)

▸ **getProviderHelper**(`provider`, `task`): `ImageToTextTaskHelper` & `TaskProviderHelper`

#### Parâmetros[[getproviderhelper.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `provider` | ``"baseten"`` \| ``"cerebras"`` \| ``"cohere"`` \| ``"deepinfra"`` \| ``"fal-ai"`` \| ``"featherless-ai"`` \| ``"fireworks-ai"`` \| ``"groq"`` \| ``"hf-inference"`` \| ``"humain-ai"`` \| ``"novita"`` \| ``"nscale"`` \| ``"openai"`` \| ``"openrouter"`` \| ``"ovhcloud"`` \| ``"publicai"`` \| ``"replicate"`` \| ``"scaleway"`` \| ``"together"`` \| ``"wavespeed"`` \| ``"zai-org"`` \| ``"auto"`` |
| `task` | ``"image-to-text"`` |

#### Retorna[[getproviderhelper.returns]]

`ImageToTextTaskHelper` & `TaskProviderHelper`

#### Definido em[[getproviderhelper.defined-in]]

[inference/src/lib/getProviderHelper.ts:265](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/getProviderHelper.ts#L265)

▸ **getProviderHelper**(`provider`, `task`): `ObjectDetectionTaskHelper` & `TaskProviderHelper`

#### Parâmetros[[getproviderhelper.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `provider` | ``"baseten"`` \| ``"cerebras"`` \| ``"cohere"`` \| ``"deepinfra"`` \| ``"fal-ai"`` \| ``"featherless-ai"`` \| ``"fireworks-ai"`` \| ``"groq"`` \| ``"hf-inference"`` \| ``"humain-ai"`` \| ``"novita"`` \| ``"nscale"`` \| ``"openai"`` \| ``"openrouter"`` \| ``"ovhcloud"`` \| ``"publicai"`` \| ``"replicate"`` \| ``"scaleway"`` \| ``"together"`` \| ``"wavespeed"`` \| ``"zai-org"`` \| ``"auto"`` |
| `task` | ``"object-detection"`` |

#### Retorna[[getproviderhelper.returns]]

`ObjectDetectionTaskHelper` & `TaskProviderHelper`

#### Definido em[[getproviderhelper.defined-in]]

[inference/src/lib/getProviderHelper.ts:269](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/getProviderHelper.ts#L269)

▸ **getProviderHelper**(`provider`, `task`): `ZeroShotImageClassificationTaskHelper` & `TaskProviderHelper`

#### Parâmetros[[getproviderhelper.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `provider` | ``"baseten"`` \| ``"cerebras"`` \| ``"cohere"`` \| ``"deepinfra"`` \| ``"fal-ai"`` \| ``"featherless-ai"`` \| ``"fireworks-ai"`` \| ``"groq"`` \| ``"hf-inference"`` \| ``"humain-ai"`` \| ``"novita"`` \| ``"nscale"`` \| ``"openai"`` \| ``"openrouter"`` \| ``"ovhcloud"`` \| ``"publicai"`` \| ``"replicate"`` \| ``"scaleway"`` \| ``"together"`` \| ``"wavespeed"`` \| ``"zai-org"`` \| ``"auto"`` |
| `task` | ``"zero-shot-image-classification"`` |

#### Retorna[[getproviderhelper.returns]]

`ZeroShotImageClassificationTaskHelper` & `TaskProviderHelper`

#### Definido em[[getproviderhelper.defined-in]]

[inference/src/lib/getProviderHelper.ts:273](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/getProviderHelper.ts#L273)

▸ **getProviderHelper**(`provider`, `task`): `ZeroShotClassificationTaskHelper` & `TaskProviderHelper`

#### Parâmetros[[getproviderhelper.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `provider` | ``"baseten"`` \| ``"cerebras"`` \| ``"cohere"`` \| ``"deepinfra"`` \| ``"fal-ai"`` \| ``"featherless-ai"`` \| ``"fireworks-ai"`` \| ``"groq"`` \| ``"hf-inference"`` \| ``"humain-ai"`` \| ``"novita"`` \| ``"nscale"`` \| ``"openai"`` \| ``"openrouter"`` \| ``"ovhcloud"`` \| ``"publicai"`` \| ``"replicate"`` \| ``"scaleway"`` \| ``"together"`` \| ``"wavespeed"`` \| ``"zai-org"`` \| ``"auto"`` |
| `task` | ``"zero-shot-classification"`` |

#### Retorna[[getproviderhelper.returns]]

`ZeroShotClassificationTaskHelper` & `TaskProviderHelper`

#### Definido em[[getproviderhelper.defined-in]]

[inference/src/lib/getProviderHelper.ts:277](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/getProviderHelper.ts#L277)

▸ **getProviderHelper**(`provider`, `task`): `ImageToImageTaskHelper` & `TaskProviderHelper`

#### Parâmetros[[getproviderhelper.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `provider` | ``"baseten"`` \| ``"cerebras"`` \| ``"cohere"`` \| ``"deepinfra"`` \| ``"fal-ai"`` \| ``"featherless-ai"`` \| ``"fireworks-ai"`` \| ``"groq"`` \| ``"hf-inference"`` \| ``"humain-ai"`` \| ``"novita"`` \| ``"nscale"`` \| ``"openai"`` \| ``"openrouter"`` \| ``"ovhcloud"`` \| ``"publicai"`` \| ``"replicate"`` \| ``"scaleway"`` \| ``"together"`` \| ``"wavespeed"`` \| ``"zai-org"`` \| ``"auto"`` |
| `task` | ``"image-to-image"`` |

#### Retorna[[getproviderhelper.returns]]

`ImageToImageTaskHelper` & `TaskProviderHelper`

#### Definido em[[getproviderhelper.defined-in]]

[inference/src/lib/getProviderHelper.ts:281](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/getProviderHelper.ts#L281)

▸ **getProviderHelper**(`provider`, `task`): `ImageToVideoTaskHelper` & `TaskProviderHelper`

