@huggingface/tasks 0.13.1 → 0.13.2

package/dist/esm/tasks/text2text-generation/inference.d.ts

@@ -0,0 +1,54 @@
+/**
+ * Inference code generated from the JSON schema spec in ./spec
+ *
+ * Using src/scripts/inference-codegen
+ */
+/**
+ * Inputs for Text2text Generation inference
+ */
+export interface Text2TextGenerationInput {
+    /**
+     * The input text data
+     */
+    inputs: string;
+    /**
+     * Additional inference parameters
+     */
+    parameters?: Text2TextGenerationParameters;
+    [property: string]: unknown;
+}
+/**
+ * Additional inference parameters
+ *
+ * Additional inference parameters for Text2text Generation
+ */
+export interface Text2TextGenerationParameters {
+    /**
+     * Whether to clean up the potential extra spaces in the text output.
+     */
+    clean_up_tokenization_spaces?: boolean;
+    /**
+     * Additional parametrization of the text generation algorithm
+     */
+    generate_parameters?: {
+        [key: string]: unknown;
+    };
+    /**
+     * The truncation strategy to use
+     */
+    truncation?: Text2TextGenerationTruncationStrategy;
+    [property: string]: unknown;
+}
+export type Text2TextGenerationTruncationStrategy = "do_not_truncate" | "longest_first" | "only_first" | "only_second";
+/**
+ * Outputs of inference for the Text2text Generation task
+ */
+export interface Text2TextGenerationOutput {
+    generatedText: unknown;
+    /**
+     * The generated text.
+     */
+    generated_text?: string;
+    [property: string]: unknown;
+}
+//# sourceMappingURL=inference.d.ts.map

package/dist/esm/tasks/text2text-generation/inference.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"inference.d.ts","sourceRoot":"","sources":["../../../../src/tasks/text2text-generation/inference.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAEH;;GAEG;AACH,MAAM,WAAW,wBAAwB;IACxC;;OAEG;IACH,MAAM,EAAE,MAAM,CAAC;IACf;;OAEG;IACH,UAAU,CAAC,EAAE,6BAA6B,CAAC;IAC3C,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AAED;;;;GAIG;AACH,MAAM,WAAW,6BAA6B;IAC7C;;OAEG;IACH,4BAA4B,CAAC,EAAE,OAAO,CAAC;IACvC;;OAEG;IACH,mBAAmB,CAAC,EAAE;QAAE,CAAC,GAAG,EAAE,MAAM,GAAG,OAAO,CAAA;KAAE,CAAC;IACjD;;OAEG;IACH,UAAU,CAAC,EAAE,qCAAqC,CAAC;IACnD,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AAED,MAAM,MAAM,qCAAqC,GAAG,iBAAiB,GAAG,eAAe,GAAG,YAAY,GAAG,aAAa,CAAC;AAEvH;;GAEG;AACH,MAAM,WAAW,yBAAyB;IACzC,aAAa,EAAE,OAAO,CAAC;IACvB;;OAEG;IACH,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B"}

package/dist/esm/tasks/text2text-generation/inference.js

@@ -0,0 +1,6 @@
+/**
+ * Inference code generated from the JSON schema spec in ./spec
+ *
+ * Using src/scripts/inference-codegen
+ */
+export {};

package/dist/esm/tasks/token-classification/data.d.ts

@@ -0,0 +1,4 @@
+import type { TaskDataCustom } from "../index.js";
+declare const taskData: TaskDataCustom;
+export default taskData;
+//# sourceMappingURL=data.d.ts.map

package/dist/esm/tasks/token-classification/data.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/token-classification/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,aAAa,CAAC;AAElD,QAAA,MAAM,QAAQ,EAAE,cAuFf,CAAC;AAEF,eAAe,QAAQ,CAAC"}

