# Kelas: InferenceClient

## Hierarki

- `Task`

  ↳ **`InferenceClient`**

  ↳↳ [`InferenceClientEndpoint`](InferenceClientEndpoint)

  ↳↳ [`HfInference`](HfInference)

## Konstruktor

### constructor

• **new InferenceClient**(`accessToken?`, `defaultOptions?`): [`InferenceClient`](InferenceClient)

#### Parameter[[constructor.parameters]]

| Nama | Tipe | Nilai default |
| :------ | :------ | :------ |
| `accessToken` | `string` | `""` |
| `defaultOptions` | [`Options`](../interfaces/Options) & \{ `endpointUrl?`: `string`  } | `{}` |

#### Mengembalikan[[constructor.returns]]

[`InferenceClient`](InferenceClient)

#### Didefinisikan di[[constructor.defined-in]]

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

## Properti

### accessToken

• `Private` `Readonly` **accessToken**: `string`

#### Didefinisikan di[[accesstoken.defined-in]]

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

___

### defaultOptions

• `Private` `Readonly` **defaultOptions**: [`Options`](../interfaces/Options)

#### Didefinisikan di[[defaultoptions.defined-in]]

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

## Metode

### audioClassification

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

Tugas ini membaca beberapa input audio dan menghasilkan kemungkinan kelas. Model yang direkomendasikan: superb/hubert-large-superb-er

#### Parameter[[audioclassification.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | [`AudioClassificationArgs`](../modules#audioclassificationargs) |
| `options?` | [`Options`](../interfaces/Options) |

#### Mengembalikan[[audioclassification.returns]]

`Promise`\<`AudioClassificationOutput`\>

#### Didefinisikan di[[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)[]\>

Tugas ini membaca beberapa input audio dan menghasilkan satu atau beberapa file audio. Contoh model: speechbrain/sepformer-wham melakukan pemisahan sumber audio.

#### Parameter[[audiotoaudio.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | [`AudioToAudioArgs`](../modules#audiotoaudioargs) |
| `options?` | [`Options`](../interfaces/Options) |

#### Mengembalikan[[audiotoaudio.returns]]

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

#### Didefinisikan di[[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`\>

Tugas ini membaca beberapa input audio dan mengoutputkan kata-kata yang diucapkan di dalam file audio. Model yang direkomendasikan (bahasa Inggris): facebook/wav2vec2-large-960h-lv60-self

#### Parameter[[automaticspeechrecognition.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | [`AutomaticSpeechRecognitionArgs`](../modules#automaticspeechrecognitionargs) |
| `options?` | [`Options`](../interfaces/Options) |

#### Mengembalikan[[automaticspeechrecognition.returns]]

`Promise`\<`AutomaticSpeechRecognitionOutput`\>

#### Didefinisikan di[[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`\>

Gunakan endpoint chat completion untuk menghasilkan respons terhadap prompt, menggunakan API penyelesaian pesan OpenAI tanpa stream

#### Parameter[[chatcompletion.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | [`BaseArgs`](../interfaces/BaseArgs) & `ChatCompletionInput` |
| `options?` | [`Options`](../interfaces/Options) |

#### Mengembalikan[[chatcompletion.returns]]

`Promise`\<`ChatCompletionOutput`\>

#### Didefinisikan di[[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`\>

Gunakan untuk melanjutkan teks dari sebuah prompt. Sama seperti `textGeneration` tetapi mengembalikan generator yang dapat dibaca satu token pada satu waktu

#### Parameter[[chatcompletionstream.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | [`BaseArgs`](../interfaces/BaseArgs) & `ChatCompletionInput` |
| `options?` | [`Options`](../interfaces/Options) |

#### Mengembalikan[[chatcompletionstream.returns]]

`AsyncGenerator`\<`ChatCompletionStreamOutput`\>

#### Didefinisikan di[[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`]\>

Menjawab pertanyaan pada gambar dokumen. Model yang direkomendasikan: impira/layoutlm-document-qa.

#### Parameter[[documentquestionanswering.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | [`DocumentQuestionAnsweringArgs`](../modules#documentquestionansweringargs) |
| `options?` | [`Options`](../interfaces/Options) |

#### Mengembalikan[[documentquestionanswering.returns]]

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

#### Didefinisikan di[[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)

___

### endpoint

▸ **endpoint**(`endpointUrl`): [`InferenceClient`](InferenceClient)

Mengembalikan instance baru dari InferenceClient yang terhubung ke endpoint yang ditentukan.