#### Parâmetros[[getproviderhelper.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `provider` | ``"baseten"`` \| ``"cerebras"`` \| ``"cohere"`` \| ``"deepinfra"`` \| ``"fal-ai"`` \| ``"featherless-ai"`` \| ``"fireworks-ai"`` \| ``"groq"`` \| ``"hf-inference"`` \| ``"humain-ai"`` \| ``"novita"`` \| ``"nscale"`` \| ``"openai"`` \| ``"openrouter"`` \| ``"ovhcloud"`` \| ``"publicai"`` \| ``"replicate"`` \| ``"scaleway"`` \| ``"together"`` \| ``"wavespeed"`` \| ``"zai-org"`` \| ``"auto"`` |
| `task` | ``"image-to-video"`` |

#### Retorna[[getproviderhelper.returns]]

`ImageToVideoTaskHelper` & `TaskProviderHelper`

#### Definido em[[getproviderhelper.defined-in]]

[inference/src/lib/getProviderHelper.ts:285](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/getProviderHelper.ts#L285)

▸ **getProviderHelper**(`provider`, `task`): `ImageTextToImageTaskHelper` & `TaskProviderHelper`

#### Parâmetros[[getproviderhelper.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `provider` | ``"baseten"`` \| ``"cerebras"`` \| ``"cohere"`` \| ``"deepinfra"`` \| ``"fal-ai"`` \| ``"featherless-ai"`` \| ``"fireworks-ai"`` \| ``"groq"`` \| ``"hf-inference"`` \| ``"humain-ai"`` \| ``"novita"`` \| ``"nscale"`` \| ``"openai"`` \| ``"openrouter"`` \| ``"ovhcloud"`` \| ``"publicai"`` \| ``"replicate"`` \| ``"scaleway"`` \| ``"together"`` \| ``"wavespeed"`` \| ``"zai-org"`` \| ``"auto"`` |
| `task` | ``"image-text-to-image"`` |

#### Retorna[[getproviderhelper.returns]]

`ImageTextToImageTaskHelper` & `TaskProviderHelper`

#### Definido em[[getproviderhelper.defined-in]]

[inference/src/lib/getProviderHelper.ts:289](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/getProviderHelper.ts#L289)

▸ **getProviderHelper**(`provider`, `task`): `ImageTextToVideoTaskHelper` & `TaskProviderHelper`

#### Parâmetros[[getproviderhelper.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `provider` | ``"baseten"`` \| ``"cerebras"`` \| ``"cohere"`` \| ``"deepinfra"`` \| ``"fal-ai"`` \| ``"featherless-ai"`` \| ``"fireworks-ai"`` \| ``"groq"`` \| ``"hf-inference"`` \| ``"humain-ai"`` \| ``"novita"`` \| ``"nscale"`` \| ``"openai"`` \| ``"openrouter"`` \| ``"ovhcloud"`` \| ``"publicai"`` \| ``"replicate"`` \| ``"scaleway"`` \| ``"together"`` \| ``"wavespeed"`` \| ``"zai-org"`` \| ``"auto"`` |
| `task` | ``"image-text-to-video"`` |

#### Retorna[[getproviderhelper.returns]]

`ImageTextToVideoTaskHelper` & `TaskProviderHelper`

#### Definido em[[getproviderhelper.defined-in]]

[inference/src/lib/getProviderHelper.ts:293](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/getProviderHelper.ts#L293)

▸ **getProviderHelper**(`provider`, `task`): `TextRankingTaskHelper` & `TaskProviderHelper`

#### Parâmetros[[getproviderhelper.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `provider` | ``"baseten"`` \| ``"cerebras"`` \| ``"cohere"`` \| ``"deepinfra"`` \| ``"fal-ai"`` \| ``"featherless-ai"`` \| ``"fireworks-ai"`` \| ``"groq"`` \| ``"hf-inference"`` \| ``"humain-ai"`` \| ``"novita"`` \| ``"nscale"`` \| ``"openai"`` \| ``"openrouter"`` \| ``"ovhcloud"`` \| ``"publicai"`` \| ``"replicate"`` \| ``"scaleway"`` \| ``"together"`` \| ``"wavespeed"`` \| ``"zai-org"`` \| ``"auto"`` |
| `task` | ``"text-ranking"`` |

#### Retorna[[getproviderhelper.returns]]

`TextRankingTaskHelper` & `TaskProviderHelper`

#### Definido em[[getproviderhelper.defined-in]]

[inference/src/lib/getProviderHelper.ts:297](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/getProviderHelper.ts#L297)

▸ **getProviderHelper**(`provider`, `task`): `SentenceSimilarityTaskHelper` & `TaskProviderHelper`

#### Parâmetros[[getproviderhelper.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `provider` | ``"baseten"`` \| ``"cerebras"`` \| ``"cohere"`` \| ``"deepinfra"`` \| ``"fal-ai"`` \| ``"featherless-ai"`` \| ``"fireworks-ai"`` \| ``"groq"`` \| ``"hf-inference"`` \| ``"humain-ai"`` \| ``"novita"`` \| ``"nscale"`` \| ``"openai"`` \| ``"openrouter"`` \| ``"ovhcloud"`` \| ``"publicai"`` \| ``"replicate"`` \| ``"scaleway"`` \| ``"together"`` \| ``"wavespeed"`` \| ``"zai-org"`` \| ``"auto"`` |
| `task` | ``"sentence-similarity"`` |

#### Retorna[[getproviderhelper.returns]]

`SentenceSimilarityTaskHelper` & `TaskProviderHelper`

#### Definido em[[getproviderhelper.defined-in]]

[inference/src/lib/getProviderHelper.ts:301](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/getProviderHelper.ts#L301)

▸ **getProviderHelper**(`provider`, `task`): `TableQuestionAnsweringTaskHelper` & `TaskProviderHelper`

