pipelines

Pipelines provide a high-level, easy to use, API for running machine learning models.

Example: Instantiate pipeline using thepipeline function.

import { pipeline }from'@huggingface/transformers';const classifier =awaitpipeline('sentiment-analysis');const output =awaitclassifier('I love transformers!');// [{'label': 'POSITIVE', 'score': 0.999817686}]

• pipelines
  • static
    • .Pipeline
      • new Pipeline(options)
      • .dispose() :DisposeType
    • .TextClassificationPipeline
      • new TextClassificationPipeline(options)
      • ._call() :TextClassificationPipelineCallback
    • .TokenClassificationPipeline
      • new TokenClassificationPipeline(options)
      • ._call() :TokenClassificationPipelineCallback
    • .QuestionAnsweringPipeline
      • new QuestionAnsweringPipeline(options)
      • ._call() :QuestionAnsweringPipelineCallback
    • .FillMaskPipeline
      • new FillMaskPipeline(options)
      • ._call() :FillMaskPipelineCallback
    • .Text2TextGenerationPipeline
      • new Text2TextGenerationPipeline(options)
      • ._key :’generated_text’
      • ._call() :Text2TextGenerationPipelineCallback
    • .SummarizationPipeline
      • new SummarizationPipeline(options)
      • ._key :’summary_text’
    • .TranslationPipeline
      • new TranslationPipeline(options)
      • ._key :’translation_text’
    • .TextGenerationPipeline
      • new TextGenerationPipeline(options)
      • ._call() :TextGenerationPipelineCallback
    • .ZeroShotClassificationPipeline
      • new ZeroShotClassificationPipeline(options)
      • .model :any
      • ._call() :ZeroShotClassificationPipelineCallback
    • .FeatureExtractionPipeline
      • new FeatureExtractionPipeline(options)
      • ._call() :FeatureExtractionPipelineCallback
    • .ImageFeatureExtractionPipeline
      • new ImageFeatureExtractionPipeline(options)
      • ._call() :ImageFeatureExtractionPipelineCallback
    • .AudioClassificationPipeline
      • new AudioClassificationPipeline(options)
      • ._call() :AudioClassificationPipelineCallback
    • .ZeroShotAudioClassificationPipeline
      • new ZeroShotAudioClassificationPipeline(options)
      • ._call() :ZeroShotAudioClassificationPipelineCallback
    • .AutomaticSpeechRecognitionPipeline
      • new AutomaticSpeechRecognitionPipeline(options)
      • ._call() :AutomaticSpeechRecognitionPipelineCallback
    • .ImageToTextPipeline
      • new ImageToTextPipeline(options)
      • ._call() :ImageToTextPipelineCallback
    • .ImageClassificationPipeline
      • new ImageClassificationPipeline(options)
      • ._call() :ImageClassificationPipelineCallback
    • .ImageSegmentationPipeline
      • new ImageSegmentationPipeline(options)
      • ._call() :ImageSegmentationPipelineCallback
    • .BackgroundRemovalPipeline
      • new BackgroundRemovalPipeline(options)
      • ._call() :BackgroundRemovalPipelineCallback
    • .ZeroShotImageClassificationPipeline
      • new ZeroShotImageClassificationPipeline(options)
      • ._call() :ZeroShotImageClassificationPipelineCallback
    • .ObjectDetectionPipeline
      • new ObjectDetectionPipeline(options)
      • ._call() :ObjectDetectionPipelineCallback
    • .ZeroShotObjectDetectionPipeline
      • new ZeroShotObjectDetectionPipeline(options)
      • ._call() :ZeroShotObjectDetectionPipelineCallback
    • .DocumentQuestionAnsweringPipeline
      • new DocumentQuestionAnsweringPipeline(options)
      • ._call() :DocumentQuestionAnsweringPipelineCallback
    • .TextToAudioPipeline
      • new TextToAudioPipeline(options)
      • ._call() :TextToAudioPipelineCallback
    • .ImageToImagePipeline
      • new ImageToImagePipeline(options)
      • ._call() :ImageToImagePipelineCallback
    • .DepthEstimationPipeline
      • new DepthEstimationPipeline(options)
      • ._call() :DepthEstimationPipelineCallback
    • .pipeline(task, [model], [options]) ⇒*
  • inner
    • ~ImagePipelineInputs :string |RawImage |URL |Blob |HTMLCanvasElement |OffscreenCanvas
    • ~AudioPipelineInputs :string |URL |Float32Array |Float64Array
    • ~BoundingBox :Object
    • ~Disposable ⇒Promise.<void>
    • ~TextPipelineConstructorArgs :Object
    • ~ImagePipelineConstructorArgs :Object
    • ~TextImagePipelineConstructorArgs :Object
    • ~TextClassificationPipelineType ⇒Promise.<(TextClassificationOutput|Array<TextClassificationOutput>)>
    • ~TokenClassificationPipelineType ⇒Promise.<(TokenClassificationOutput|Array<TokenClassificationOutput>)>
    • ~QuestionAnsweringPipelineType ⇒Promise.<(QuestionAnsweringOutput|Array<QuestionAnsweringOutput>)>
    • ~FillMaskPipelineType ⇒Promise.<(FillMaskOutput|Array<FillMaskOutput>)>
    • ~Text2TextGenerationPipelineType ⇒Promise.<(Text2TextGenerationOutput|Array<Text2TextGenerationOutput>)>
    • ~SummarizationPipelineType ⇒Promise.<(SummarizationOutput|Array<SummarizationOutput>)>
    • ~TranslationPipelineType ⇒Promise.<(TranslationOutput|Array<TranslationOutput>)>
    • ~TextGenerationPipelineType ⇒Promise.<(TextGenerationOutput|Array<TextGenerationOutput>)>
    • ~ZeroShotClassificationPipelineType ⇒Promise.<(ZeroShotClassificationOutput|Array<ZeroShotClassificationOutput>)>
    • ~FeatureExtractionPipelineType ⇒Promise.<Tensor>
    • ~ImageFeatureExtractionPipelineType ⇒Promise.<Tensor>
    • ~AudioClassificationPipelineType ⇒Promise.<(AudioClassificationOutput|Array<AudioClassificationOutput>)>
    • ~ZeroShotAudioClassificationPipelineType ⇒Promise.<(Array<ZeroShotAudioClassificationOutput>|Array<Array<ZeroShotAudioClassificationOutput>>)>
    • ~Chunk :Object
    • ~AutomaticSpeechRecognitionPipelineType ⇒Promise.<(AutomaticSpeechRecognitionOutput|Array<AutomaticSpeechRecognitionOutput>)>
    • ~ImageToTextPipelineType ⇒Promise.<(ImageToTextOutput|Array<ImageToTextOutput>)>
    • ~ImageClassificationPipelineType ⇒Promise.<(ImageClassificationOutput|Array<ImageClassificationOutput>)>
    • ~ImageSegmentationPipelineType ⇒Promise.<Array<ImageSegmentationPipelineOutput>>
    • ~BackgroundRemovalPipelineType ⇒Promise.<Array<RawImage>>
    • ~ZeroShotImageClassificationPipelineType ⇒Promise.<(Array<ZeroShotImageClassificationOutput>|Array<Array<ZeroShotImageClassificationOutput>>)>
    • ~ObjectDetectionPipelineType ⇒Promise.<(ObjectDetectionPipelineOutput|Array<ObjectDetectionPipelineOutput>)>
    • ~ZeroShotObjectDetectionPipelineType ⇒Promise.<(Array<ZeroShotObjectDetectionOutput>|Array<Array<ZeroShotObjectDetectionOutput>>)>
    • ~DocumentQuestionAnsweringPipelineType ⇒Promise.<(DocumentQuestionAnsweringOutput|Array<DocumentQuestionAnsweringOutput>)>
    • ~TextToAudioPipelineConstructorArgs :Object
    • ~TextToAudioPipelineType ⇒Promise.<TextToAudioOutput>
    • ~ImageToImagePipelineType ⇒Promise.<(RawImage|Array<RawImage>)>
    • ~DepthEstimationPipelineType ⇒Promise.<(DepthEstimationPipelineOutput|Array<DepthEstimationPipelineOutput>)>
    • ~AllTasks :*

pipelines.Pipeline

The Pipeline class is the class from which all pipelines inherit.Refer to this class for methods shared across different pipelines.