Sebagian besar untuk kompatibilitas mundur.

#### Parameter[[endpoint.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `endpointUrl` | `string` |

#### Mengembalikan[[endpoint.returns]]

[`InferenceClient`](InferenceClient)

#### Didefinisikan di[[endpoint.defined-in]]

[inference/src/InferenceClient.ts:46](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/InferenceClient.ts#L46)

___

### featureExtraction

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

Tugas ini membaca beberapa teks dan menghasilkan nilai float mentah, yang biasanya dikonsumsi sebagai bagian dari basis data semantik/pencarian semantik.

#### Parameter[[featureextraction.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | [`FeatureExtractionArgs`](../modules#featureextractionargs) |
| `options?` | [`Options`](../interfaces/Options) |

#### Mengembalikan[[featureextraction.returns]]

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

#### Didefinisikan di[[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`\>

Mencoba mengisi celah dengan kata yang hilang (lebih tepatnya, token). Itulah tugas dasar untuk model BERT.

#### Parameter[[fillmask.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | [`FillMaskArgs`](../modules#fillmaskargs) |
| `options?` | [`Options`](../interfaces/Options) |

#### Mengembalikan[[fillmask.returns]]

`Promise`\<`FillMaskOutput`\>

#### Didefinisikan di[[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)

___

### imageClassification

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

Tugas ini membaca beberapa input gambar dan menghasilkan kemungkinan kelas. Model yang direkomendasikan: google/vit-base-patch16-224

#### Parameter[[imageclassification.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | [`ImageClassificationArgs`](../modules#imageclassificationargs) |
| `options?` | [`Options`](../interfaces/Options) |

#### Mengembalikan[[imageclassification.returns]]

`Promise`\<`ImageClassificationOutput`\>

#### Didefinisikan di[[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`\>

Tugas ini membaca beberapa input gambar dan menghasilkan kemungkinan kelas & kotak pembatas dari objek yang terdeteksi. Model yang direkomendasikan: facebook/detr-resnet-50-panoptic

#### Parameter[[imagesegmentation.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | [`ImageSegmentationArgs`](../modules#imagesegmentationargs) |
| `options?` | [`Options`](../interfaces/Options) |

#### Mengembalikan[[imagesegmentation.returns]]

`Promise`\<`ImageSegmentationOutput`\>

#### Didefinisikan di[[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`\>

Tugas ini menerima input gambar dan teks, lalu menghasilkan gambar baru yang dibuat. Model yang direkomendasikan: black-forest-labs/FLUX.2-dev

#### Parameter[[imagetexttoimage.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | [`ImageTextToImageArgs`](../modules#imagetexttoimageargs) |
| `options?` | [`Options`](../interfaces/Options) |

#### Mengembalikan[[imagetexttoimage.returns]]

`Promise`\<`Blob`\>

#### Didefinisikan di[[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`\>

Tugas ini menerima input gambar dan teks serta menghasilkan video yang dibuat. Model yang direkomendasikan: Lightricks/LTX-Video

#### Parameter[[imagetexttovideo.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | [`ImageTextToVideoArgs`](../modules#imagetexttovideoargs) |
| `options?` | [`Options`](../interfaces/Options) |

#### Mengembalikan[[imagetexttovideo.returns]]

`Promise`\<`Blob`\>

#### Didefinisikan di[[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`\>

Tugas ini membaca beberapa teks input dan menghasilkan gambar. Model yang direkomendasikan: lllyasviel/sd-controlnet-depth

#### Parameter[[imagetoimage.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | [`ImageToImageArgs`](../modules#imagetoimageargs) |
| `options?` | [`Options`](../interfaces/Options) |

#### Mengembalikan[[imagetoimage.returns]]

`Promise`\<`Blob`\>

#### Didefinisikan di[[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`\>

Tugas ini membaca beberapa input gambar dan menghasilkan teks keterangan.

