@huggingface/tasks 0.13.0 → 0.13.1-test

package/dist/commonjs/tasks/automatic-speech-recognition/data.js

@@ -0,0 +1,80 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+const taskData = {
+    datasets: [
+        {
+            description: "31,175 hours of multilingual audio-text dataset in 108 languages.",
+            id: "mozilla-foundation/common_voice_17_0",
+        },
+        {
+            description: "A dataset with 44.6k hours of English speaker data and 6k hours of other language speakers.",
+            id: "parler-tts/mls_eng",
+        },
+        {
+            description: "A multi-lingual audio dataset with 370K hours of audio.",
+            id: "espnet/yodas",
+        },
+    ],
+    demo: {
+        inputs: [
+            {
+                filename: "input.flac",
+                type: "audio",
+            },
+        ],
+        outputs: [
+            {
+                /// GOING ALONG SLUSHY COUNTRY ROADS AND SPEAKING TO DAMP AUDIENCES I
+                label: "Transcript",
+                content: "Going along slushy country roads and speaking to damp audiences in...",
+                type: "text",
+            },
+        ],
+    },
+    metrics: [
+        {
+            description: "",
+            id: "wer",
+        },
+        {
+            description: "",
+            id: "cer",
+        },
+    ],
+    models: [
+        {
+            description: "A powerful ASR model by OpenAI.",
+            id: "openai/whisper-large-v3",
+        },
+        {
+            description: "A good generic speech model by MetaAI for fine-tuning.",
+            id: "facebook/w2v-bert-2.0",
+        },
+        {
+            description: "An end-to-end model that performs ASR and Speech Translation by MetaAI.",
+            id: "facebook/seamless-m4t-v2-large",
+        },
+        {
+            description: "Powerful speaker diarization model.",
+            id: "pyannote/speaker-diarization-3.1",
+        },
+    ],
+    spaces: [
+        {
+            description: "A powerful general-purpose speech recognition application.",
+            id: "hf-audio/whisper-large-v3",
+        },
+        {
+            description: "Fastest speech recognition application.",
+            id: "sanchit-gandhi/whisper-jax",
+        },
+        {
+            description: "A high quality speech and text translation model by Meta.",
+            id: "facebook/seamless_m4t",
+        },
+    ],
+    summary: "Automatic Speech Recognition (ASR), also known as Speech to Text (STT), is the task of transcribing a given audio to text. It has many applications, such as voice user interfaces.",
+    widgetModels: ["openai/whisper-large-v3"],
+    youtubeId: "TksaY_FDgnk",
+};
+exports.default = taskData;

package/dist/commonjs/tasks/automatic-speech-recognition/inference.js

@@ -0,0 +1,7 @@
+"use strict";
+/**
+ * Inference code generated from the JSON schema spec in ./spec
+ *
+ * Using src/scripts/inference-codegen
+ */
+Object.defineProperty(exports, "__esModule", { value: true });

package/dist/commonjs/tasks/chat-completion/inference.js

@@ -0,0 +1,7 @@
+"use strict";
+/**
+ * Inference code generated from the JSON schema spec in ./spec
+ *
+ * Using src/scripts/inference-codegen
+ */
+Object.defineProperty(exports, "__esModule", { value: true });

package/dist/commonjs/tasks/depth-estimation/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/commonjs/tasks/depth-estimation/data.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/depth-estimation/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/commonjs/tasks/depth-estimation/data.js

@@ -0,0 +1,69 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+const taskData = {
+    datasets: [
+        {
+            description: "NYU Depth V2 Dataset: Video dataset containing both RGB and depth sensor data.",
+            id: "sayakpaul/nyu_depth_v2",
+        },
+        {
+            description: "Monocular depth estimation benchmark based without noise and errors.",
+            id: "depth-anything/DA-2K",
+        },
+    ],
+    demo: {
+        inputs: [
+            {
+                filename: "depth-estimation-input.jpg",
+                type: "img",
+            },
+        ],
+        outputs: [
+            {
+                filename: "depth-estimation-output.png",
+                type: "img",
+            },
+        ],
+    },
+    metrics: [],
+    models: [
+        {
+            description: "Cutting-edge depth estimation model.",
+            id: "depth-anything/Depth-Anything-V2-Large",
+        },
+        {
+            description: "A strong monocular depth estimation model.",
+            id: "jingheya/lotus-depth-g-v1-0",
+        },
+        {
+            description: "A depth estimation model that predicts depth in videos.",
+            id: "tencent/DepthCrafter",
+        },
+        {
+            description: "A robust depth estimation model.",
+            id: "apple/DepthPro",
+        },
+    ],
+    spaces: [
+        {
+            description: "An application that predicts the depth of an image and then reconstruct the 3D model as voxels.",
+            id: "radames/dpt-depth-estimation-3d-voxels",
+        },
+        {
+            description: "An application for bleeding-edge depth estimation.",
+            id: "akhaliq/depth-pro",
+        },
+        {
+            description: "An application on cutting-edge depth estimation in videos.",
+            id: "tencent/DepthCrafter",
+        },
+        {
+            description: "A human-centric depth estimation application.",
+            id: "facebook/sapiens-depth",
+        },
+    ],
+    summary: "Depth estimation is the task of predicting depth of the objects present in an image.",
+    widgetModels: [""],
+    youtubeId: "",
+};
+exports.default = taskData;