Kind: static class ofpipelines

• .Pipeline
  • new Pipeline(options)
  • .dispose() :DisposeType

new Pipeline(options)

Create a new Pipeline.

pipeline.dispose() : <code> DisposeType </code>

Kind: instance method ofPipeline

pipelines.TextClassificationPipeline

Text classification pipeline using anyModelForSequenceClassification.

Example: Sentiment-analysis w/Xenova/distilbert-base-uncased-finetuned-sst-2-english.

const classifier =awaitpipeline('sentiment-analysis','Xenova/distilbert-base-uncased-finetuned-sst-2-english');const output =awaitclassifier('I love transformers!');// [{ label: 'POSITIVE', score: 0.999788761138916 }]

Example: Multilingual sentiment-analysis w/Xenova/bert-base-multilingual-uncased-sentiment (and return top 5 classes).

const classifier =awaitpipeline('sentiment-analysis','Xenova/bert-base-multilingual-uncased-sentiment');const output =awaitclassifier('Le meilleur film de tous les temps.', {top_k:5 });// [//   { label: '5 stars', score: 0.9610759615898132 },//   { label: '4 stars', score: 0.03323351591825485 },//   { label: '3 stars', score: 0.0036155181005597115 },//   { label: '1 star', score: 0.0011325967498123646 },//   { label: '2 stars', score: 0.0009423971059732139 }// ]

Example: Toxic comment classification w/Xenova/toxic-bert (and return all classes).

const classifier =awaitpipeline('text-classification','Xenova/toxic-bert');const output =awaitclassifier('I hate you!', {top_k:null });// [//   { label: 'toxic', score: 0.9593140482902527 },//   { label: 'insult', score: 0.16187334060668945 },//   { label: 'obscene', score: 0.03452680632472038 },//   { label: 'identity_hate', score: 0.0223250575363636 },//   { label: 'threat', score: 0.019197041168808937 },//   { label: 'severe_toxic', score: 0.005651099607348442 }// ]

Kind: static class ofpipelines

• .TextClassificationPipeline
  • new TextClassificationPipeline(options)
  • ._call() :TextClassificationPipelineCallback

new TextClassificationPipeline(options)

Create a new TextClassificationPipeline.

textClassificationPipeline._call() : <code> TextClassificationPipelineCallback </code>

Kind: instance method ofTextClassificationPipeline

pipelines.TokenClassificationPipeline

Named Entity Recognition pipeline using anyModelForTokenClassification.

Example: Perform named entity recognition withXenova/bert-base-NER.

const classifier =awaitpipeline('token-classification','Xenova/bert-base-NER');const output =awaitclassifier('My name is Sarah and I live in London');// [//   { entity: 'B-PER', score: 0.9980202913284302, index: 4, word: 'Sarah' },//   { entity: 'B-LOC', score: 0.9994474053382874, index: 9, word: 'London' }// ]

Example: Perform named entity recognition withXenova/bert-base-NER (and return all labels).

const classifier =awaitpipeline('token-classification','Xenova/bert-base-NER');const output =awaitclassifier('Sarah lives in the United States of America', {ignore_labels: [] });// [//   { entity: 'B-PER', score: 0.9966587424278259, index: 1, word: 'Sarah' },//   { entity: 'O', score: 0.9987385869026184, index: 2, word: 'lives' },//   { entity: 'O', score: 0.9990072846412659, index: 3, word: 'in' },//   { entity: 'O', score: 0.9988298416137695, index: 4, word: 'the' },//   { entity: 'B-LOC', score: 0.9995510578155518, index: 5, word: 'United' },//   { entity: 'I-LOC', score: 0.9990395307540894, index: 6, word: 'States' },//   { entity: 'I-LOC', score: 0.9986724853515625, index: 7, word: 'of' },//   { entity: 'I-LOC', score: 0.9975294470787048, index: 8, word: 'America' }// ]

Kind: static class ofpipelines

• .TokenClassificationPipeline
  • new TokenClassificationPipeline(options)
  • ._call() :TokenClassificationPipelineCallback

new TokenClassificationPipeline(options)

Create a new TokenClassificationPipeline.

tokenClassificationPipeline._call() : <code> TokenClassificationPipelineCallback </code>

Kind: instance method ofTokenClassificationPipeline

pipelines.QuestionAnsweringPipeline

Question Answering pipeline using anyModelForQuestionAnswering.

Example: Run question answering withXenova/distilbert-base-uncased-distilled-squad.

const answerer =awaitpipeline('question-answering','Xenova/distilbert-base-uncased-distilled-squad');const question ='Who was Jim Henson?';const context ='Jim Henson was a nice puppet.';const output =awaitanswerer(question, context);// {//   answer: "a nice puppet",//   score: 0.5768911502526741// }

Kind: static class ofpipelines

• .QuestionAnsweringPipeline
  • new QuestionAnsweringPipeline(options)
  • ._call() :QuestionAnsweringPipelineCallback

new QuestionAnsweringPipeline(options)

Create a new QuestionAnsweringPipeline.

questionAnsweringPipeline._call() : <code> QuestionAnsweringPipelineCallback </code>

Kind: instance method ofQuestionAnsweringPipeline

pipelines.FillMaskPipeline

Masked language modeling prediction pipeline using anyModelWithLMHead.

Example: Perform masked language modelling (a.k.a. “fill-mask”) withXenova/bert-base-uncased.

const unmasker =awaitpipeline('fill-mask','Xenova/bert-base-cased');const output =awaitunmasker('The goal of life is [MASK].');// [//   { token_str: 'survival', score: 0.06137419492006302, token: 8115, sequence: 'The goal of life is survival.' },//   { token_str: 'love', score: 0.03902450203895569, token: 1567, sequence: 'The goal of life is love.' },//   { token_str: 'happiness', score: 0.03253183513879776, token: 9266, sequence: 'The goal of life is happiness.' },//   { token_str: 'freedom', score: 0.018736306577920914, token: 4438, sequence: 'The goal of life is freedom.' },//   { token_str: 'life', score: 0.01859794743359089, token: 1297, sequence: 'The goal of life is life.' }// ]

Example: Perform masked language modelling (a.k.a. “fill-mask”) withXenova/bert-base-cased (and return top result).

const unmasker =awaitpipeline('fill-mask','Xenova/bert-base-cased');const output =awaitunmasker('The Milky Way is a [MASK] galaxy.', {top_k:1 });// [{ token_str: 'spiral', score: 0.6299987435340881, token: 14061, sequence: 'The Milky Way is a spiral galaxy.' }]

Kind: static class ofpipelines

• .FillMaskPipeline
  • new FillMaskPipeline(options)
  • ._call() :FillMaskPipelineCallback

new FillMaskPipeline(options)

Create a new FillMaskPipeline.

fillMaskPipeline._call() : <code> FillMaskPipelineCallback </code>

Kind: instance method ofFillMaskPipeline

pipelines.Text2TextGenerationPipeline

Text2TextGenerationPipeline class for generating text using a model that performs text-to-text generation tasks.