package/dist/esm/tasks/token-classification/data.js

@@ -0,0 +1,85 @@
+const taskData = {
+    datasets: [
+        {
+            description: "A widely used dataset useful to benchmark named entity recognition models.",
+            id: "eriktks/conll2003",
+        },
+        {
+            description: "A multilingual dataset of Wikipedia articles annotated for named entity recognition in over 150 different languages.",
+            id: "unimelb-nlp/wikiann",
+        },
+    ],
+    demo: {
+        inputs: [
+            {
+                label: "Input",
+                content: "My name is Omar and I live in Zürich.",
+                type: "text",
+            },
+        ],
+        outputs: [
+            {
+                text: "My name is Omar and I live in Zürich.",
+                tokens: [
+                    {
+                        type: "PERSON",
+                        start: 11,
+                        end: 15,
+                    },
+                    {
+                        type: "GPE",
+                        start: 30,
+                        end: 36,
+                    },
+                ],
+                type: "text-with-tokens",
+            },
+        ],
+    },
+    metrics: [
+        {
+            description: "",
+            id: "accuracy",
+        },
+        {
+            description: "",
+            id: "recall",
+        },
+        {
+            description: "",
+            id: "precision",
+        },
+        {
+            description: "",
+            id: "f1",
+        },
+    ],
+    models: [
+        {
+            description: "A robust performance model to identify people, locations, organizations and names of miscellaneous entities.",
+            id: "dslim/bert-base-NER",
+        },
+        {
+            description: "A strong model to identify people, locations, organizations and names in multiple languages.",
+            id: "FacebookAI/xlm-roberta-large-finetuned-conll03-english",
+        },
+        {
+            description: "A token classification model specialized on medical entity recognition.",
+            id: "blaze999/Medical-NER",
+        },
+        {
+            description: "Flair models are typically the state of the art in named entity recognition tasks.",
+            id: "flair/ner-english",
+        },
+    ],
+    spaces: [
+        {
+            description: "An application that can recognizes entities, extracts noun chunks and recognizes various linguistic features of each token.",
+            id: "spacy/gradio_pipeline_visualizer",
+        },
+    ],
+    summary: "Token classification is a natural language understanding task in which a label is assigned to some tokens in a text. Some popular token classification subtasks are Named Entity Recognition (NER) and Part-of-Speech (PoS) tagging. NER models could be trained to identify specific entities in a text, such as dates, individuals and places; and PoS tagging would identify, for example, which words in a text are verbs, nouns, and punctuation marks.",
+    widgetModels: ["FacebookAI/xlm-roberta-large-finetuned-conll03-english"],
+    youtubeId: "wVHdVlPScxA",
+};
+export default taskData;

package/dist/esm/tasks/token-classification/inference.d.ts

@@ -0,0 +1,86 @@
+/**
+ * Inference code generated from the JSON schema spec in ./spec
+ *
+ * Using src/scripts/inference-codegen
+ */
+/**
+ * Inputs for Token Classification inference
+ */
+export interface TokenClassificationInput {
+    /**
+     * The input text data
+     */
+    inputs: string;
+    /**
+     * Additional inference parameters
+     */
+    parameters?: TokenClassificationParameters;
+    [property: string]: unknown;
+}
+/**
+ * Additional inference parameters
+ *
+ * Additional inference parameters for Token Classification
+ */
+export interface TokenClassificationParameters {
+    /**
+     * The strategy used to fuse tokens based on model predictions
+     */
+    aggregation_strategy?: TokenClassificationAggregationStrategy;
+    /**
+     * A list of labels to ignore
+     */
+    ignore_labels?: string[];
+    /**
+     * The number of overlapping tokens between chunks when splitting the input text.
+     */
+    stride?: number;
+    [property: string]: unknown;
+}
+/**
+ * Do not aggregate tokens
+ *
+ * Group consecutive tokens with the same label in a single entity.
+ *
+ * Similar to "simple", also preserves word integrity (use the label predicted for the first
+ * token in a word).
+ *
+ * Similar to "simple", also preserves word integrity (uses the label with the highest
+ * score, averaged across the word's tokens).
+ *
+ * Similar to "simple", also preserves word integrity (uses the label with the highest score
+ * across the word's tokens).
+ */
+export type TokenClassificationAggregationStrategy = "none" | "simple" | "first" | "average" | "max";
+export type TokenClassificationOutput = TokenClassificationOutputElement[];
+/**
+ * Outputs of inference for the Token Classification task
+ */
+export interface TokenClassificationOutputElement {
+    /**
+     * The character position in the input where this group ends.
+     */
+    end: number;
+    /**
+     * The predicted label for a single token
+     */
+    entity?: string;
+    /**
+     * The predicted label for a group of one or more tokens
+     */
+    entity_group?: string;
+    /**
+     * The associated score / probability
+     */
+    score: number;
+    /**
+     * The character position in the input where this group begins.
+     */
+    start: number;
+    /**
+     * The corresponding text
+     */
+    word: string;
+    [property: string]: unknown;
+}
+//# sourceMappingURL=inference.d.ts.map