#### Parâmetros[[getproviderhelper.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `provider` | ``"baseten"`` \| ``"cerebras"`` \| ``"cohere"`` \| ``"deepinfra"`` \| ``"fal-ai"`` \| ``"featherless-ai"`` \| ``"fireworks-ai"`` \| ``"groq"`` \| ``"hf-inference"`` \| ``"humain-ai"`` \| ``"novita"`` \| ``"nscale"`` \| ``"openai"`` \| ``"openrouter"`` \| ``"ovhcloud"`` \| ``"publicai"`` \| ``"replicate"`` \| ``"scaleway"`` \| ``"together"`` \| ``"wavespeed"`` \| ``"zai-org"`` \| ``"auto"`` |
| `task` | ``"table-question-answering"`` |

#### Retorna[[getproviderhelper.returns]]

`TableQuestionAnsweringTaskHelper` & `TaskProviderHelper`

#### Definido em[[getproviderhelper.defined-in]]

[inference/src/lib/getProviderHelper.ts:305](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/getProviderHelper.ts#L305)

▸ **getProviderHelper**(`provider`, `task`): `TabularClassificationTaskHelper` & `TaskProviderHelper`

#### Parâmetros[[getproviderhelper.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `provider` | ``"baseten"`` \| ``"cerebras"`` \| ``"cohere"`` \| ``"deepinfra"`` \| ``"fal-ai"`` \| ``"featherless-ai"`` \| ``"fireworks-ai"`` \| ``"groq"`` \| ``"hf-inference"`` \| ``"humain-ai"`` \| ``"novita"`` \| ``"nscale"`` \| ``"openai"`` \| ``"openrouter"`` \| ``"ovhcloud"`` \| ``"publicai"`` \| ``"replicate"`` \| ``"scaleway"`` \| ``"together"`` \| ``"wavespeed"`` \| ``"zai-org"`` \| ``"auto"`` |
| `task` | ``"tabular-classification"`` |

#### Retorna[[getproviderhelper.returns]]

`TabularClassificationTaskHelper` & `TaskProviderHelper`

#### Definido em[[getproviderhelper.defined-in]]

[inference/src/lib/getProviderHelper.ts:309](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/getProviderHelper.ts#L309)

▸ **getProviderHelper**(`provider`, `task`): `TabularRegressionTaskHelper` & `TaskProviderHelper`

#### Parâmetros[[getproviderhelper.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `provider` | ``"baseten"`` \| ``"cerebras"`` \| ``"cohere"`` \| ``"deepinfra"`` \| ``"fal-ai"`` \| ``"featherless-ai"`` \| ``"fireworks-ai"`` \| ``"groq"`` \| ``"hf-inference"`` \| ``"humain-ai"`` \| ``"novita"`` \| ``"nscale"`` \| ``"openai"`` \| ``"openrouter"`` \| ``"ovhcloud"`` \| ``"publicai"`` \| ``"replicate"`` \| ``"scaleway"`` \| ``"together"`` \| ``"wavespeed"`` \| ``"zai-org"`` \| ``"auto"`` |
| `task` | ``"tabular-regression"`` |

#### Retorna[[getproviderhelper.returns]]

`TabularRegressionTaskHelper` & `TaskProviderHelper`

#### Definido em[[getproviderhelper.defined-in]]

[inference/src/lib/getProviderHelper.ts:313](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/getProviderHelper.ts#L313)

▸ **getProviderHelper**(`provider`, `task`): `TokenClassificationTaskHelper` & `TaskProviderHelper`

#### Parâmetros[[getproviderhelper.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `provider` | ``"baseten"`` \| ``"cerebras"`` \| ``"cohere"`` \| ``"deepinfra"`` \| ``"fal-ai"`` \| ``"featherless-ai"`` \| ``"fireworks-ai"`` \| ``"groq"`` \| ``"hf-inference"`` \| ``"humain-ai"`` \| ``"novita"`` \| ``"nscale"`` \| ``"openai"`` \| ``"openrouter"`` \| ``"ovhcloud"`` \| ``"publicai"`` \| ``"replicate"`` \| ``"scaleway"`` \| ``"together"`` \| ``"wavespeed"`` \| ``"zai-org"`` \| ``"auto"`` |
| `task` | ``"token-classification"`` |

#### Retorna[[getproviderhelper.returns]]

`TokenClassificationTaskHelper` & `TaskProviderHelper`

#### Definido em[[getproviderhelper.defined-in]]

[inference/src/lib/getProviderHelper.ts:317](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/getProviderHelper.ts#L317)

▸ **getProviderHelper**(`provider`, `task`): `TranslationTaskHelper` & `TaskProviderHelper`

#### Parâmetros[[getproviderhelper.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `provider` | ``"baseten"`` \| ``"cerebras"`` \| ``"cohere"`` \| ``"deepinfra"`` \| ``"fal-ai"`` \| ``"featherless-ai"`` \| ``"fireworks-ai"`` \| ``"groq"`` \| ``"hf-inference"`` \| ``"humain-ai"`` \| ``"novita"`` \| ``"nscale"`` \| ``"openai"`` \| ``"openrouter"`` \| ``"ovhcloud"`` \| ``"publicai"`` \| ``"replicate"`` \| ``"scaleway"`` \| ``"together"`` \| ``"wavespeed"`` \| ``"zai-org"`` \| ``"auto"`` |
| `task` | ``"translation"`` |

#### Retorna[[getproviderhelper.returns]]

`TranslationTaskHelper` & `TaskProviderHelper`

#### Definido em[[getproviderhelper.defined-in]]

[inference/src/lib/getProviderHelper.ts:321](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/getProviderHelper.ts#L321)

▸ **getProviderHelper**(`provider`, `task`): `SummarizationTaskHelper` & `TaskProviderHelper`