Example: Text-to-text generation w/Xenova/LaMini-Flan-T5-783M.

const generator =awaitpipeline('text2text-generation','Xenova/LaMini-Flan-T5-783M');const output =awaitgenerator('how can I become more healthy?', {max_new_tokens:100,});// [{ generated_text: "To become more healthy, you can: 1. Eat a balanced diet with plenty of fruits, vegetables, whole grains, lean proteins, and healthy fats. 2. Stay hydrated by drinking plenty of water. 3. Get enough sleep and manage stress levels. 4. Avoid smoking and excessive alcohol consumption. 5. Regularly exercise and maintain a healthy weight. 6. Practice good hygiene and sanitation. 7. Seek medical attention if you experience any health issues." }]

Kind: static class ofpipelines

• .Text2TextGenerationPipeline
  • new Text2TextGenerationPipeline(options)
  • ._key :’generated_text’
  • ._call() :Text2TextGenerationPipelineCallback

new Text2TextGenerationPipeline(options)

Create a new Text2TextGenerationPipeline.

text2TextGenerationPipeline._key : <code> ’ generated_text ’ </code>

Kind: instance property ofText2TextGenerationPipeline

text2TextGenerationPipeline._call() : <code> Text2TextGenerationPipelineCallback </code>

Kind: instance method ofText2TextGenerationPipeline

pipelines.SummarizationPipeline

A pipeline for summarization tasks, inheriting from Text2TextGenerationPipeline.

Example: Summarization w/Xenova/distilbart-cnn-6-6.

const generator =awaitpipeline('summarization','Xenova/distilbart-cnn-6-6');const text ='The tower is 324 metres (1,063 ft) tall, about the same height as an 81-storey building, ' +'and the tallest structure in Paris. Its base is square, measuring 125 metres (410 ft) on each side. ' +'During its construction, the Eiffel Tower surpassed the Washington Monument to become the tallest ' +'man-made structure in the world, a title it held for 41 years until the Chrysler Building in New ' +'York City was finished in 1930. It was the first structure to reach a height of 300 metres. Due to ' +'the addition of a broadcasting aerial at the top of the tower in 1957, it is now taller than the ' +'Chrysler Building by 5.2 metres (17 ft). Excluding transmitters, the Eiffel Tower is the second ' +'tallest free-standing structure in France after the Millau Viaduct.';const output =awaitgenerator(text, {max_new_tokens:100,});// [{ summary_text: ' The Eiffel Tower is about the same height as an 81-storey building and the tallest structure in Paris. It is the second tallest free-standing structure in France after the Millau Viaduct.' }]

Kind: static class ofpipelines

• .SummarizationPipeline
  • new SummarizationPipeline(options)
  • ._key :’summary_text’

new SummarizationPipeline(options)

Create a new SummarizationPipeline.

summarizationPipeline._key : <code> ’ summary_text ’ </code>

Kind: instance property ofSummarizationPipeline

pipelines.TranslationPipeline

Translates text from one language to another.

Example: Multilingual translation w/Xenova/nllb-200-distilled-600M.

Seeherefor the full list of languages and their corresponding codes.

const translator =awaitpipeline('translation','Xenova/nllb-200-distilled-600M');const output =awaittranslator('जीवन एक चॉकलेट बॉक्स की तरह है।', {src_lang:'hin_Deva',// Hinditgt_lang:'fra_Latn',// French});// [{ translation_text: 'La vie est comme une boîte à chocolat.' }]

Example: Multilingual translation w/Xenova/m2m100_418M.

Seeherefor the full list of languages and their corresponding codes.

const translator =awaitpipeline('translation','Xenova/m2m100_418M');const output =awaittranslator('生活就像一盒巧克力。', {src_lang:'zh',// Chinesetgt_lang:'en',// English});// [{ translation_text: 'Life is like a box of chocolate.' }]

Example: Multilingual translation w/Xenova/mbart-large-50-many-to-many-mmt.

Seeherefor the full list of languages and their corresponding codes.

const translator =awaitpipeline('translation','Xenova/mbart-large-50-many-to-many-mmt');const output =awaittranslator('संयुक्त राष्ट्र के प्रमुख का कहना है कि सीरिया में कोई सैन्य समाधान नहीं है', {src_lang:'hi_IN',// Hinditgt_lang:'fr_XX',// French});// [{ translation_text: 'Le chef des Nations affirme qu 'il n 'y a military solution in Syria.' }]

Kind: static class ofpipelines

• .TranslationPipeline
  • new TranslationPipeline(options)
  • ._key :’translation_text’

new TranslationPipeline(options)

Create a new TranslationPipeline.

translationPipeline._key : <code> ’ translation_text ’ </code>

Kind: instance property ofTranslationPipeline

pipelines.TextGenerationPipeline

Language generation pipeline using anyModelWithLMHead orModelForCausalLM.This pipeline predicts the words that will follow a specified text prompt.NOTE: For the full list of generation parameters, seeGenerationConfig.

Example: Text generation withXenova/distilgpt2 (default settings).

const generator =awaitpipeline('text-generation','Xenova/distilgpt2');const text ='I enjoy walking with my cute dog,';const output =awaitgenerator(text);// [{ generated_text: "I enjoy walking with my cute dog, and I love to play with the other dogs." }]

Example: Text generation withXenova/distilgpt2 (custom settings).

const generator =awaitpipeline('text-generation','Xenova/distilgpt2');const text ='Once upon a time, there was';const output =awaitgenerator(text, {temperature:2,max_new_tokens:10,repetition_penalty:1.5,no_repeat_ngram_size:2,num_beams:2,num_return_sequences:2,});// [{//   "generated_text": "Once upon a time, there was an abundance of information about the history and activities that"// }, {//   "generated_text": "Once upon a time, there was an abundance of information about the most important and influential"// }]

Example: Run code generation withXenova/codegen-350M-mono.

const generator =awaitpipeline('text-generation','Xenova/codegen-350M-mono');const text ='def fib(n):';const output =awaitgenerator(text, {max_new_tokens:44,});// [{//   generated_text: 'def fib(n):\n' +//     '    if n == 0:\n' +//     '        return 0\n' +//     '    elif n == 1:\n' +//     '        return 1\n' +//     '    else:\n' +//     '        return fib(n-1) + fib(n-2)\n'// }]

Kind: static class ofpipelines

• .TextGenerationPipeline
  • new TextGenerationPipeline(options)
  • ._call() :TextGenerationPipelineCallback

new TextGenerationPipeline(options)

Create a new TextGenerationPipeline.

textGenerationPipeline._call() : <code> TextGenerationPipelineCallback </code>

Kind: instance method ofTextGenerationPipeline

pipelines.ZeroShotClassificationPipeline

NLI-based zero-shot classification pipeline using aModelForSequenceClassificationtrained on NLI (natural language inference) tasks. Equivalent oftext-classificationpipelines, but these models don’t require a hardcoded number of potential classes, theycan be chosen at runtime. It usually means it’s slower but it ismuch more flexible.