package/dist/commonjs/tasks/depth-estimation/inference.js

@@ -0,0 +1,7 @@
+"use strict";
+/**
+ * Inference code generated from the JSON schema spec in ./spec
+ *
+ * Using src/scripts/inference-codegen
+ */
+Object.defineProperty(exports, "__esModule", { value: true });

package/dist/commonjs/tasks/document-question-answering/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/commonjs/tasks/document-question-answering/data.d.ts.map

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

package/dist/commonjs/tasks/document-question-answering/data.js

@@ -0,0 +1,80 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+const taskData = {
+    datasets: [
+        {
+            description: "Largest document understanding dataset.",
+            id: "HuggingFaceM4/Docmatix",
+        },
+        {
+            description: "Dataset from the 2020 DocVQA challenge. The documents are taken from the UCSF Industry Documents Library.",
+            id: "eliolio/docvqa",
+        },
+    ],
+    demo: {
+        inputs: [
+            {
+                label: "Question",
+                content: "What is the idea behind the consumer relations efficiency team?",
+                type: "text",
+            },
+            {
+                filename: "document-question-answering-input.png",
+                type: "img",
+            },
+        ],
+        outputs: [
+            {
+                label: "Answer",
+                content: "Balance cost efficiency with quality customer service",
+                type: "text",
+            },
+        ],
+    },
+    metrics: [
+        {
+            description: "The evaluation metric for the DocVQA challenge is the Average Normalized Levenshtein Similarity (ANLS). This metric is flexible to character regognition errors and compares the predicted answer with the ground truth answer.",
+            id: "anls",
+        },
+        {
+            description: "Exact Match is a metric based on the strict character match of the predicted answer and the right answer. For answers predicted correctly, the Exact Match will be 1. Even if only one character is different, Exact Match will be 0",
+            id: "exact-match",
+        },
+    ],
+    models: [
+        {
+            description: "A robust document question answering model.",
+            id: "impira/layoutlm-document-qa",
+        },
+        {
+            description: "A document question answering model specialized in invoices.",
+            id: "impira/layoutlm-invoices",
+        },
+        {
+            description: "A special model for OCR-free document question answering.",
+            id: "microsoft/udop-large",
+        },
+        {
+            description: "A powerful model for document question answering.",
+            id: "google/pix2struct-docvqa-large",
+        },
+    ],
+    spaces: [
+        {
+            description: "A robust document question answering application.",
+            id: "impira/docquery",
+        },
+        {
+            description: "An application that can answer questions from invoices.",
+            id: "impira/invoices",
+        },
+        {
+            description: "An application to compare different document question answering models.",
+            id: "merve/compare_docvqa_models",
+        },
+    ],
+    summary: "Document Question Answering (also known as Document Visual Question Answering) is the task of answering questions on document images. Document question answering models take a (document, question) pair as input and return an answer in natural language. Models usually rely on multi-modal features, combining text, position of words (bounding-boxes) and image.",
+    widgetModels: ["impira/layoutlm-invoices"],
+    youtubeId: "",
+};
+exports.default = taskData;

package/dist/commonjs/tasks/document-question-answering/inference.js

@@ -0,0 +1,2 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });

package/dist/commonjs/tasks/feature-extraction/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/commonjs/tasks/feature-extraction/data.d.ts.map