#### Parâmetros[[getproviderhelper.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `provider` | ``"baseten"`` \| ``"cerebras"`` \| ``"cohere"`` \| ``"deepinfra"`` \| ``"fal-ai"`` \| ``"featherless-ai"`` \| ``"fireworks-ai"`` \| ``"groq"`` \| ``"hf-inference"`` \| ``"humain-ai"`` \| ``"novita"`` \| ``"nscale"`` \| ``"openai"`` \| ``"openrouter"`` \| ``"ovhcloud"`` \| ``"publicai"`` \| ``"replicate"`` \| ``"scaleway"`` \| ``"together"`` \| ``"wavespeed"`` \| ``"zai-org"`` \| ``"auto"`` |
| `task` | ``"summarization"`` |

#### Retorna[[getproviderhelper.returns]]

`SummarizationTaskHelper` & `TaskProviderHelper`

#### Definido em[[getproviderhelper.defined-in]]

[inference/src/lib/getProviderHelper.ts:325](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/getProviderHelper.ts#L325)

▸ **getProviderHelper**(`provider`, `task`): `VisualQuestionAnsweringTaskHelper` & `TaskProviderHelper`

#### Parâmetros[[getproviderhelper.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `provider` | ``"baseten"`` \| ``"cerebras"`` \| ``"cohere"`` \| ``"deepinfra"`` \| ``"fal-ai"`` \| ``"featherless-ai"`` \| ``"fireworks-ai"`` \| ``"groq"`` \| ``"hf-inference"`` \| ``"humain-ai"`` \| ``"novita"`` \| ``"nscale"`` \| ``"openai"`` \| ``"openrouter"`` \| ``"ovhcloud"`` \| ``"publicai"`` \| ``"replicate"`` \| ``"scaleway"`` \| ``"together"`` \| ``"wavespeed"`` \| ``"zai-org"`` \| ``"auto"`` |
| `task` | ``"visual-question-answering"`` |

#### Retorna[[getproviderhelper.returns]]

`VisualQuestionAnsweringTaskHelper` & `TaskProviderHelper`

#### Definido em[[getproviderhelper.defined-in]]

[inference/src/lib/getProviderHelper.ts:329](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/getProviderHelper.ts#L329)

▸ **getProviderHelper**(`provider`, `task`): `TaskProviderHelper`

#### Parâmetros[[getproviderhelper.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `provider` | ``"baseten"`` \| ``"cerebras"`` \| ``"cohere"`` \| ``"deepinfra"`` \| ``"fal-ai"`` \| ``"featherless-ai"`` \| ``"fireworks-ai"`` \| ``"groq"`` \| ``"hf-inference"`` \| ``"humain-ai"`` \| ``"novita"`` \| ``"nscale"`` \| ``"openai"`` \| ``"openrouter"`` \| ``"ovhcloud"`` \| ``"publicai"`` \| ``"replicate"`` \| ``"scaleway"`` \| ``"together"`` \| ``"wavespeed"`` \| ``"zai-org"`` \| ``"auto"`` |
| `task` | `undefined` \| [`InferenceTask`](modules#inferencetask) |

#### Retorna[[getproviderhelper.returns]]

`TaskProviderHelper`

#### Definido em[[getproviderhelper.defined-in]]

[inference/src/lib/getProviderHelper.ts:333](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/getProviderHelper.ts#L333)

___

### imageClassification

▸ **imageClassification**(`args`, `options?`): `Promise`\<`ImageClassificationOutput`\>

Esta tarefa lê uma entrada de imagem e produz a probabilidade das classes. Modelo recomendado: google/vit-base-patch16-224

#### Parâmetros[[imageclassification.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`ImageClassificationArgs`](modules#imageclassificationargs) |
| `options?` | [`Options`](interfaces/Options) |

#### Retorna[[imageclassification.returns]]

`Promise`\<`ImageClassificationOutput`\>

#### Definido em[[imageclassification.defined-in]]

[inference/src/tasks/cv/imageClassification.ts:14](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/cv/imageClassification.ts#L14)

___

### imageSegmentation

▸ **imageSegmentation**(`args`, `options?`): `Promise`\<`ImageSegmentationOutput`\>

Esta tarefa lê uma entrada de imagem e produz a probabilidade das classes & as caixas delimitadoras dos objetos detectados. Modelo recomendado: facebook/detr-resnet-50-panoptic

#### Parâmetros[[imagesegmentation.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`ImageSegmentationArgs`](modules#imagesegmentationargs) |
| `options?` | [`Options`](interfaces/Options) |

#### Retorna[[imagesegmentation.returns]]

`Promise`\<`ImageSegmentationOutput`\>

#### Definido em[[imagesegmentation.defined-in]]

[inference/src/tasks/cv/imageSegmentation.ts:14](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/cv/imageSegmentation.ts#L14)

___

### imageTextToImage

▸ **imageTextToImage**(`args`, `options?`): `Promise`\<`Blob`\>

Esta tarefa recebe uma imagem e um texto como entrada e gera uma nova imagem. Modelo recomendado: black-forest-labs/FLUX.2-dev

#### Parâmetros[[imagetexttoimage.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`ImageTextToImageArgs`](modules#imagetexttoimageargs) |
| `options?` | [`Options`](interfaces/Options) |

#### Retorna[[imagetexttoimage.returns]]

`Promise`\<`Blob`\>

#### Definido em[[imagetexttoimage.defined-in]]

[inference/src/tasks/cv/imageTextToImage.ts:13](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/cv/imageTextToImage.ts#L13)

___

### imageTextToVideo

▸ **imageTextToVideo**(`args`, `options?`): `Promise`\<`Blob`\>

Esta tarefa recebe uma imagem e um texto como entrada e gera um vídeo como saída. Modelo recomendado: Lightricks/LTX-Video

#### Parâmetros[[imagetexttovideo.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`ImageTextToVideoArgs`](modules#imagetexttovideoargs) |
| `options?` | [`Options`](interfaces/Options) |