Example: Zero shot classification withXenova/mobilebert-uncased-mnli.

const classifier =awaitpipeline('zero-shot-classification','Xenova/mobilebert-uncased-mnli');const text ='Last week I upgraded my iOS version and ever since then my phone has been overheating whenever I use your app.';const labels = ['mobile','billing','website','account access' ];const output =awaitclassifier(text, labels);// {//   sequence: 'Last week I upgraded my iOS version and ever since then my phone has been overheating whenever I use your app.',//   labels: [ 'mobile', 'website', 'billing', 'account access' ],//   scores: [ 0.5562091040482018, 0.1843621307860853, 0.13942646639336376, 0.12000229877234923 ]// }

Example: Zero shot classification withXenova/nli-deberta-v3-xsmall (multi-label).

const classifier =awaitpipeline('zero-shot-classification','Xenova/nli-deberta-v3-xsmall');const text ='I have a problem with my iphone that needs to be resolved asap!';const labels = ['urgent','not urgent','phone','tablet','computer' ];const output =awaitclassifier(text, labels, {multi_label:true });// {//   sequence: 'I have a problem with my iphone that needs to be resolved asap!',//   labels: [ 'urgent', 'phone', 'computer', 'tablet', 'not urgent' ],//   scores: [ 0.9958870956360275, 0.9923963400697035, 0.002333537946160235, 0.0015134138567598765, 0.0010699384208377163 ]// }

Kind: static class ofpipelines

• .ZeroShotClassificationPipeline
  • new ZeroShotClassificationPipeline(options)
  • .model :any
  • ._call() :ZeroShotClassificationPipelineCallback

new ZeroShotClassificationPipeline(options)

Create a new ZeroShotClassificationPipeline.

zeroShotClassificationPipeline.model : <code> any </code>

Kind: instance property ofZeroShotClassificationPipeline

zeroShotClassificationPipeline._call() : <code> ZeroShotClassificationPipelineCallback </code>

Kind: instance method ofZeroShotClassificationPipeline

pipelines.FeatureExtractionPipeline

Feature extraction pipeline using no model head. This pipeline extracts the hiddenstates from the base transformer, which can be used as features in downstream tasks.

Example: Run feature extraction withbert-base-uncased (without pooling/normalization).

const extractor =awaitpipeline('feature-extraction','Xenova/bert-base-uncased', {revision:'default' });const output =awaitextractor('This is a simple test.');// Tensor {//   type: 'float32',//   data: Float32Array [0.05939924716949463, 0.021655935794115067, ...],//   dims: [1, 8, 768]// }

Example: Run feature extraction withbert-base-uncased (with pooling/normalization).

const extractor =awaitpipeline('feature-extraction','Xenova/bert-base-uncased', {revision:'default' });const output =awaitextractor('This is a simple test.', {pooling:'mean',normalize:true });// Tensor {//   type: 'float32',//   data: Float32Array [0.03373778983950615, -0.010106077417731285, ...],//   dims: [1, 768]// }

Example: Calculating embeddings withsentence-transformers models.

const extractor =awaitpipeline('feature-extraction','Xenova/all-MiniLM-L6-v2');const output =awaitextractor('This is a simple test.', {pooling:'mean',normalize:true });// Tensor {//   type: 'float32',//   data: Float32Array [0.09094982594251633, -0.014774246141314507, ...],//   dims: [1, 384]// }

Example: Calculating binary embeddings withsentence-transformers models.

const extractor =awaitpipeline('feature-extraction','Xenova/all-MiniLM-L6-v2');const output =awaitextractor('This is a simple test.', {pooling:'mean',quantize:true,precision:'binary' });// Tensor {//   type: 'int8',//   data: Int8Array [49, 108, 24, ...],//   dims: [1, 48]// }

Kind: static class ofpipelines

• .FeatureExtractionPipeline
  • new FeatureExtractionPipeline(options)
  • ._call() :FeatureExtractionPipelineCallback

new FeatureExtractionPipeline(options)

Create a new FeatureExtractionPipeline.

featureExtractionPipeline._call() : <code> FeatureExtractionPipelineCallback </code>

Kind: instance method ofFeatureExtractionPipeline

pipelines.ImageFeatureExtractionPipeline

Image feature extraction pipeline using no model head. This pipeline extracts the hiddenstates from the base transformer, which can be used as features in downstream tasks.

Example: Perform image feature extraction withXenova/vit-base-patch16-224-in21k.

const image_feature_extractor =awaitpipeline('image-feature-extraction','Xenova/vit-base-patch16-224-in21k');const url ='https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/cats.png';const features =awaitimage_feature_extractor(url);// Tensor {//   dims: [ 1, 197, 768 ],//   type: 'float32',//   data: Float32Array(151296) [ ... ],//   size: 151296// }

Example: Compute image embeddings withXenova/clip-vit-base-patch32.

const image_feature_extractor =awaitpipeline('image-feature-extraction','Xenova/clip-vit-base-patch32');const url ='https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/cats.png';const features =awaitimage_feature_extractor(url);// Tensor {//   dims: [ 1, 512 ],//   type: 'float32',//   data: Float32Array(512) [ ... ],//   size: 512// }

Kind: static class ofpipelines

• .ImageFeatureExtractionPipeline
  • new ImageFeatureExtractionPipeline(options)
  • ._call() :ImageFeatureExtractionPipelineCallback

new ImageFeatureExtractionPipeline(options)

Create a new ImageFeatureExtractionPipeline.

imageFeatureExtractionPipeline._call() : <code> ImageFeatureExtractionPipelineCallback </code>

Kind: instance method ofImageFeatureExtractionPipeline

pipelines.AudioClassificationPipeline

Audio classification pipeline using anyAutoModelForAudioClassification.This pipeline predicts the class of a raw waveform or an audio file.

Example: Perform audio classification withXenova/wav2vec2-large-xlsr-53-gender-recognition-librispeech.

const classifier =awaitpipeline('audio-classification','Xenova/wav2vec2-large-xlsr-53-gender-recognition-librispeech');const url ='https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/jfk.wav';const output =awaitclassifier(url);// [//   { label: 'male', score: 0.9981542229652405 },//   { label: 'female', score: 0.001845747814513743 }// ]

Example: Perform audio classification withXenova/ast-finetuned-audioset-10-10-0.4593 and return top 4 results.

const classifier =awaitpipeline('audio-classification','Xenova/ast-finetuned-audioset-10-10-0.4593');const url ='https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/cat_meow.wav';const output =awaitclassifier(url, {top_k:4 });// [//   { label: 'Meow', score: 0.5617874264717102 },//   { label: 'Cat', score: 0.22365376353263855 },//   { label: 'Domestic animals, pets', score: 0.1141069084405899 },//   { label: 'Animal', score: 0.08985692262649536 },// ]

Kind: static class ofpipelines

• .AudioClassificationPipeline
  • new AudioClassificationPipeline(options)
  • ._call() :AudioClassificationPipelineCallback

new AudioClassificationPipeline(options)

Create a new AudioClassificationPipeline.

audioClassificationPipeline._call() : <code> AudioClassificationPipelineCallback </code>

Kind: instance method ofAudioClassificationPipeline

pipelines.ZeroShotAudioClassificationPipeline

Zero shot audio classification pipeline usingClapModel. This pipeline predicts the class of an audio when youprovide an audio and a set ofcandidate_labels.