#### Parameter[[imagetotext.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | [`ImageToTextArgs`](../modules#imagetotextargs) |
| `options?` | [`Options`](../interfaces/Options) |

#### Mengembalikan[[imagetotext.returns]]

`Promise`\<`ImageToTextOutput`\>

#### Didefinisikan di[[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`\>

Tugas ini membaca beberapa teks masukan dan menghasilkan gambar. Model yang direkomendasikan: Wan-AI/Wan2.1-I2V-14B-720P

#### Parameter[[imagetovideo.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | [`ImageToVideoArgs`](../modules#imagetovideoargs) |
| `options?` | [`Options`](../interfaces/Options) |

#### Mengembalikan[[imagetovideo.returns]]

`Promise`\<`Blob`\>

#### Didefinisikan di[[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)

___

### objectDetection

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

Tugas ini membaca beberapa input gambar dan menghasilkan kemungkinan kelas & kotak pembatas dari objek yang terdeteksi. Model yang direkomendasikan: facebook/detr-resnet-50

#### Parameter[[objectdetection.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | [`ObjectDetectionArgs`](../modules#objectdetectionargs) |
| `options?` | [`Options`](../interfaces/Options) |

#### Mengembalikan[[objectdetection.returns]]

`Promise`\<`ObjectDetectionOutput`\>

#### Didefinisikan di[[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`]\>

Ingin memiliki bot pintar yang bisa menjawab pertanyaan apa pun? Model yang direkomendasikan: deepset/roberta-base-squad2

#### Parameter[[questionanswering.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | [`QuestionAnsweringArgs`](../modules#questionansweringargs) |
| `options?` | [`Options`](../interfaces/Options) |

#### Mengembalikan[[questionanswering.returns]]

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

#### Didefinisikan di[[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

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

Primitive untuk membuat panggilan khusus ke penyedia inferensi

#### Parameter tipe[[request.type-parameters]]

| Nama |
| :------ |
| `T` |

#### Parameter[[request.parameters]]

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

#### Mengembalikan[[request.returns]]

`Promise`\<`T`\>

**`Deprecated`**

Gunakan fungsi tugas tertentu sebagai gantinya. Fungsi ini akan dihapus dalam versi mendatang.

#### Didefinisikan di[[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`\>

Hitung kemiripan semantik antara satu teks dan daftar kalimat lainnya dengan membandingkan embedding mereka.

#### Parameter[[sentencesimilarity.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | [`SentenceSimilarityArgs`](../modules#sentencesimilarityargs) |
| `options?` | [`Options`](../interfaces/Options) |

#### Mengembalikan[[sentencesimilarity.returns]]

`Promise`\<`SentenceSimilarityOutput`\>

#### Didefinisikan di[[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)

___

### streamingRequest

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

Primitive untuk membuat panggilan inferensi kustom yang mengharapkan server-sent events, dan mengembalikan respons melalui generator

#### Parameter tipe[[streamingrequest.type-parameters]]

| Nama |
| :------ |
| `T` |

#### Parameter[[streamingrequest.parameters]]

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

#### Mengembalikan[[streamingrequest.returns]]

`AsyncGenerator`\<`T`\>

**`Deprecated`**

Gunakan fungsi tugas tertentu sebagai gantinya. Fungsi ini akan dihapus dalam versi mendatang.

#### Didefinisikan di[[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)

___

### ringkasan

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

Tugas ini dikenal luas untuk merangkum teks yang lebih panjang menjadi lebih pendek. Hati-hati, beberapa model memiliki batas maksimum panjang input. Artinya, ringkasan tidak dapat memproses buku utuh, misalnya. Perhatikan dengan baik saat memilih model Anda.

#### Parameter[[summarization.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | [`SummarizationArgs`](../modules#summarizationargs) |
| `options?` | [`Options`](../interfaces/Options) |

#### Mengembalikan[[summarization.returns]]

`Promise`\<`SummarizationOutput`\>

#### Didefinisikan di[[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`]\>

Tidak tahu SQL? Tidak ingin menyelami spreadsheet besar? Ajukan pertanyaan dalam bahasa Inggris biasa! Model yang direkomendasikan: google/tapas-base-finetuned-wtq.