package/dist/esm/tasks/token-classification/inference.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"inference.d.ts","sourceRoot":"","sources":["../../../../src/tasks/token-classification/inference.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AACH;;GAEG;AACH,MAAM,WAAW,wBAAwB;IACxC;;OAEG;IACH,MAAM,EAAE,MAAM,CAAC;IACf;;OAEG;IACH,UAAU,CAAC,EAAE,6BAA6B,CAAC;IAC3C,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;;;GAIG;AACH,MAAM,WAAW,6BAA6B;IAC7C;;OAEG;IACH,oBAAoB,CAAC,EAAE,sCAAsC,CAAC;IAC9D;;OAEG;IACH,aAAa,CAAC,EAAE,MAAM,EAAE,CAAC;IACzB;;OAEG;IACH,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;;;;;;;;;;;;GAaG;AACH,MAAM,MAAM,sCAAsC,GAAG,MAAM,GAAG,QAAQ,GAAG,OAAO,GAAG,SAAS,GAAG,KAAK,CAAC;AACrG,MAAM,MAAM,yBAAyB,GAAG,gCAAgC,EAAE,CAAC;AAC3E;;GAEG;AACH,MAAM,WAAW,gCAAgC;IAChD;;OAEG;IACH,GAAG,EAAE,MAAM,CAAC;IACZ;;OAEG;IACH,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB;;OAEG;IACH,YAAY,CAAC,EAAE,MAAM,CAAC;IACtB;;OAEG;IACH,KAAK,EAAE,MAAM,CAAC;IACd;;OAEG;IACH,KAAK,EAAE,MAAM,CAAC;IACd;;OAEG;IACH,IAAI,EAAE,MAAM,CAAC;IACb,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B"}

package/dist/esm/tasks/token-classification/inference.js

@@ -0,0 +1 @@
+export {};

package/dist/esm/tasks/translation/data.d.ts

@@ -0,0 +1,4 @@
+import type { TaskDataCustom } from "../index.js";
+declare const taskData: TaskDataCustom;
+export default taskData;
+//# sourceMappingURL=data.d.ts.map

package/dist/esm/tasks/translation/data.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/translation/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,aAAa,CAAC;AAElD,QAAA,MAAM,QAAQ,EAAE,cAiEf,CAAC;AAEF,eAAe,QAAQ,CAAC"}

package/dist/esm/tasks/translation/data.js

@@ -0,0 +1,63 @@
+const taskData = {
+    canonicalId: "text2text-generation",
+    datasets: [
+        {
+            description: "A dataset of copyright-free books translated into 16 different languages.",
+            id: "Helsinki-NLP/opus_books",
+        },
+        {
+            description: "An example of translation between programming languages. This dataset consists of functions in Java and C#.",
+            id: "google/code_x_glue_cc_code_to_code_trans",
+        },
+    ],
+    demo: {
+        inputs: [
+            {
+                label: "Input",
+                content: "My name is Omar and I live in Zürich.",
+                type: "text",
+            },
+        ],
+        outputs: [
+            {
+                label: "Output",
+                content: "Mein Name ist Omar und ich wohne in Zürich.",
+                type: "text",
+            },
+        ],
+    },
+    metrics: [
+        {
+            description: "BLEU score is calculated by counting the number of shared single or subsequent tokens between the generated sequence and the reference. Subsequent n tokens are called “n-grams”. Unigram refers to a single token while bi-gram refers to token pairs and n-grams refer to n subsequent tokens. The score ranges from 0 to 1, where 1 means the translation perfectly matched and 0 did not match at all",
+            id: "bleu",
+        },
+        {
+            description: "",
+            id: "sacrebleu",
+        },
+    ],
+    models: [
+        {
+            description: "Very powerful model that can translate many languages between each other, especially low-resource languages.",
+            id: "facebook/nllb-200-1.3B",
+        },
+        {
+            description: "A general-purpose Transformer that can be used to translate from English to German, French, or Romanian.",
+            id: "google-t5/t5-base",
+        },
+    ],
+    spaces: [
+        {
+            description: "An application that can translate between 100 languages.",
+            id: "Iker/Translate-100-languages",
+        },
+        {
+            description: "An application that can translate between many languages.",
+            id: "Geonmo/nllb-translation-demo",
+        },
+    ],
+    summary: "Translation is the task of converting text from one language to another.",
+    widgetModels: ["facebook/mbart-large-50-many-to-many-mmt"],
+    youtubeId: "1JvfrvZgi6c",
+};
+export default taskData;