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

package/dist/commonjs/tasks/feature-extraction/data.js

@@ -0,0 +1,55 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+const taskData = {
+    datasets: [
+        {
+            description: "Wikipedia dataset containing cleaned articles of all languages. Can be used to train `feature-extraction` models.",
+            id: "wikipedia",
+        },
+    ],
+    demo: {
+        inputs: [
+            {
+                label: "Input",
+                content: "India, officially the Republic of India, is a country in South Asia.",
+                type: "text",
+            },
+        ],
+        outputs: [
+            {
+                table: [
+                    ["Dimension 1", "Dimension 2", "Dimension 3"],
+                    ["2.583383083343506", "2.757075071334839", "0.9023529887199402"],
+                    ["8.29393482208252", "1.1071064472198486", "2.03399395942688"],
+                    ["-0.7754912972450256", "-1.647324562072754", "-0.6113331913948059"],
+                    ["0.07087723910808563", "1.5942802429199219", "1.4610432386398315"],
+                ],
+                type: "tabular",
+            },
+        ],
+    },
+    metrics: [],
+    models: [
+        {
+            description: "A powerful feature extraction model for natural language processing tasks.",
+            id: "thenlper/gte-large",
+        },
+        {
+            description: "A strong feature extraction model for retrieval.",
+            id: "Alibaba-NLP/gte-Qwen1.5-7B-instruct",
+        },
+    ],
+    spaces: [
+        {
+            description: "A leaderboard to rank text feature extraction models based on a benchmark.",
+            id: "mteb/leaderboard",
+        },
+        {
+            description: "A leaderboard to rank best feature extraction models based on human feedback.",
+            id: "mteb/arena",
+        },
+    ],
+    summary: "Feature extraction is the task of extracting features learnt in a model.",
+    widgetModels: ["facebook/bart-base"],
+};
+exports.default = taskData;

package/dist/commonjs/tasks/feature-extraction/inference.js

@@ -0,0 +1,7 @@
+"use strict";
+/**
+ * Inference code generated from the JSON schema spec in ./spec
+ *
+ * Using src/scripts/inference-codegen
+ */
+Object.defineProperty(exports, "__esModule", { value: true });

package/dist/commonjs/tasks/fill-mask/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/commonjs/tasks/fill-mask/data.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/fill-mask/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,aAAa,CAAC;AAElD,QAAA,MAAM,QAAQ,EAAE,cA0Ef,CAAC;AAEF,eAAe,QAAQ,CAAC"}

package/dist/commonjs/tasks/fill-mask/data.js

@@ -0,0 +1,75 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+const taskData = {
+    datasets: [
+        {
+            description: "A common dataset that is used to train models for many languages.",
+            id: "wikipedia",
+        },
+        {
+            description: "A large English dataset with text crawled from the web.",
+            id: "c4",
+        },
+    ],
+    demo: {
+        inputs: [
+            {
+                label: "Input",
+                content: "The <mask> barked at me",
+                type: "text",
+            },
+        ],
+        outputs: [
+            {
+                type: "chart",
+                data: [
+                    {
+                        label: "wolf",
+                        score: 0.487,
+                    },
+                    {
+                        label: "dog",
+                        score: 0.061,
+                    },
+                    {
+                        label: "cat",
+                        score: 0.058,
+                    },
+                    {
+                        label: "fox",
+                        score: 0.047,
+                    },
+                    {
+                        label: "squirrel",
+                        score: 0.025,
+                    },
+                ],
+            },
+        ],
+    },
+    metrics: [
+        {
+            description: "Cross Entropy is a metric that calculates the difference between two probability distributions. Each probability distribution is the distribution of predicted words",
+            id: "cross_entropy",
+        },
+        {
+            description: "Perplexity is the exponential of the cross-entropy loss. It evaluates the probabilities assigned to the next word by the model. Lower perplexity indicates better performance",
+            id: "perplexity",
+        },
+    ],
+    models: [
+        {
+            description: "The famous BERT model.",
+            id: "google-bert/bert-base-uncased",
+        },
+        {
+            description: "A multilingual model trained on 100 languages.",
+            id: "FacebookAI/xlm-roberta-base",
+        },
+    ],
+    spaces: [],
+    summary: "Masked language modeling is the task of masking some of the words in a sentence and predicting which words should replace those masks. These models are useful when we want to get a statistical understanding of the language in which the model is trained in.",
+    widgetModels: ["distilroberta-base"],
+    youtubeId: "mqElG5QJWUg",
+};
+exports.default = taskData;

package/dist/commonjs/tasks/fill-mask/inference.js

@@ -0,0 +1,2 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });

package/dist/commonjs/tasks/image-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/commonjs/tasks/image-classification/data.d.ts.map