Example: Perform zero-shot audio classification withXenova/clap-htsat-unfused.

const classifier =awaitpipeline('zero-shot-audio-classification','Xenova/clap-htsat-unfused');const audio ='https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/dog_barking.wav';const candidate_labels = ['dog','vaccum cleaner'];const scores =awaitclassifier(audio, candidate_labels);// [//   { score: 0.9993992447853088, label: 'dog' },//   { score: 0.0006007603369653225, label: 'vaccum cleaner' }// ]

Kind: static class ofpipelines

• .ZeroShotAudioClassificationPipeline
  • new ZeroShotAudioClassificationPipeline(options)
  • ._call() :ZeroShotAudioClassificationPipelineCallback

new ZeroShotAudioClassificationPipeline(options)

Create a new ZeroShotAudioClassificationPipeline.

zeroShotAudioClassificationPipeline._call() : <code> ZeroShotAudioClassificationPipelineCallback </code>

Kind: instance method ofZeroShotAudioClassificationPipeline

pipelines.AutomaticSpeechRecognitionPipeline

Pipeline that aims at extracting spoken text contained within some audio.

Example: Transcribe English.

const transcriber =awaitpipeline('automatic-speech-recognition','Xenova/whisper-tiny.en');const url ='https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/jfk.wav';const output =awaittranscriber(url);// { text: " And so my fellow Americans ask not what your country can do for you, ask what you can do for your country." }

Example: Transcribe English w/ timestamps.

const transcriber =awaitpipeline('automatic-speech-recognition','Xenova/whisper-tiny.en');const url ='https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/jfk.wav';const output =awaittranscriber(url, {return_timestamps:true });// {//   text: " And so my fellow Americans ask not what your country can do for you, ask what you can do for your country."//   chunks: [//     { timestamp: [0, 8],  text: " And so my fellow Americans ask not what your country can do for you" }//     { timestamp: [8, 11], text: " ask what you can do for your country." }//   ]// }

Example: Transcribe English w/ word-level timestamps.

const transcriber =awaitpipeline('automatic-speech-recognition','Xenova/whisper-tiny.en');const url ='https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/jfk.wav';const output =awaittranscriber(url, {return_timestamps:'word' });// {//   "text": " And so my fellow Americans ask not what your country can do for you ask what you can do for your country.",//   "chunks": [//     { "text": " And", "timestamp": [0, 0.78] },//     { "text": " so", "timestamp": [0.78, 1.06] },//     { "text": " my", "timestamp": [1.06, 1.46] },//     ...//     { "text": " for", "timestamp": [9.72, 9.92] },//     { "text": " your", "timestamp": [9.92, 10.22] },//     { "text": " country.", "timestamp": [10.22, 13.5] }//   ]// }

Example: Transcribe French.

const transcriber =awaitpipeline('automatic-speech-recognition','Xenova/whisper-small');const url ='https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/french-audio.mp3';const output =awaittranscriber(url, {language:'french',task:'transcribe' });// { text: " J'adore, j'aime, je n'aime pas, je déteste." }

Example: Translate French to English.

const transcriber =awaitpipeline('automatic-speech-recognition','Xenova/whisper-small');const url ='https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/french-audio.mp3';const output =awaittranscriber(url, {language:'french',task:'translate' });// { text: " I love, I like, I don't like, I hate." }

Example: Transcribe/translate audio longer than 30 seconds.

const transcriber =awaitpipeline('automatic-speech-recognition','Xenova/whisper-tiny.en');const url ='https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/ted_60.wav';const output =awaittranscriber(url, {chunk_length_s:30,stride_length_s:5 });// { text: " So in college, I was a government major, which means [...] So I'd start off light and I'd bump it up" }

Kind: static class ofpipelines

• .AutomaticSpeechRecognitionPipeline
  • new AutomaticSpeechRecognitionPipeline(options)
  • ._call() :AutomaticSpeechRecognitionPipelineCallback

new AutomaticSpeechRecognitionPipeline(options)

Create a new AutomaticSpeechRecognitionPipeline.

automaticSpeechRecognitionPipeline._call() : <code> AutomaticSpeechRecognitionPipelineCallback </code>

Kind: instance method ofAutomaticSpeechRecognitionPipeline

pipelines.ImageToTextPipeline

Image To Text pipeline using aAutoModelForVision2Seq. This pipeline predicts a caption for a given image.

Example: Generate a caption for an image w/Xenova/vit-gpt2-image-captioning.

const captioner =awaitpipeline('image-to-text','Xenova/vit-gpt2-image-captioning');const url ='https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/cats.jpg';const output =awaitcaptioner(url);// [{ generated_text: 'a cat laying on a couch with another cat' }]

Example: Optical Character Recognition (OCR) w/Xenova/trocr-small-handwritten.

const captioner =awaitpipeline('image-to-text','Xenova/trocr-small-handwritten');const url ='https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/handwriting.jpg';const output =awaitcaptioner(url);// [{ generated_text: 'Mr. Brown commented icily.' }]

Kind: static class ofpipelines

• .ImageToTextPipeline
  • new ImageToTextPipeline(options)
  • ._call() :ImageToTextPipelineCallback

new ImageToTextPipeline(options)

Create a new ImageToTextPipeline.

imageToTextPipeline._call() : <code> ImageToTextPipelineCallback </code>

Kind: instance method ofImageToTextPipeline

pipelines.ImageClassificationPipeline

Image classification pipeline using anyAutoModelForImageClassification.This pipeline predicts the class of an image.

Example: Classify an image.

const classifier =awaitpipeline('image-classification','Xenova/vit-base-patch16-224');const url ='https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/tiger.jpg';const output =awaitclassifier(url);// [//   { label: 'tiger, Panthera tigris', score: 0.632695734500885 },// ]

Example: Classify an image and return topn classes.

const classifier =awaitpipeline('image-classification','Xenova/vit-base-patch16-224');const url ='https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/tiger.jpg';const output =awaitclassifier(url, {top_k:3 });// [//   { label: 'tiger, Panthera tigris', score: 0.632695734500885 },//   { label: 'tiger cat', score: 0.3634825646877289 },//   { label: 'lion, king of beasts, Panthera leo', score: 0.00045060308184474707 },// ]

Example: Classify an image and return all classes.

const classifier =awaitpipeline('image-classification','Xenova/vit-base-patch16-224');const url ='https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/tiger.jpg';const output =awaitclassifier(url, {top_k:0 });// [//   { label: 'tiger, Panthera tigris', score: 0.632695734500885 },//   { label: 'tiger cat', score: 0.3634825646877289 },//   { label: 'lion, king of beasts, Panthera leo', score: 0.00045060308184474707 },//   { label: 'jaguar, panther, Panthera onca, Felis onca', score: 0.00035465499968267977 },//   ...// ]

Kind: static class ofpipelines

• .ImageClassificationPipeline
  • new ImageClassificationPipeline(options)
  • ._call() :ImageClassificationPipelineCallback

new ImageClassificationPipeline(options)

Create a new ImageClassificationPipeline.

imageClassificationPipeline._call() : <code> ImageClassificationPipelineCallback </code>

Kind: instance method ofImageClassificationPipeline

pipelines.ImageSegmentationPipeline

Image segmentation pipeline using anyAutoModelForXXXSegmentation.This pipeline predicts masks of objects and their classes.