package/dist/esm/tasks/translation/inference.d.ts

@@ -0,0 +1,66 @@
+/**
+ * Inference code generated from the JSON schema spec in ./spec
+ *
+ * Using src/scripts/inference-codegen
+ */
+/**
+ * Inputs for Translation inference
+ */
+export interface TranslationInput {
+    /**
+     * The text to translate.
+     */
+    inputs: string;
+    /**
+     * Additional inference parameters
+     */
+    parameters?: TranslationParameters;
+    [property: string]: unknown;
+}
+/**
+ * Additional inference parameters
+ *
+ * Additional inference parameters for Translation
+ */
+export interface TranslationParameters {
+    /**
+     * Whether to clean up the potential extra spaces in the text output.
+     */
+    clean_up_tokenization_spaces?: boolean;
+    /**
+     * Additional parametrization of the text generation algorithm.
+     */
+    generate_parameters?: {
+        [key: string]: unknown;
+    };
+    /**
+     * The source language of the text. Required for models that can translate from multiple
+     * languages.
+     */
+    src_lang?: string;
+    /**
+     * Target language to translate to. Required for models that can translate to multiple
+     * languages.
+     */
+    tgt_lang?: string;
+    /**
+     * The truncation strategy to use.
+     */
+    truncation?: TranslationTruncationStrategy;
+    [property: string]: unknown;
+}
+/**
+ * The truncation strategy to use.
+ */
+export type TranslationTruncationStrategy = "do_not_truncate" | "longest_first" | "only_first" | "only_second";
+/**
+ * Outputs of inference for the Translation task
+ */
+export interface TranslationOutput {
+    /**
+     * The translated text.
+     */
+    translation_text: string;
+    [property: string]: unknown;
+}
+//# sourceMappingURL=inference.d.ts.map

package/dist/esm/tasks/translation/inference.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"inference.d.ts","sourceRoot":"","sources":["../../../../src/tasks/translation/inference.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAEH;;GAEG;AACH,MAAM,WAAW,gBAAgB;IAChC;;OAEG;IACH,MAAM,EAAE,MAAM,CAAC;IACf;;OAEG;IACH,UAAU,CAAC,EAAE,qBAAqB,CAAC;IACnC,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AAED;;;;GAIG;AACH,MAAM,WAAW,qBAAqB;IACrC;;OAEG;IACH,4BAA4B,CAAC,EAAE,OAAO,CAAC;IACvC;;OAEG;IACH,mBAAmB,CAAC,EAAE;QAAE,CAAC,GAAG,EAAE,MAAM,GAAG,OAAO,CAAA;KAAE,CAAC;IACjD;;;OAGG;IACH,QAAQ,CAAC,EAAE,MAAM,CAAC;IAClB;;;OAGG;IACH,QAAQ,CAAC,EAAE,MAAM,CAAC;IAClB;;OAEG;IACH,UAAU,CAAC,EAAE,6BAA6B,CAAC;IAC3C,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AAED;;GAEG;AACH,MAAM,MAAM,6BAA6B,GAAG,iBAAiB,GAAG,eAAe,GAAG,YAAY,GAAG,aAAa,CAAC;AAE/G;;GAEG;AACH,MAAM,WAAW,iBAAiB;IACjC;;OAEG;IACH,gBAAgB,EAAE,MAAM,CAAC;IACzB,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B"}

package/dist/esm/tasks/translation/inference.js

@@ -0,0 +1,6 @@
+/**
+ * Inference code generated from the JSON schema spec in ./spec
+ *
+ * Using src/scripts/inference-codegen
+ */
+export {};

package/dist/esm/tasks/unconditional-image-generation/data.d.ts

@@ -0,0 +1,4 @@
+import type { TaskDataCustom } from "../index.js";
+declare const taskData: TaskDataCustom;
+export default taskData;
+//# sourceMappingURL=data.d.ts.map

package/dist/esm/tasks/unconditional-image-generation/data.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/unconditional-image-generation/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,aAAa,CAAC;AAElD,QAAA,MAAM,QAAQ,EAAE,cAmEf,CAAC;AAEF,eAAe,QAAQ,CAAC"}