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

package/dist/commonjs/tasks/image-classification/data.js

@@ -0,0 +1,86 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+const taskData = {
+    datasets: [
+        {
+            // TODO write proper description
+            description: "Benchmark dataset used for image classification with images that belong to 100 classes.",
+            id: "cifar100",
+        },
+        {
+            // TODO write proper description
+            description: "Dataset consisting of images of garments.",
+            id: "fashion_mnist",
+        },
+    ],
+    demo: {
+        inputs: [
+            {
+                filename: "image-classification-input.jpeg",
+                type: "img",
+            },
+        ],
+        outputs: [
+            {
+                type: "chart",
+                data: [
+                    {
+                        label: "Egyptian cat",
+                        score: 0.514,
+                    },
+                    {
+                        label: "Tabby cat",
+                        score: 0.193,
+                    },
+                    {
+                        label: "Tiger cat",
+                        score: 0.068,
+                    },
+                ],
+            },
+        ],
+    },
+    metrics: [
+        {
+            description: "",
+            id: "accuracy",
+        },
+        {
+            description: "",
+            id: "recall",
+        },
+        {
+            description: "",
+            id: "precision",
+        },
+        {
+            description: "",
+            id: "f1",
+        },
+    ],
+    models: [
+        {
+            description: "A strong image classification model.",
+            id: "google/vit-base-patch16-224",
+        },
+        {
+            description: "A robust image classification model.",
+            id: "facebook/deit-base-distilled-patch16-224",
+        },
+        {
+            description: "A strong image classification model.",
+            id: "facebook/convnext-large-224",
+        },
+    ],
+    spaces: [
+        {
+            // TO DO: write description
+            description: "An application that classifies what a given image is about.",
+            id: "nielsr/perceiver-image-classification",
+        },
+    ],
+    summary: "Image classification is the task of assigning a label or class to an entire image. Images are expected to have only one class for each image. Image classification models take an image as input and return a prediction about which class the image belongs to.",
+    widgetModels: ["google/vit-base-patch16-224"],
+    youtubeId: "tjAIM7BOYhw",
+};
+exports.default = taskData;

package/dist/commonjs/tasks/image-classification/inference.js

@@ -0,0 +1,2 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });

package/dist/commonjs/tasks/image-feature-extraction/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/commonjs/tasks/image-feature-extraction/data.d.ts.map

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

package/dist/commonjs/tasks/image-feature-extraction/data.js

@@ -0,0 +1,57 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+const taskData = {
+    datasets: [
+        {
+            description: "ImageNet-1K is a image classification dataset in which images are used to train image-feature-extraction models.",
+            id: "imagenet-1k",
+        },
+    ],
+    demo: {
+        inputs: [
+            {
+                filename: "mask-generation-input.png",
+                type: "img",
+            },
+        ],
+        outputs: [
+            {
+                table: [
+                    ["Dimension 1", "Dimension 2", "Dimension 3"],
+                    ["0.21236686408519745", "1.0919708013534546", "0.8512550592422485"],
+                    ["0.809657871723175", "-0.18544459342956543", "-0.7851548194885254"],
+                    ["1.3103108406066895", "-0.2479034662246704", "-0.9107287526130676"],
+                    ["1.8536205291748047", "-0.36419737339019775", "0.09717650711536407"],
+                ],
+                type: "tabular",
+            },
+        ],
+    },
+    metrics: [],
+    models: [
+        {
+            description: "A powerful image feature extraction model.",
+            id: "timm/vit_large_patch14_dinov2.lvd142m",
+        },
+        {
+            description: "A strong image feature extraction model.",
+            id: "nvidia/MambaVision-T-1K",
+        },
+        {
+            description: "A robust image feature extraction model.",
+            id: "facebook/dino-vitb16",
+        },
+        {
+            description: "Strong image feature extraction model made for information retrieval from documents.",
+            id: "vidore/colpali",
+        },
+        {
+            description: "Strong image feature extraction model that can be used on images and documents.",
+            id: "OpenGVLab/InternViT-6B-448px-V1-2",
+        },
+    ],
+    spaces: [],
+    summary: "Image feature extraction is the task of extracting features learnt in a computer vision model.",
+    widgetModels: [],
+};
+exports.default = taskData;

package/dist/commonjs/tasks/image-segmentation/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/commonjs/tasks/image-segmentation/data.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/image-segmentation/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,aAAa,CAAC;AAElD,QAAA,MAAM,QAAQ,EAAE,cA8Ff,CAAC;AAEF,eAAe,QAAQ,CAAC"}