@huggingface/tasks 0.13.1 → 0.13.3

package/src/tasks/audio-to-audio/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	datasets: [

package/src/tasks/automatic-speech-recognition/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	datasets: [
@@ -6,12 +6,16 @@ const taskData: TaskDataCustom = {
 			description: "31,175 hours of multilingual audio-text dataset in 108 languages.",
 			id: "mozilla-foundation/common_voice_17_0",
 		},
+		{
+			description: "Multilingual and diverse audio dataset with 101k hours of audio.",
+			id: "amphion/Emilia-Dataset",
+		},
 		{
 			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.",
+			description: "A multilingual audio dataset with 370K hours of audio.",
 			id: "espnet/yodas",
 		},
 	],
@@ -54,6 +58,10 @@ const taskData: TaskDataCustom = {
 			description: "An end-to-end model that performs ASR and Speech Translation by MetaAI.",
 			id: "facebook/seamless-m4t-v2-large",
 		},
+		{
+			description: "A powerful multilingual ASR and Speech Translation model by Nvidia.",
+			id: "nvidia/canary-1b",
+		},
 		{
 			description: "Powerful speaker diarization model.",
 			id: "pyannote/speaker-diarization-3.1",
@@ -65,13 +73,17 @@ const taskData: TaskDataCustom = {
 			id: "hf-audio/whisper-large-v3",
 		},
 		{
-			description: "Fastest speech recognition application.",
-			id: "sanchit-gandhi/whisper-jax",
+			description: "Latest ASR model from Useful Sensors.",
+			id: "mrfakename/Moonshinex",
 		},
 		{
 			description: "A high quality speech and text translation model by Meta.",
 			id: "facebook/seamless_m4t",
 		},
+		{
+			description: "A powerful multilingual ASR and Speech Translation model by Nvidia",
+			id: "nvidia/canary-1b",
+		},
 	],
 	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.",

package/src/tasks/depth-estimation/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	datasets: [

package/src/tasks/document-question-answering/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	datasets: [

package/src/tasks/feature-extraction/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	datasets: [

package/src/tasks/fill-mask/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	datasets: [

package/src/tasks/image-classification/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	datasets: [

package/src/tasks/image-feature-extraction/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	datasets: [

package/src/tasks/image-segmentation/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	datasets: [

package/src/tasks/image-text-to-text/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	datasets: [

package/src/tasks/image-to-3d/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	datasets: [

package/src/tasks/image-to-image/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	datasets: [

package/src/tasks/image-to-text/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	datasets: [

package/src/tasks/index.ts

@@ -1,49 +1,49 @@
-import type { PipelineType } from "../pipelines";
-import { PIPELINE_DATA } from "../pipelines";
+import type { PipelineType } from "../pipelines.js";
+import { PIPELINE_DATA } from "../pipelines.js";
 
-import audioClassification from "./audio-classification/data";
-import audioToAudio from "./audio-to-audio/data";
-import automaticSpeechRecognition from "./automatic-speech-recognition/data";
-import documentQuestionAnswering from "./document-question-answering/data";
-import featureExtraction from "./feature-extraction/data";
-import fillMask from "./fill-mask/data";
-import imageClassification from "./image-classification/data";
-import imageFeatureExtraction from "./image-feature-extraction/data";
-import imageToImage from "./image-to-image/data";
-import imageToText from "./image-to-text/data";
-import imageTextToText from "./image-text-to-text/data";
-import imageSegmentation from "./image-segmentation/data";
-import maskGeneration from "./mask-generation/data";
-import objectDetection from "./object-detection/data";
-import depthEstimation from "./depth-estimation/data";
-import placeholder from "./placeholder/data";
-import reinforcementLearning from "./reinforcement-learning/data";
-import questionAnswering from "./question-answering/data";
-import sentenceSimilarity from "./sentence-similarity/data";
-import summarization from "./summarization/data";
-import tableQuestionAnswering from "./table-question-answering/data";
-import tabularClassification from "./tabular-classification/data";
-import tabularRegression from "./tabular-regression/data";
-import textToImage from "./text-to-image/data";
-import textToSpeech from "./text-to-speech/data";
-import tokenClassification from "./token-classification/data";
-import translation from "./translation/data";
-import textClassification from "./text-classification/data";
-import textGeneration from "./text-generation/data";
-import textToVideo from "./text-to-video/data";
-import unconditionalImageGeneration from "./unconditional-image-generation/data";
-import videoClassification from "./video-classification/data";
-import visualQuestionAnswering from "./visual-question-answering/data";
-import zeroShotClassification from "./zero-shot-classification/data";
-import zeroShotImageClassification from "./zero-shot-image-classification/data";
-import zeroShotObjectDetection from "./zero-shot-object-detection/data";
-import imageTo3D from "./image-to-3d/data";
-import textTo3D from "./text-to-3d/data";
-import keypointDetection from "./keypoint-detection/data";
-import videoTextToText from "./video-text-to-text/data";
+import audioClassification from "./audio-classification/data.js";
+import audioToAudio from "./audio-to-audio/data.js";
+import automaticSpeechRecognition from "./automatic-speech-recognition/data.js";
+import documentQuestionAnswering from "./document-question-answering/data.js";
+import featureExtraction from "./feature-extraction/data.js";
+import fillMask from "./fill-mask/data.js";
+import imageClassification from "./image-classification/data.js";
+import imageFeatureExtraction from "./image-feature-extraction/data.js";
+import imageToImage from "./image-to-image/data.js";
+import imageToText from "./image-to-text/data.js";
+import imageTextToText from "./image-text-to-text/data.js";
+import imageSegmentation from "./image-segmentation/data.js";
+import maskGeneration from "./mask-generation/data.js";
+import objectDetection from "./object-detection/data.js";
+import depthEstimation from "./depth-estimation/data.js";
+import placeholder from "./placeholder/data.js";
+import reinforcementLearning from "./reinforcement-learning/data.js";
+import questionAnswering from "./question-answering/data.js";
+import sentenceSimilarity from "./sentence-similarity/data.js";
+import summarization from "./summarization/data.js";
+import tableQuestionAnswering from "./table-question-answering/data.js";
+import tabularClassification from "./tabular-classification/data.js";
+import tabularRegression from "./tabular-regression/data.js";
+import textToImage from "./text-to-image/data.js";
+import textToSpeech from "./text-to-speech/data.js";
+import tokenClassification from "./token-classification/data.js";
+import translation from "./translation/data.js";
+import textClassification from "./text-classification/data.js";
+import textGeneration from "./text-generation/data.js";
+import textToVideo from "./text-to-video/data.js";
+import unconditionalImageGeneration from "./unconditional-image-generation/data.js";
+import videoClassification from "./video-classification/data.js";
+import visualQuestionAnswering from "./visual-question-answering/data.js";
+import zeroShotClassification from "./zero-shot-classification/data.js";
+import zeroShotImageClassification from "./zero-shot-image-classification/data.js";
+import zeroShotObjectDetection from "./zero-shot-object-detection/data.js";
+import imageTo3D from "./image-to-3d/data.js";
+import textTo3D from "./text-to-3d/data.js";
+import keypointDetection from "./keypoint-detection/data.js";
+import videoTextToText from "./video-text-to-text/data.js";
 