Example: Perform image segmentation withXenova/detr-resnet-50-panoptic.

const segmenter =awaitpipeline('image-segmentation','Xenova/detr-resnet-50-panoptic');const url ='https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/cats.jpg';const output =awaitsegmenter(url);// [//   { label: 'remote', score: 0.9984649419784546, mask: RawImage { ... } },//   { label: 'cat', score: 0.9994316101074219, mask: RawImage { ... } }// ]

Kind: static class ofpipelines

• .ImageSegmentationPipeline
  • new ImageSegmentationPipeline(options)
  • ._call() :ImageSegmentationPipelineCallback

new ImageSegmentationPipeline(options)

Create a new ImageSegmentationPipeline.

imageSegmentationPipeline._call() : <code> ImageSegmentationPipelineCallback </code>

Kind: instance method ofImageSegmentationPipeline

pipelines.BackgroundRemovalPipeline

Background removal pipeline using certainAutoModelForXXXSegmentation.This pipeline removes the backgrounds of images.

Example: Perform background removal withXenova/modnet.

const segmenter =awaitpipeline('background-removal','Xenova/modnet');const url ='https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/portrait-of-woman_small.jpg';const output =awaitsegmenter(url);// [//   RawImage { data: Uint8ClampedArray(648000) [ ... ], width: 360, height: 450, channels: 4 }// ]

Kind: static class ofpipelines

• .BackgroundRemovalPipeline
  • new BackgroundRemovalPipeline(options)
  • ._call() :BackgroundRemovalPipelineCallback

new BackgroundRemovalPipeline(options)

Create a new BackgroundRemovalPipeline.

backgroundRemovalPipeline._call() : <code> BackgroundRemovalPipelineCallback </code>

Kind: instance method ofBackgroundRemovalPipeline

pipelines.ZeroShotImageClassificationPipeline

Zero shot image classification pipeline. This pipeline predicts the class ofan image when you provide an image and a set ofcandidate_labels.

Example: Zero shot image classification w/Xenova/clip-vit-base-patch32.

const classifier =awaitpipeline('zero-shot-image-classification','Xenova/clip-vit-base-patch32');const url ='https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/tiger.jpg';const output =awaitclassifier(url, ['tiger','horse','dog']);// [//   { score: 0.9993917942047119, label: 'tiger' },//   { score: 0.0003519294841680676, label: 'horse' },//   { score: 0.0002562698791734874, label: 'dog' }// ]

Kind: static class ofpipelines

• .ZeroShotImageClassificationPipeline
  • new ZeroShotImageClassificationPipeline(options)
  • ._call() :ZeroShotImageClassificationPipelineCallback

new ZeroShotImageClassificationPipeline(options)

Create a new ZeroShotImageClassificationPipeline.

zeroShotImageClassificationPipeline._call() : <code> ZeroShotImageClassificationPipelineCallback </code>

Kind: instance method ofZeroShotImageClassificationPipeline

pipelines.ObjectDetectionPipeline

Object detection pipeline using anyAutoModelForObjectDetection.This pipeline predicts bounding boxes of objects and their classes.

Example: Run object-detection withXenova/detr-resnet-50.

const detector =awaitpipeline('object-detection','Xenova/detr-resnet-50');const img ='https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/cats.jpg';const output =awaitdetector(img, {threshold:0.9 });// [{//   score: 0.9976370930671692,//   label: "remote",//   box: { xmin: 31, ymin: 68, xmax: 190, ymax: 118 }// },// ...// {//   score: 0.9984092116355896,//   label: "cat",//   box: { xmin: 331, ymin: 19, xmax: 649, ymax: 371 }// }]

Kind: static class ofpipelines

• .ObjectDetectionPipeline
  • new ObjectDetectionPipeline(options)
  • ._call() :ObjectDetectionPipelineCallback

new ObjectDetectionPipeline(options)

Create a new ObjectDetectionPipeline.

objectDetectionPipeline._call() : <code> ObjectDetectionPipelineCallback </code>

Kind: instance method ofObjectDetectionPipeline

pipelines.ZeroShotObjectDetectionPipeline

Zero-shot object detection pipeline. This pipeline predicts bounding boxes ofobjects when you provide an image and a set ofcandidate_labels.

Example: Zero-shot object detection w/Xenova/owlvit-base-patch32.

const detector =awaitpipeline('zero-shot-object-detection','Xenova/owlvit-base-patch32');const url ='https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/astronaut.png';const candidate_labels = ['human face','rocket','helmet','american flag'];const output =awaitdetector(url, candidate_labels);// [//   {//     score: 0.24392342567443848,//     label: 'human face',//     box: { xmin: 180, ymin: 67, xmax: 274, ymax: 175 }//   },//   {//     score: 0.15129457414150238,//     label: 'american flag',//     box: { xmin: 0, ymin: 4, xmax: 106, ymax: 513 }//   },//   {//     score: 0.13649864494800568,//     label: 'helmet',//     box: { xmin: 277, ymin: 337, xmax: 511, ymax: 511 }//   },//   {//     score: 0.10262022167444229,//     label: 'rocket',//     box: { xmin: 352, ymin: -1, xmax: 463, ymax: 287 }//   }// ]

Example: Zero-shot object detection w/Xenova/owlvit-base-patch32 (returning top 4 matches and setting a threshold).

const detector =awaitpipeline('zero-shot-object-detection','Xenova/owlvit-base-patch32');const url ='https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/beach.png';const candidate_labels = ['hat','book','sunglasses','camera'];const output =awaitdetector(url, candidate_labels, {top_k:4,threshold:0.05 });// [//   {//     score: 0.1606510728597641,//     label: 'sunglasses',//     box: { xmin: 347, ymin: 229, xmax: 429, ymax: 264 }//   },//   {//     score: 0.08935828506946564,//     label: 'hat',//     box: { xmin: 38, ymin: 174, xmax: 258, ymax: 364 }//   },//   {//     score: 0.08530698716640472,//     label: 'camera',//     box: { xmin: 187, ymin: 350, xmax: 260, ymax: 411 }//   },//   {//     score: 0.08349756896495819,//     label: 'book',//     box: { xmin: 261, ymin: 280, xmax: 494, ymax: 425 }//   }// ]

Kind: static class ofpipelines

• .ZeroShotObjectDetectionPipeline
  • new ZeroShotObjectDetectionPipeline(options)
  • ._call() :ZeroShotObjectDetectionPipelineCallback

new ZeroShotObjectDetectionPipeline(options)

Create a new ZeroShotObjectDetectionPipeline.

zeroShotObjectDetectionPipeline._call() : <code> ZeroShotObjectDetectionPipelineCallback </code>

Kind: instance method ofZeroShotObjectDetectionPipeline

pipelines.DocumentQuestionAnsweringPipeline

Document Question Answering pipeline using anyAutoModelForDocumentQuestionAnswering.The inputs/outputs are similar to the (extractive) question answering pipeline; however,the pipeline takes an image (and optional OCR’d words/boxes) as input instead of text context.

Example: Answer questions about a document withXenova/donut-base-finetuned-docvqa.

const qa_pipeline =awaitpipeline('document-question-answering','Xenova/donut-base-finetuned-docvqa');const image ='https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/invoice.png';const question ='What is the invoice number?';const output =awaitqa_pipeline(image, question);// [{ answer: 'us-001' }]

Kind: static class ofpipelines

• .DocumentQuestionAnsweringPipeline
  • new DocumentQuestionAnsweringPipeline(options)
  • ._call() :DocumentQuestionAnsweringPipelineCallback

new DocumentQuestionAnsweringPipeline(options)

Create a new DocumentQuestionAnsweringPipeline.

documentQuestionAnsweringPipeline._call() : <code> DocumentQuestionAnsweringPipelineCallback </code>

Kind: instance method ofDocumentQuestionAnsweringPipeline

pipelines.TextToAudioPipeline

Text-to-audio generation pipeline using anyAutoModelForTextToWaveform orAutoModelForTextToSpectrogram.This pipeline generates an audio file from an input text and optional other conditional inputs.