#### Retorna[[imagetexttovideo.returns]]

`Promise`\<`Blob`\>

#### Definido em[[imagetexttovideo.defined-in]]

[inference/src/tasks/cv/imageTextToVideo.ts:13](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/cv/imageTextToVideo.ts#L13)

___

### imageToImage

▸ **imageToImage**(`args`, `options?`): `Promise`\<`Blob`\>

Esta tarefa lê uma entrada de texto e gera uma imagem. Modelo recomendado: lllyasviel/sd-controlnet-depth

#### Parâmetros[[imagetoimage.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`ImageToImageArgs`](modules#imagetoimageargs) |
| `options?` | [`Options`](interfaces/Options) |

#### Retorna[[imagetoimage.returns]]

`Promise`\<`Blob`\>

#### Definido em[[imagetoimage.defined-in]]

[inference/src/tasks/cv/imageToImage.ts:14](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/cv/imageToImage.ts#L14)

___

### imageToText

▸ **imageToText**(`args`, `options?`): `Promise`\<`ImageToTextOutput`\>

Esta tarefa lê uma entrada de imagem e gera a legenda de texto.

#### Parâmetros[[imagetotext.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`ImageToTextArgs`](modules#imagetotextargs) |
| `options?` | [`Options`](interfaces/Options) |

#### Retorna[[imagetotext.returns]]

`Promise`\<`ImageToTextOutput`\>

#### Definido em[[imagetotext.defined-in]]

[inference/src/tasks/cv/imageToText.ts:12](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/cv/imageToText.ts#L12)

___

### imageToVideo

▸ **imageToVideo**(`args`, `options?`): `Promise`\<`Blob`\>

Esta tarefa lê uma entrada de texto e gera uma imagem. Modelo recomendado: Wan-AI/Wan2.1-I2V-14B-720P

#### Parâmetros[[imagetovideo.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`ImageToVideoArgs`](modules#imagetovideoargs) |
| `options?` | [`Options`](interfaces/Options) |

#### Retorna[[imagetovideo.returns]]

`Promise`\<`Blob`\>

#### Definido em[[imagetovideo.defined-in]]

[inference/src/tasks/cv/imageToVideo.ts:14](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/cv/imageToVideo.ts#L14)

___

### makeRequestOptions

▸ **makeRequestOptions**(`args`, `providerHelper`, `options?`): `Promise`\<\{ `info`: `RequestInit` ; `url`: `string`  }\>

Auxiliar que prepara os argumentos da solicitação. Esta versão assíncrona trata a etapa de resolução do ID do modelo.

#### Parâmetros[[makerequestoptions.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`RequestArgs`](modules#requestargs) & \{ `data?`: `Blob` \| `ArrayBuffer` ; `stream?`: `boolean`  } |
| `providerHelper` | `TaskProviderHelper` |
| `options?` | [`Options`](interfaces/Options) & \{ `task?`: [`InferenceTask`](modules#inferencetask)  } |

#### Retorna[[makerequestoptions.returns]]

`Promise`\<\{ `info`: `RequestInit` ; `url`: `string`  }\>

#### Definido em[[makerequestoptions.defined-in]]

[inference/src/lib/makeRequestOptions.ts:19](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/makeRequestOptions.ts#L19)

___

### makeRequestOptionsFromResolvedModel

▸ **makeRequestOptionsFromResolvedModel**(`resolvedModel`, `providerHelper`, `args`, `mapping`, `options?`): `Object`

Auxiliar que prepara os argumentos da solicitação. - apenas para uso interno Esta versão síncrona ignora a etapa de resolução do ID do modelo

#### Parâmetros[[makerequestoptionsfromresolvedmodel.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `resolvedModel` | `string` |
| `providerHelper` | `TaskProviderHelper` |
| `args` | [`RequestArgs`](modules#requestargs) & \{ `data?`: `Blob` \| `ArrayBuffer` ; `stream?`: `boolean`  } |
| `mapping` | `undefined` \| [`InferenceProviderMappingEntry`](interfaces/InferenceProviderMappingEntry) |
| `options?` | [`Options`](interfaces/Options) & \{ `outputType?`: [`OutputType`](modules#outputtype) ; `task?`: [`InferenceTask`](modules#inferencetask)  } |

#### Retorna[[makerequestoptionsfromresolvedmodel.returns]]

`Object`

| Nome | Tipo |
| :------ | :------ |
| `info` | `RequestInit` |
| `url` | `string` |

#### Definido em[[makerequestoptionsfromresolvedmodel.defined-in]]

[inference/src/lib/makeRequestOptions.ts:105](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/makeRequestOptions.ts#L105)

___

### objectDetection

▸ **objectDetection**(`args`, `options?`): `Promise`\<`ObjectDetectionOutput`\>

Esta tarefa lê uma entrada de imagem e produz a probabilidade das classes & as caixas delimitadoras dos objetos detectados. Modelo recomendado: facebook/detr-resnet-50

#### Parâmetros[[objectdetection.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`ObjectDetectionArgs`](modules#objectdetectionargs) |
| `options?` | [`Options`](interfaces/Options) |

#### Retorna[[objectdetection.returns]]

`Promise`\<`ObjectDetectionOutput`\>

#### Definido em[[objectdetection.defined-in]]

[inference/src/tasks/cv/objectDetection.ts:14](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/cv/objectDetection.ts#L14)

___

### questionAnswering

▸ **questionAnswering**(`args`, `options?`): `Promise`\<`QuestionAnsweringOutput`[`number`]\>

Quer ter um bot que sabe de tudo e pode responder a qualquer pergunta? Modelo recomendado: deepset/roberta-base-squad2

#### Parâmetros[[questionanswering.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`QuestionAnsweringArgs`](modules#questionansweringargs) |
| `options?` | [`Options`](interfaces/Options) |

#### Retorna[[questionanswering.returns]]

`Promise`\<`QuestionAnsweringOutput`[`number`]\>

#### Definido em[[questionanswering.defined-in]]

[inference/src/tasks/nlp/questionAnswering.ts:13](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/nlp/questionAnswering.ts#L13)

___

### request

▸ **request**\<`T`\>(`args`, `options?`): `Promise`\<`T`\>

Primitive para fazer chamadas personalizadas ao provedor de inferência

#### Parâmetros de tipo[[request.type-parameters]]

| Nome |
| :------ |
| `T` |

#### Parâmetros[[request.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`RequestArgs`](modules#requestargs) |
| `options?` | [`Options`](interfaces/Options) & \{ `task?`: [`InferenceTask`](modules#inferencetask)  } |

#### Retorna[[request.returns]]

`Promise`\<`T`\>

**`Deprecated`**

Use funções de tarefa específicas em vez disso. Esta função será removida em uma versão futura.