package/dist/esm/tasks/unconditional-image-generation/data.js

@@ -0,0 +1,63 @@
+const taskData = {
+    datasets: [
+        {
+            description: "The CIFAR-100 dataset consists of 60000 32x32 colour images in 100 classes, with 600 images per class.",
+            id: "cifar100",
+        },
+        {
+            description: "Multiple images of celebrities, used for facial expression translation.",
+            id: "CelebA",
+        },
+    ],
+    demo: {
+        inputs: [
+            {
+                label: "Seed",
+                content: "42",
+                type: "text",
+            },
+            {
+                label: "Number of images to generate:",
+                content: "4",
+                type: "text",
+            },
+        ],
+        outputs: [
+            {
+                filename: "unconditional-image-generation-output.jpeg",
+                type: "img",
+            },
+        ],
+    },
+    metrics: [
+        {
+            description: "The inception score (IS) evaluates the quality of generated images. It measures the diversity of the generated images (the model predictions are evenly distributed across all possible labels) and their 'distinction' or 'sharpness' (the model confidently predicts a single label for each image).",
+            id: "Inception score (IS)",
+        },
+        {
+            description: "The Fréchet Inception Distance (FID) evaluates the quality of images created by a generative model by calculating the distance between feature vectors for real and generated images.",
+            id: "Frećhet Inception Distance (FID)",
+        },
+    ],
+    models: [
+        {
+            description: "High-quality image generation model trained on the CIFAR-10 dataset. It synthesizes images of the ten classes presented in the dataset using diffusion probabilistic models, a class of latent variable models inspired by considerations from nonequilibrium thermodynamics.",
+            id: "google/ddpm-cifar10-32",
+        },
+        {
+            description: "High-quality image generation model trained on the 256x256 CelebA-HQ dataset. It synthesizes images of faces using diffusion probabilistic models, a class of latent variable models inspired by considerations from nonequilibrium thermodynamics.",
+            id: "google/ddpm-celebahq-256",
+        },
+    ],
+    spaces: [
+        {
+            description: "An application that can generate realistic faces.",
+            id: "CompVis/celeba-latent-diffusion",
+        },
+    ],
+    summary: "Unconditional image generation is the task of generating images with no condition in any context (like a prompt text or another image). Once trained, the model will create images that resemble its training data distribution.",
+    widgetModels: [""],
+    // TODO: Add related video
+    youtubeId: "",
+};
+export default taskData;

package/dist/esm/tasks/video-classification/data.d.ts

@@ -0,0 +1,4 @@
+import type { TaskDataCustom } from "../index.js";
+declare const taskData: TaskDataCustom;
+export default taskData;
+//# sourceMappingURL=data.d.ts.map

package/dist/esm/tasks/video-classification/data.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/video-classification/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,aAAa,CAAC;AAElD,QAAA,MAAM,QAAQ,EAAE,cA+Ef,CAAC;AAEF,eAAe,QAAQ,CAAC"}

package/dist/esm/tasks/video-classification/data.js

@@ -0,0 +1,80 @@
+const taskData = {
+    datasets: [
+        {
+            // TODO write proper description
+            description: "Benchmark dataset used for video classification with videos that belong to 400 classes.",
+            id: "kinetics400",
+        },
+    ],
+    demo: {
+        inputs: [
+            {
+                filename: "video-classification-input.gif",
+                type: "img",
+            },
+        ],
+        outputs: [
+            {
+                type: "chart",
+                data: [
+                    {
+                        label: "Playing Guitar",
+                        score: 0.514,
+                    },
+                    {
+                        label: "Playing Tennis",
+                        score: 0.193,
+                    },
+                    {
+                        label: "Cooking",
+                        score: 0.068,
+                    },
+                ],
+            },
+        ],
+    },
+    metrics: [
+        {
+            description: "",
+            id: "accuracy",
+        },
+        {
+            description: "",
+            id: "recall",
+        },
+        {
+            description: "",
+            id: "precision",
+        },
+        {
+            description: "",
+            id: "f1",
+        },
+    ],
+    models: [
+        {
+            // TO DO: write description
+            description: "Strong Video Classification model trained on the Kinetics 400 dataset.",
+            id: "google/vivit-b-16x2-kinetics400",
+        },
+        {
+            // TO DO: write description
+            description: "Strong Video Classification model trained on the Kinetics 400 dataset.",
+            id: "microsoft/xclip-base-patch32",
+        },
+    ],
+    spaces: [
+        {
+            description: "An application that classifies video at different timestamps.",
+            id: "nateraw/lavila",
+        },
+        {
+            description: "An application that classifies video.",
+            id: "fcakyon/video-classification",
+        },
+    ],
+    summary: "Video classification is the task of assigning a label or class to an entire video. Videos are expected to have only one class for each video. Video classification models take a video as input and return a prediction about which class the video belongs to.",
+    widgetModels: [],
+    youtubeId: "",
+};
+export default taskData;