Example: Generate audio from text withXenova/speecht5_tts.

const synthesizer =awaitpipeline('text-to-speech','Xenova/speecht5_tts', {quantized:false });const speaker_embeddings ='https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/speaker_embeddings.bin';const out =awaitsynthesizer('Hello, my dog is cute', { speaker_embeddings });// RawAudio {//   audio: Float32Array(26112) [-0.00005657337896991521, 0.00020583874720614403, ...],//   sampling_rate: 16000// }

You can then save the audio to a .wav file with thewavefile package:

import wavefilefrom'wavefile';import fsfrom'fs';const wav =new wavefile.WaveFile();wav.fromScratch(1, out.sampling_rate,'32f', out.audio);fs.writeFileSync('out.wav', wav.toBuffer());

Example: Multilingual speech generation withXenova/mms-tts-fra. Seehere for the full list of available languages (1107).

const synthesizer =awaitpipeline('text-to-speech','Xenova/mms-tts-fra');const out =awaitsynthesizer('Bonjour');// RawAudio {//   audio: Float32Array(23808) [-0.00037693005288019776, 0.0003325853613205254, ...],//   sampling_rate: 16000// }

Kind: static class ofpipelines

• .TextToAudioPipeline
  • new TextToAudioPipeline(options)
  • ._call() :TextToAudioPipelineCallback

new TextToAudioPipeline(options)

Create a new TextToAudioPipeline.

textToAudioPipeline._call() : <code> TextToAudioPipelineCallback </code>

Kind: instance method ofTextToAudioPipeline

pipelines.ImageToImagePipeline

Image to Image pipeline using anyAutoModelForImageToImage. This pipeline generates an image based on a previous image input.

Example: Super-resolution w/Xenova/swin2SR-classical-sr-x2-64

const upscaler =awaitpipeline('image-to-image','Xenova/swin2SR-classical-sr-x2-64');const url ='https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/butterfly.jpg';const output =awaitupscaler(url);// RawImage {//   data: Uint8Array(786432) [ 41, 31, 24,  43, ... ],//   width: 512,//   height: 512,//   channels: 3// }

Kind: static class ofpipelines

• .ImageToImagePipeline
  • new ImageToImagePipeline(options)
  • ._call() :ImageToImagePipelineCallback

new ImageToImagePipeline(options)

Create a new ImageToImagePipeline.

imageToImagePipeline._call() : <code> ImageToImagePipelineCallback </code>

Kind: instance method ofImageToImagePipeline

pipelines.DepthEstimationPipeline

Depth estimation pipeline using anyAutoModelForDepthEstimation. This pipeline predicts the depth of an image.

Example: Depth estimation w/Xenova/dpt-hybrid-midas

const depth_estimator =awaitpipeline('depth-estimation','Xenova/dpt-hybrid-midas');const url ='https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/cats.jpg';const out =awaitdepth_estimator(url);// {//   predicted_depth: Tensor {//     dims: [ 384, 384 ],//     type: 'float32',//     data: Float32Array(147456) [ 542.859130859375, 545.2833862304688, 546.1649169921875, ... ],//     size: 147456//   },//   depth: RawImage {//     data: Uint8Array(307200) [ 86, 86, 86, ... ],//     width: 640,//     height: 480,//     channels: 1//   }// }

Kind: static class ofpipelines

• .DepthEstimationPipeline
  • new DepthEstimationPipeline(options)
  • ._call() :DepthEstimationPipelineCallback

new DepthEstimationPipeline(options)

Create a new DepthEstimationPipeline.

depthEstimationPipeline._call() : <code> DepthEstimationPipelineCallback </code>

Kind: instance method ofDepthEstimationPipeline

pipelines.pipeline(task, [model], [options]) ⇒ <code> * </code>

Utility factory method to build aPipeline object.

Kind: static method ofpipelines
Returns:* - A Pipeline object for the specified task.
Throws:

• Error If an unsupported pipeline is requested.

pipelines~ImagePipelineInputs : <code> string </code> | <code> RawImage </code> | <code> URL </code> | <code> Blob </code> | <code> HTMLCanvasElement </code> | <code> OffscreenCanvas </code>

Kind: inner typedef ofpipelines

pipelines~AudioPipelineInputs : <code> string </code> | <code> URL </code> | <code> Float32Array </code> | <code> Float64Array </code>

Kind: inner typedef ofpipelines

pipelines~BoundingBox : <code> Object </code>

Kind: inner typedef ofpipelines
Properties

pipelines~Disposable ⇒ <code> Promise. < void > </code>

Kind: inner typedef ofpipelines
Returns:Promise.<void> - A promise that resolves when the item has been disposed.
Properties

pipelines~TextPipelineConstructorArgs : <code> Object </code>

An object used to instantiate a text-based pipeline.

Kind: inner typedef ofpipelines
Properties

pipelines~ImagePipelineConstructorArgs : <code> Object </code>

An object used to instantiate an audio-based pipeline.

Kind: inner typedef ofpipelines
Properties

pipelines~TextImagePipelineConstructorArgs : <code> Object </code>

An object used to instantiate a text- and audio-based pipeline.

Kind: inner typedef ofpipelines
Properties

pipelines~TextClassificationPipelineType ⇒ <code> Promise. < (TextClassificationOutput|Array < TextClassificationOutput > ) > </code>

Parameters specific to text classification pipelines.

Kind: inner typedef ofpipelines
Returns:Promise.<(TextClassificationOutput|Array<TextClassificationOutput>)> - An array or object containing the predicted labels and scores.

Properties

pipelines~TokenClassificationPipelineType ⇒ <code> Promise. < (TokenClassificationOutput|Array < TokenClassificationOutput > ) > </code>

Parameters specific to token classification pipelines.

Kind: inner typedef ofpipelines
Returns:Promise.<(TokenClassificationOutput|Array<TokenClassificationOutput>)> - The result.

Properties

pipelines~QuestionAnsweringPipelineType ⇒ <code> Promise. < (QuestionAnsweringOutput|Array < QuestionAnsweringOutput > ) > </code>

Parameters specific to question answering pipelines.

Kind: inner typedef ofpipelines
Returns:Promise.<(QuestionAnsweringOutput|Array<QuestionAnsweringOutput>)> - An array or object containing the predicted answers and scores.

Properties

pipelines~FillMaskPipelineType ⇒ <code> Promise. < (FillMaskOutput|Array < FillMaskOutput > ) > </code>

Parameters specific to fill mask pipelines.

Kind: inner typedef ofpipelines
Returns:Promise.<(FillMaskOutput|Array<FillMaskOutput>)> - An array of objects containing the score, predicted token, predicted token string,and the sequence with the predicted token filled in, or an array of such arrays (one for each input text).If only one input text is given, the output will be an array of objects.
Throws:

• Error When the mask token is not found in the input text.