#### Definido em[[request.defined-in]]

[inference/src/tasks/custom/request.ts:11](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/custom/request.ts#L11)

___

### sentenceSimilarity

▸ **sentenceSimilarity**(`args`, `options?`): `Promise`\<`SentenceSimilarityOutput`\>

Calcule a similaridade semântica entre um texto e uma lista de outras frases comparando seus embeddings.

#### Parâmetros[[sentencesimilarity.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`SentenceSimilarityArgs`](modules#sentencesimilarityargs) |
| `options?` | [`Options`](interfaces/Options) |

#### Retorna[[sentencesimilarity.returns]]

`Promise`\<`SentenceSimilarityOutput`\>

#### Definido em[[sentencesimilarity.defined-in]]

[inference/src/tasks/nlp/sentenceSimilarity.ts:12](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/nlp/sentenceSimilarity.ts#L12)

___

### setLogger

▸ **setLogger**(`logger`): `void`

#### Parâmetros[[setlogger.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `logger` | [`Logger`](interfaces/Logger) |

#### Retorna[[setlogger.returns]]

`void`

#### Definido em[[setlogger.defined-in]]

[inference/src/lib/logger.ts:5](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/lib/logger.ts#L5)

___

### streamingRequest

▸ **streamingRequest**\<`T`\>(`args`, `options?`): `AsyncGenerator`\<`T`\>

Primitive para fazer chamadas de inferência personalizadas que esperam eventos enviados pelo servidor e retorna a resposta por meio de um gerador

#### Parâmetros de tipo[[streamingrequest.type-parameters]]

| Nome |
| :------ |
| `T` |

#### Parâmetros[[streamingrequest.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`RequestArgs`](modules#requestargs) |
| `options?` | [`Options`](interfaces/Options) & \{ `task?`: [`InferenceTask`](modules#inferencetask)  } |

#### Retorna[[streamingrequest.returns]]

`AsyncGenerator`\<`T`\>

**`Deprecated`**

Use funções de tarefa específicas em vez disso. Esta função será removida em uma versão futura.

#### Definido em[[streamingrequest.defined-in]]

[inference/src/tasks/custom/streamingRequest.ts:11](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/custom/streamingRequest.ts#L11)

___

### sumarização

▸ **summarization**(`args`, `options?`): `Promise`\<`SummarizationOutput`\>

Esta tarefa é bem conhecida por resumir textos mais longos em textos mais curtos. Tenha cuidado, pois alguns modelos possuem um comprimento máximo de entrada. Isso significa que o resumo não consegue processar, por exemplo, livros inteiros. Tenha cuidado ao escolher seu modelo.

#### Parâmetros[[summarization.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`SummarizationArgs`](modules#summarizationargs) |
| `options?` | [`Options`](interfaces/Options) |

#### Retorna[[summarization.returns]]

`Promise`\<`SummarizationOutput`\>

#### Definido em[[summarization.defined-in]]

[inference/src/tasks/nlp/summarization.ts:12](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/nlp/summarization.ts#L12)

___

### tableQuestionAnswering

▸ **tableQuestionAnswering**(`args`, `options?`): `Promise`\<`TableQuestionAnsweringOutput`[`number`]\>

Não sabe SQL? Não quer se aprofundar em uma planilha grande? Faça perguntas em inglês simples! Modelo recomendado: google/tapas-base-finetuned-wtq.

#### Parâmetros[[tablequestionanswering.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`TableQuestionAnsweringArgs`](modules#tablequestionansweringargs) |
| `options?` | [`Options`](interfaces/Options) |

#### Retorna[[tablequestionanswering.returns]]

`Promise`\<`TableQuestionAnsweringOutput`[`number`]\>

#### Definido em[[tablequestionanswering.defined-in]]

[inference/src/tasks/nlp/tableQuestionAnswering.ts:12](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/nlp/tableQuestionAnswering.ts#L12)

___

### tabularClassification

▸ **tabularClassification**(`args`, `options?`): `Promise`\<[`TabularClassificationOutput`](modules#tabularclassificationoutput)\>

Prevê o rótulo alvo para um conjunto de recursos em formato tabular. Normalmente, você treinará um modelo de classificação em seus dados de treinamento e o usará com seus novos dados no mesmo formato. Modelo de exemplo: vvmnnnkv/wine-quality

#### Parâmetros[[tabularclassification.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`TabularClassificationArgs`](modules#tabularclassificationargs) |
| `options?` | [`Options`](interfaces/Options) |

#### Retorna[[tabularclassification.returns]]

`Promise`\<[`TabularClassificationOutput`](modules#tabularclassificationoutput)\>

#### Definido em[[tabularclassification.defined-in]]

[inference/src/tasks/tabular/tabularClassification.ts:25](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/tabular/tabularClassification.ts#L25)

___

### tabularRegression

▸ **tabularRegression**(`args`, `options?`): `Promise`\<[`TabularRegressionOutput`](modules#tabularregressionoutput)\>

Prevê o valor de destino para um conjunto de recursos em formato tabular. Normalmente, você treinará um modelo de regressão em seus dados de treinamento e o usará com seus novos dados no mesmo formato. Modelo de exemplo: scikit-learn/Fish-Weight