#### Parameter[[tablequestionanswering.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | [`TableQuestionAnsweringArgs`](../modules#tablequestionansweringargs) |
| `options?` | [`Options`](../interfaces/Options) |

#### Mengembalikan[[tablequestionanswering.returns]]

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

#### Didefinisikan di[[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)

___

### Klasifikasi Data Tabular

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

Memprediksi label target untuk seperangkat fitur tertentu dalam bentuk tabular. Biasanya, Anda akan melatih model klasifikasi pada data pelatihan Anda dan menggunakannya dengan data baru Anda yang memiliki format yang sama. Contoh model: vvmnnnkv/wine-quality

#### Parameter[[tabularclassification.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | [`TabularClassificationArgs`](../modules#tabularclassificationargs) |
| `options?` | [`Options`](../interfaces/Options) |

#### Mengembalikan[[tabularclassification.returns]]

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

#### Didefinisikan di[[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)\>

Memprediksi nilai target untuk seperangkat fitur tertentu dalam bentuk tabular. Biasanya, Anda akan melatih model regresi pada data pelatihan Anda dan menggunakannya dengan data baru Anda yang memiliki format yang sama. Contoh model: scikit-learn/Fish-Weight

#### Parameter[[tabularregression.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | [`TabularRegressionArgs`](../modules#tabularregressionargs) |
| `options?` | [`Options`](../interfaces/Options) |

#### Mengembalikan[[tabularregression.returns]]

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

#### Didefinisikan di[[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`\>

Biasanya digunakan untuk analisis sentimen, ini akan menghasilkan kemungkinan kelas dari input. Model yang direkomendasikan: distilbert-base-uncased-finetuned-sst-2-english

#### Parameter[[textclassification.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | [`TextClassificationArgs`](../modules#textclassificationargs) |
| `options?` | [`Options`](../interfaces/Options) |

#### Mengembalikan[[textclassification.returns]]

`Promise`\<`TextClassificationOutput`\>

#### Didefinisikan di[[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)\>

Gunakan untuk melanjutkan teks dari sebuah prompt. Ini adalah tugas yang sangat umum. Model yang direkomendasikan: gpt2 (ini adalah model sederhana, tetapi menyenangkan untuk dicoba).

#### Parameter[[textgeneration.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | [`BaseArgs`](../interfaces/BaseArgs) & [`TextGenerationInput`](../interfaces/TextGenerationInput) |
| `options?` | [`Options`](../interfaces/Options) |

#### Mengembalikan[[textgeneration.returns]]

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

#### Didefinisikan di[[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)\>

Gunakan untuk melanjutkan teks dari sebuah prompt. Sama seperti `textGeneration` tetapi mengembalikan generator yang dapat dibaca satu token pada satu waktu

#### Parameter[[textgenerationstream.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | [`BaseArgs`](../interfaces/BaseArgs) & [`TextGenerationInput`](../interfaces/TextGenerationInput) |
| `options?` | [`Options`](../interfaces/Options) |

#### Mengembalikan[[textgenerationstream.returns]]

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

#### Didefinisikan di[[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`\>

Urutkan dokumen berdasarkan relevansinya terhadap kueri menggunakan model reranker.

#### Parameter[[textranking.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | [`TextRankingArgs`](../modules#textrankingargs) |
| `options?` | [`Options`](../interfaces/Options) |

#### Mengembalikan[[textranking.returns]]

`Promise`\<`TextRankingOutput`\>

#### Didefinisikan di[[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`\>

Tugas ini menghasilkan audio (misalnya musik atau efek suara) dari prompt teks input. Contoh model: stabilityai/stable-audio-open-1.0

#### Parameter[[texttoaudio.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | [`TextToAudioArgs`](../modules#texttoaudioargs) |
| `options?` | [`Options`](../interfaces/Options) |

#### Mengembalikan[[texttoaudio.returns]]

`Promise`\<`Blob`\>

#### Didefinisikan di[[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`\>

Tugas ini membaca beberapa teks masukan dan menghasilkan gambar. Model yang direkomendasikan: stabilityai/stable-diffusion-2

#### Parameter[[texttoimage.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | [`TextToImageArgs`](../modules#texttoimageargs) |
| `options?` | `TextToImageOptions` & \{ `outputType`: ``"url"``  } |

#### Mengembalikan[[texttoimage.returns]]

`Promise`\<`string`\>

#### Didefinisikan di[[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`\>

#### Parameter[[texttoimage.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | [`TextToImageArgs`](../modules#texttoimageargs) |
| `options?` | `TextToImageOptions` & \{ `outputType`: ``"dataUrl"``  } |