Properties

pipelines~Text2TextGenerationPipelineType ⇒ <code> Promise. < (Text2TextGenerationOutput|Array < Text2TextGenerationOutput > ) > </code>

Kind: inner typedef ofpipelines

Properties

pipelines~SummarizationPipelineType ⇒ <code> Promise. < (SummarizationOutput|Array < SummarizationOutput > ) > </code>

Kind: inner typedef ofpipelines

Properties

pipelines~TranslationPipelineType ⇒ <code> Promise. < (TranslationOutput|Array < TranslationOutput > ) > </code>

Kind: inner typedef ofpipelines

Properties

pipelines~TextGenerationPipelineType ⇒ <code> Promise. < (TextGenerationOutput|Array < TextGenerationOutput > ) > </code>

Parameters specific to text-generation pipelines.

Kind: inner typedef ofpipelines
Returns:Promise.<(TextGenerationOutput|Array<TextGenerationOutput>)> - An array or object containing the generated texts.

Properties

pipelines~ZeroShotClassificationPipelineType ⇒ <code> Promise. < (ZeroShotClassificationOutput|Array < ZeroShotClassificationOutput > ) > </code>

Parameters specific to zero-shot classification pipelines.

Kind: inner typedef ofpipelines
Returns:Promise.<(ZeroShotClassificationOutput|Array<ZeroShotClassificationOutput>)> - An array or object containing the predicted labels and scores.

Properties

pipelines~FeatureExtractionPipelineType ⇒ <code> Promise. < Tensor > </code>

Parameters specific to feature extraction pipelines.

Kind: inner typedef ofpipelines
Returns:Promise.<Tensor> - The features computed by the model.

Properties

pipelines~ImageFeatureExtractionPipelineType ⇒ <code> Promise. < Tensor > </code>

Parameters specific to image feature extraction pipelines.

Kind: inner typedef ofpipelines
Returns:Promise.<Tensor> - The image features computed by the model.

Properties

pipelines~AudioClassificationPipelineType ⇒ <code> Promise. < (AudioClassificationOutput|Array < AudioClassificationOutput > ) > </code>

Parameters specific to audio classification pipelines.

Kind: inner typedef ofpipelines
Returns:Promise.<(AudioClassificationOutput|Array<AudioClassificationOutput>)> - An array or object containing the predicted labels and scores.

Properties

pipelines~ZeroShotAudioClassificationPipelineType ⇒ <code> Promise. < (Array < ZeroShotAudioClassificationOutput > |Array < Array < ZeroShotAudioClassificationOutput > > ) > </code>

Parameters specific to zero-shot audio classification pipelines.

Kind: inner typedef ofpipelines
Returns:Promise.<(Array<ZeroShotAudioClassificationOutput>|Array<Array<ZeroShotAudioClassificationOutput>>)> - An array of objects containing the predicted labels and scores.

Properties

pipelines~Chunk : <code> Object </code>

Kind: inner typedef ofpipelines
Properties

pipelines~AutomaticSpeechRecognitionPipelineType ⇒ <code> Promise. < (AutomaticSpeechRecognitionOutput|Array < AutomaticSpeechRecognitionOutput > ) > </code>

Parameters specific to automatic-speech-recognition pipelines.

Kind: inner typedef ofpipelines
Returns:Promise.<(AutomaticSpeechRecognitionOutput|Array<AutomaticSpeechRecognitionOutput>)> - An object containing the transcription text and optionally timestamps ifreturn_timestamps istrue.

Properties

pipelines~ImageToTextPipelineType ⇒ <code> Promise. < (ImageToTextOutput|Array < ImageToTextOutput > ) > </code>

Kind: inner typedef ofpipelines
Returns:Promise.<(ImageToTextOutput|Array<ImageToTextOutput>)> - An object (or array of objects) containing the generated text(s).

Properties

pipelines~ImageClassificationPipelineType ⇒ <code> Promise. < (ImageClassificationOutput|Array < ImageClassificationOutput > ) > </code>

Parameters specific to image classification pipelines.

Kind: inner typedef ofpipelines
Returns:Promise.<(ImageClassificationOutput|Array<ImageClassificationOutput>)> - An array or object containing the predicted labels and scores.

Properties

pipelines~ImageSegmentationPipelineType ⇒ <code> Promise. < Array < ImageSegmentationPipelineOutput > > </code>

Parameters specific to image segmentation pipelines.

Kind: inner typedef ofpipelines
Returns:Promise.<Array<ImageSegmentationPipelineOutput>> - The annotated segments.

Properties

pipelines~BackgroundRemovalPipelineType ⇒ <code> Promise. < Array < RawImage > > </code>

Parameters specific to image segmentation pipelines.

Kind: inner typedef ofpipelines
Returns:Promise.<Array<RawImage>> - The images with the background removed.

pipelines~ZeroShotImageClassificationPipelineType ⇒ <code> Promise. < (Array < ZeroShotImageClassificationOutput > |Array < Array < ZeroShotImageClassificationOutput > > ) > </code>

Parameters specific to zero-shot image classification pipelines.

Kind: inner typedef ofpipelines
Returns:Promise.<(Array<ZeroShotImageClassificationOutput>|Array<Array<ZeroShotImageClassificationOutput>>)> - An array of objects containing the predicted labels and scores.

Properties

pipelines~ObjectDetectionPipelineType ⇒ <code> Promise. < (ObjectDetectionPipelineOutput|Array < ObjectDetectionPipelineOutput > ) > </code>

Parameters specific to object detection pipelines.

Kind: inner typedef ofpipelines
Returns:Promise.<(ObjectDetectionPipelineOutput|Array<ObjectDetectionPipelineOutput>)> - A list of objects or a list of list of objects.

Properties

pipelines~ZeroShotObjectDetectionPipelineType ⇒ <code> Promise. < (Array < ZeroShotObjectDetectionOutput > |Array < Array < ZeroShotObjectDetectionOutput > > ) > </code>

Parameters specific to zero-shot object detection pipelines.

Kind: inner typedef ofpipelines
Returns:Promise.<(Array<ZeroShotObjectDetectionOutput>|Array<Array<ZeroShotObjectDetectionOutput>>)> - An array of objects containing the predicted labels, scores, and bounding boxes.

Properties

pipelines~DocumentQuestionAnsweringPipelineType ⇒ <code> Promise. < (DocumentQuestionAnsweringOutput|Array < DocumentQuestionAnsweringOutput > ) > </code>

Kind: inner typedef ofpipelines
Returns:Promise.<(DocumentQuestionAnsweringOutput|Array<DocumentQuestionAnsweringOutput>)> - An object (or array of objects) containing the answer(s).

Properties

pipelines~TextToAudioPipelineConstructorArgs : <code> Object </code>

Kind: inner typedef ofpipelines
Properties

pipelines~TextToAudioPipelineType ⇒ <code> Promise. < TextToAudioOutput > </code>

Parameters specific to text-to-audio pipelines.

Kind: inner typedef ofpipelines
Returns:Promise.<TextToAudioOutput> - An object containing the generated audio and sampling rate.

Properties

pipelines~ImageToImagePipelineType ⇒ <code> Promise. < (RawImage|Array < RawImage > ) > </code>

Kind: inner typedef ofpipelines
Returns:Promise.<(RawImage|Array<RawImage>)> - The transformed image or list of images.

pipelines~DepthEstimationPipelineType ⇒ <code> Promise. < (DepthEstimationPipelineOutput|Array < DepthEstimationPipelineOutput > ) > </code>

Kind: inner typedef ofpipelines
Returns:Promise.<(DepthEstimationPipelineOutput|Array<DepthEstimationPipelineOutput>)> - An image or a list of images containing result(s).

Properties

pipelines~AllTasks : <code> * </code>

All possible pipeline types.

Kind: inner typedef ofpipelines