package/dist/esm/tasks/video-classification/inference.d.ts

@@ -0,0 +1,60 @@
+/**
+ * Inference code generated from the JSON schema spec in ./spec
+ *
+ * Using src/scripts/inference-codegen
+ */
+/**
+ * Inputs for Video Classification inference
+ */
+export interface VideoClassificationInput {
+    /**
+     * The input video data
+     */
+    inputs: unknown;
+    /**
+     * Additional inference parameters
+     */
+    parameters?: VideoClassificationParameters;
+    [property: string]: unknown;
+}
+/**
+ * Additional inference parameters
+ *
+ * Additional inference parameters for Video Classification
+ */
+export interface VideoClassificationParameters {
+    /**
+     * The sampling rate used to select frames from the video.
+     */
+    frame_sampling_rate?: number;
+    function_to_apply?: ClassificationOutputTransform;
+    /**
+     * The number of sampled frames to consider for classification.
+     */
+    num_frames?: number;
+    /**
+     * When specified, limits the output to the top K most probable classes.
+     */
+    top_k?: number;
+    [property: string]: unknown;
+}
+/**
+ * The function to apply to the model outputs in order to retrieve the scores.
+ */
+export type ClassificationOutputTransform = "sigmoid" | "softmax" | "none";
+export type VideoClassificationOutput = VideoClassificationOutputElement[];
+/**
+ * Outputs of inference for the Video Classification task
+ */
+export interface VideoClassificationOutputElement {
+    /**
+     * The predicted class label.
+     */
+    label: string;
+    /**
+     * The corresponding probability.
+     */
+    score: number;
+    [property: string]: unknown;
+}
+//# sourceMappingURL=inference.d.ts.map

package/dist/esm/tasks/video-classification/inference.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"inference.d.ts","sourceRoot":"","sources":["../../../../src/tasks/video-classification/inference.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AACH;;GAEG;AACH,MAAM,WAAW,wBAAwB;IACxC;;OAEG;IACH,MAAM,EAAE,OAAO,CAAC;IAChB;;OAEG;IACH,UAAU,CAAC,EAAE,6BAA6B,CAAC;IAC3C,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;;;GAIG;AACH,MAAM,WAAW,6BAA6B;IAC7C;;OAEG;IACH,mBAAmB,CAAC,EAAE,MAAM,CAAC;IAC7B,iBAAiB,CAAC,EAAE,6BAA6B,CAAC;IAClD;;OAEG;IACH,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB;;OAEG;IACH,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;GAEG;AACH,MAAM,MAAM,6BAA6B,GAAG,SAAS,GAAG,SAAS,GAAG,MAAM,CAAC;AAC3E,MAAM,MAAM,yBAAyB,GAAG,gCAAgC,EAAE,CAAC;AAC3E;;GAEG;AACH,MAAM,WAAW,gCAAgC;IAChD;;OAEG;IACH,KAAK,EAAE,MAAM,CAAC;IACd;;OAEG;IACH,KAAK,EAAE,MAAM,CAAC;IACd,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B"}

package/dist/esm/tasks/video-classification/inference.js

@@ -0,0 +1 @@
+export {};

package/dist/esm/tasks/video-text-to-text/data.d.ts

@@ -0,0 +1,4 @@
+import type { TaskDataCustom } from "../index.js";
+declare const taskData: TaskDataCustom;
+export default taskData;
+//# sourceMappingURL=data.d.ts.map

package/dist/esm/tasks/video-text-to-text/data.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/video-text-to-text/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,aAAa,CAAC;AAElD,QAAA,MAAM,QAAQ,EAAE,cA6Df,CAAC;AAEF,eAAe,QAAQ,CAAC"}