#### Parâmetros[[tabularregression.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`TabularRegressionArgs`](modules#tabularregressionargs) |
| `options?` | [`Options`](interfaces/Options) |

#### Retorna[[tabularregression.returns]]

`Promise`\<[`TabularRegressionOutput`](modules#tabularregressionoutput)\>

#### Definido em[[tabularregression.defined-in]]

[inference/src/tasks/tabular/tabularRegression.ts:25](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/tabular/tabularRegression.ts#L25)

___

### textClassification

▸ **textClassification**(`args`, `options?`): `Promise`\<`TextClassificationOutput`\>

Normalmente usado para análise de sentimento, isso exibirá a probabilidade das classes de uma entrada. Modelo recomendado: distilbert-base-uncased-finetuned-sst-2-english

#### Parâmetros[[textclassification.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`TextClassificationArgs`](modules#textclassificationargs) |
| `options?` | [`Options`](interfaces/Options) |

#### Retorna[[textclassification.returns]]

`Promise`\<`TextClassificationOutput`\>

#### Definido em[[textclassification.defined-in]]

[inference/src/tasks/nlp/textClassification.ts:12](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/nlp/textClassification.ts#L12)

___

### textGeneration

▸ **textGeneration**(`args`, `options?`): `Promise`\<[`TextGenerationOutput`](interfaces/TextGenerationOutput)\>

Use para continuar um texto a partir de um prompt. Esta é uma tarefa muito genérica. Modelo recomendado: gpt2 (é um modelo simples, mas divertido para experimentar).

#### Parâmetros[[textgeneration.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`BaseArgs`](interfaces/BaseArgs) & [`TextGenerationInput`](interfaces/TextGenerationInput) |
| `options?` | [`Options`](interfaces/Options) |

#### Retorna[[textgeneration.returns]]

`Promise`\<[`TextGenerationOutput`](interfaces/TextGenerationOutput)\>

#### Definido em[[textgeneration.defined-in]]

[inference/src/tasks/nlp/textGeneration.ts:12](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/nlp/textGeneration.ts#L12)

___

### textGenerationStream

▸ **textGenerationStream**(`args`, `options?`): `AsyncGenerator`\<[`TextGenerationStreamOutput`](interfaces/TextGenerationStreamOutput)\>

Use para continuar um texto a partir de um prompt. Igual a `textGeneration`, mas retorna um gerador que pode ser lido um token de cada vez

#### Parâmetros[[textgenerationstream.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`BaseArgs`](interfaces/BaseArgs) & [`TextGenerationInput`](interfaces/TextGenerationInput) |
| `options?` | [`Options`](interfaces/Options) |

#### Retorna[[textgenerationstream.returns]]

`AsyncGenerator`\<[`TextGenerationStreamOutput`](interfaces/TextGenerationStreamOutput)\>

#### Definido em[[textgenerationstream.defined-in]]

[inference/src/tasks/nlp/textGenerationStream.ts:90](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/nlp/textGenerationStream.ts#L90)

___

### textRanking

▸ **textRanking**(`args`, `options?`): `Promise`\<`TextRankingOutput`\>

Classifique documentos pela sua relevância em relação a uma consulta usando um modelo de reranker.

#### Parâmetros[[textranking.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`TextRankingArgs`](modules#textrankingargs) |
| `options?` | [`Options`](interfaces/Options) |

#### Retorna[[textranking.returns]]

`Promise`\<`TextRankingOutput`\>

#### Definido em[[textranking.defined-in]]

[inference/src/tasks/nlp/textRanking.ts:12](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/nlp/textRanking.ts#L12)

___

### textToAudio

▸ **textToAudio**(`args`, `options?`): `Promise`\<`Blob`\>

Esta tarefa gera áudio (por exemplo, música ou efeitos sonoros) a partir de um prompt de texto de entrada. Modelo de exemplo: stabilityai/stable-audio-open-1.0

#### Parâmetros[[texttoaudio.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`TextToAudioArgs`](modules#texttoaudioargs) |
| `options?` | [`Options`](interfaces/Options) |

#### Retorna[[texttoaudio.returns]]

`Promise`\<`Blob`\>

#### Definido em[[texttoaudio.defined-in]]

[inference/src/tasks/audio/textToAudio.ts:18](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/audio/textToAudio.ts#L18)

___

### textToImage

▸ **textToImage**(`args`, `options?`): `Promise`\<`string`\>

Esta tarefa lê uma entrada de texto e gera uma imagem. Modelo recomendado: stabilityai/stable-diffusion-2

#### Parâmetros[[texttoimage.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`TextToImageArgs`](modules#texttoimageargs) |
| `options?` | `TextToImageOptions` & \{ `outputType`: ``"url"``  } |

#### Retorna[[texttoimage.returns]]

`Promise`\<`string`\>

#### Definido em[[texttoimage.defined-in]]

[inference/src/tasks/cv/textToImage.ts:18](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/cv/textToImage.ts#L18)

▸ **textToImage**(`args`, `options?`): `Promise`\<`string`\>

#### Parâmetros[[texttoimage.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`TextToImageArgs`](modules#texttoimageargs) |
| `options?` | `TextToImageOptions` & \{ `outputType`: ``"dataUrl"``  } |

#### Retorna[[texttoimage.returns]]

`Promise`\<`string`\>

#### Definido em[[texttoimage.defined-in]]

[inference/src/tasks/cv/textToImage.ts:22](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/cv/textToImage.ts#L22)

▸ **textToImage**(`args`, `options?`): `Promise`\<`Blob`\>

#### Parâmetros[[texttoimage.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`TextToImageArgs`](modules#texttoimageargs) |
| `options?` | `TextToImageOptions` & \{ `outputType?`: ``"blob"``  } |

#### Retorna[[texttoimage.returns]]

`Promise`\<`Blob`\>

#### Definido em[[texttoimage.defined-in]]

[inference/src/tasks/cv/textToImage.ts:26](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/cv/textToImage.ts#L26)