#### Mengembalikan[[texttoimage.returns]]

`Promise`\<`string`\>

#### Didefinisikan di[[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`\>

#### Parameter[[texttoimage.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | [`TextToImageArgs`](../modules#texttoimageargs) |
| `options?` | `TextToImageOptions` & \{ `outputType?`: ``"blob"``  } |

#### Mengembalikan[[texttoimage.returns]]

`Promise`\<`Blob`\>

#### Didefinisikan di[[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`\>\>

#### Parameter[[texttoimage.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | [`TextToImageArgs`](../modules#texttoimageargs) |
| `options?` | `TextToImageOptions` & \{ `outputType?`: ``"json"``  } |

#### Mengembalikan[[texttoimage.returns]]

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

#### Didefinisikan di[[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`\>

Tugas ini mensintesis audio suara yang mengucapkan teks tertentu. Model yang direkomendasikan: espnet/kan-bayashi_ljspeech_vits

#### Parameter[[texttospeech.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | `TextToSpeechArgs` |
| `options?` | [`Options`](../interfaces/Options) |

#### Mengembalikan[[texttospeech.returns]]

`Promise`\<`Blob`\>

#### Didefinisikan di[[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)\>

#### Parameter[[texttovideo.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | [`TextToVideoArgs`](../modules#texttovideoargs) |
| `options?` | [`Options`](../interfaces/Options) |

#### Mengembalikan[[texttovideo.returns]]

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

#### Didefinisikan di[[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`\>

Biasanya digunakan untuk parsing kalimat, baik secara gramatikal maupun Named Entity Recognition (NER) untuk memahami kata kunci yang terkandung dalam teks. Model yang direkomendasikan: dbmdz/bert-large-cased-finetuned-conll03-english

#### Parameter[[tokenclassification.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | [`TokenClassificationArgs`](../modules#tokenclassificationargs) |
| `options?` | [`Options`](../interfaces/Options) |

#### Mengembalikan[[tokenclassification.returns]]

`Promise`\<`TokenClassificationOutput`\>

#### Didefinisikan di[[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)

___

### terjemahan

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

Tugas ini dikenal luas untuk menerjemahkan teks dari satu bahasa ke bahasa lain. Model yang direkomendasikan: Helsinki-NLP/opus-mt-ru-en.

#### Parameter[[translation.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | [`TranslationArgs`](../modules#translationargs) |
| `options?` | [`Options`](../interfaces/Options) |

#### Mengembalikan[[translation.returns]]

`Promise`\<`TranslationOutput`\>

#### Didefinisikan di[[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`]\>

Menjawab pertanyaan pada gambar. Model yang direkomendasikan: dandelin/vilt-b32-finetuned-vqa.

#### Parameter[[visualquestionanswering.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | [`VisualQuestionAnsweringArgs`](../modules#visualquestionansweringargs) |
| `options?` | [`Options`](../interfaces/Options) |

#### Mengembalikan[[visualquestionanswering.returns]]

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

#### Didefinisikan di[[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`\>

Tugas ini sangat berguna untuk mencoba klasifikasi tanpa kode, Anda cukup melewatkan kalimat/paragraf dan label-label yang mungkin untuk kalimat tersebut, lalu Anda akan mendapatkan hasil. Model yang direkomendasikan: facebook/bart-large-mnli.

#### Parameter[[zeroshotclassification.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | [`ZeroShotClassificationArgs`](../modules#zeroshotclassificationargs) |
| `options?` | [`Options`](../interfaces/Options) |

#### Mengembalikan[[zeroshotclassification.returns]]

`Promise`\<`ZeroShotClassificationOutput`\>

#### Didefinisikan di[[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`\>

Klasifikasikan gambar ke kelas yang ditentukan. Model yang direkomendasikan: openai/clip-vit-large-patch14-336

#### Parameter[[zeroshotimageclassification.parameters]]

| Nama | Tipe |
| :------ | :------ |
| `args` | [`ZeroShotImageClassificationArgs`](../modules#zeroshotimageclassificationargs) |
| `options?` | [`Options`](../interfaces/Options) |

#### Mengembalikan[[zeroshotimageclassification.returns]]

`Promise`\<`ZeroShotImageClassificationOutput`\>

#### Didefinisikan di[[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)