▸ **textToImage**(`args`, `options?`): `Promise`\<`Record`\<`string`, `unknown`\>\>

#### Parâmetros[[texttoimage.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`TextToImageArgs`](modules#texttoimageargs) |
| `options?` | `TextToImageOptions` & \{ `outputType?`: ``"json"``  } |

#### Retorna[[texttoimage.returns]]

`Promise`\<`Record`\<`string`, `unknown`\>\>

#### Definido em[[texttoimage.defined-in]]

[inference/src/tasks/cv/textToImage.ts:30](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/cv/textToImage.ts#L30)

___

### textToSpeech

▸ **textToSpeech**(`args`, `options?`): `Promise`\<`Blob`\>

Esta tarefa sintetiza um áudio de uma voz pronunciando um texto dado. Modelo recomendado: espnet/kan-bayashi_ljspeech_vits

#### Parâmetros[[texttospeech.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | `TextToSpeechArgs` |
| `options?` | [`Options`](interfaces/Options) |

#### Retorna[[texttospeech.returns]]

`Promise`\<`Blob`\>

#### Definido em[[texttospeech.defined-in]]

[inference/src/tasks/audio/textToSpeech.ts:15](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/audio/textToSpeech.ts#L15)

___

### textToVideo

▸ **textToVideo**(`args`, `options?`): `Promise`\<[`TextToVideoOutput`](modules#texttovideooutput)\>

#### Parâmetros[[texttovideo.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`TextToVideoArgs`](modules#texttovideoargs) |
| `options?` | [`Options`](interfaces/Options) |

#### Retorna[[texttovideo.returns]]

`Promise`\<[`TextToVideoOutput`](modules#texttovideooutput)\>

#### Definido em[[texttovideo.defined-in]]

[inference/src/tasks/cv/textToVideo.ts:15](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/cv/textToVideo.ts#L15)

___

### tokenClassification

▸ **tokenClassification**(`args`, `options?`): `Promise`\<`TokenClassificationOutput`\>

Normalmente usado para análise de sentenças, seja gramatical, seja Reconhecimento de Entidades Nomeadas (NER), para entender as palavras-chave contidas no texto. Modelo recomendado: dbmdz/bert-large-cased-finetuned-conll03-english

#### Parâmetros[[tokenclassification.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`TokenClassificationArgs`](modules#tokenclassificationargs) |
| `options?` | [`Options`](interfaces/Options) |

#### Retorna[[tokenclassification.returns]]

`Promise`\<`TokenClassificationOutput`\>

#### Definido em[[tokenclassification.defined-in]]

[inference/src/tasks/nlp/tokenClassification.ts:12](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/nlp/tokenClassification.ts#L12)

___

### tradução

▸ **tradução**(`args`, `options?`): `Promise`\<`TranslationOutput`\>

Esta tarefa é bem conhecida para traduzir texto de um idioma para outro. Modelo recomendado: Helsinki-NLP/opus-mt-ru-en.

#### Parâmetros[[translation.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`TranslationArgs`](modules#translationargs) |
| `options?` | [`Options`](interfaces/Options) |

#### Retorna[[translation.returns]]

`Promise`\<`TranslationOutput`\>

#### Definido em[[translation.defined-in]]

[inference/src/tasks/nlp/translation.ts:11](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/nlp/translation.ts#L11)

___

### visualQuestionAnswering

▸ **visualQuestionAnswering**(`args`, `options?`): `Promise`\<`VisualQuestionAnsweringOutput`[`number`]\>

Responde a uma pergunta sobre uma imagem. Modelo recomendado: dandelin/vilt-b32-finetuned-vqa.

#### Parâmetros[[visualquestionanswering.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`VisualQuestionAnsweringArgs`](modules#visualquestionansweringargs) |
| `options?` | [`Options`](interfaces/Options) |

#### Retorna[[visualquestionanswering.returns]]

`Promise`\<`VisualQuestionAnsweringOutput`[`number`]\>

#### Definido em[[visualquestionanswering.defined-in]]

[inference/src/tasks/multimodal/visualQuestionAnswering.ts:19](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/multimodal/visualQuestionAnswering.ts#L19)

___

### zeroShotClassification

▸ **zeroShotClassification**(`args`, `options?`): `Promise`\<`ZeroShotClassificationOutput`\>

Esta tarefa é muito útil para experimentar a classificação sem escrever código: basta passar uma frase/parágrafo e os rótulos possíveis para essa frase, e você obtém um resultado. Modelo recomendado: facebook/bart-large-mnli.

#### Parâmetros[[zeroshotclassification.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`ZeroShotClassificationArgs`](modules#zeroshotclassificationargs) |
| `options?` | [`Options`](interfaces/Options) |

#### Retorna[[zeroshotclassification.returns]]

`Promise`\<`ZeroShotClassificationOutput`\>

#### Definido em[[zeroshotclassification.defined-in]]

[inference/src/tasks/nlp/zeroShotClassification.ts:12](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/nlp/zeroShotClassification.ts#L12)

___

### zeroShotImageClassification

▸ **zeroShotImageClassification**(`args`, `options?`): `Promise`\<`ZeroShotImageClassificationOutput`\>

Classifique uma imagem em classes especificadas. Modelo recomendado: openai/clip-vit-large-patch14-336

#### Parâmetros[[zeroshotimageclassification.parameters]]

| Nome | Tipo |
| :------ | :------ |
| `args` | [`ZeroShotImageClassificationArgs`](modules#zeroshotimageclassificationargs) |
| `options?` | [`Options`](interfaces/Options) |

#### Retorna[[zeroshotimageclassification.returns]]

`Promise`\<`ZeroShotImageClassificationOutput`\>

#### Definido em[[zeroshotimageclassification.defined-in]]

[inference/src/tasks/cv/zeroShotImageClassification.ts:44](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/cv/zeroShotImageClassification.ts#L44)