-export type * from "./audio-classification/inference";
-export type * from "./automatic-speech-recognition/inference";
+export type * from "./audio-classification/inference.js";
+export type * from "./automatic-speech-recognition/inference.js";
 export type {
 	ChatCompletionInput,
 	ChatCompletionInputMessage,
@@ -53,36 +53,36 @@ export type {
 	ChatCompletionStreamOutput,
 	ChatCompletionStreamOutputChoice,
 	ChatCompletionStreamOutputDelta,
-} from "./chat-completion/inference";
-export type * from "./document-question-answering/inference";
-export type * from "./feature-extraction/inference";
-export type * from "./fill-mask/inference";
+} from "./chat-completion/inference.js";
+export type * from "./document-question-answering/inference.js";
+export type * from "./feature-extraction/inference.js";
+export type * from "./fill-mask/inference.js";
 export type {
 	ImageClassificationInput,
 	ImageClassificationOutput,
 	ImageClassificationOutputElement,
 	ImageClassificationParameters,
-} from "./image-classification/inference";
-export type * from "./image-to-image/inference";
-export type { ImageToTextInput, ImageToTextOutput, ImageToTextParameters } from "./image-to-text/inference";
-export type * from "./image-segmentation/inference";
-export type * from "./object-detection/inference";
-export type * from "./depth-estimation/inference";
-export type * from "./question-answering/inference";
-export type * from "./sentence-similarity/inference";
-export type * from "./summarization/inference";
-export type * from "./table-question-answering/inference";
-export type { TextToImageInput, TextToImageOutput, TextToImageParameters } from "./text-to-image/inference";
-export type { TextToSpeechParameters, TextToSpeechInput, TextToSpeechOutput } from "./text-to-speech/inference";
-export type * from "./token-classification/inference";
-export type { TranslationInput, TranslationOutput } from "./translation/inference";
+} from "./image-classification/inference.js";
+export type * from "./image-to-image/inference.js";
+export type { ImageToTextInput, ImageToTextOutput, ImageToTextParameters } from "./image-to-text/inference.js";
+export type * from "./image-segmentation/inference.js";
+export type * from "./object-detection/inference.js";
+export type * from "./depth-estimation/inference.js";
+export type * from "./question-answering/inference.js";
+export type * from "./sentence-similarity/inference.js";
+export type * from "./summarization/inference.js";
+export type * from "./table-question-answering/inference.js";
+export type { TextToImageInput, TextToImageOutput, TextToImageParameters } from "./text-to-image/inference.js";
+export type { TextToSpeechParameters, TextToSpeechInput, TextToSpeechOutput } from "./text-to-speech/inference.js";
+export type * from "./token-classification/inference.js";
+export type { TranslationInput, TranslationOutput } from "./translation/inference.js";
 export type {
 	ClassificationOutputTransform,
 	TextClassificationInput,
 	TextClassificationOutput,
 	TextClassificationOutputElement,
 	TextClassificationParameters,
-} from "./text-classification/inference";
+} from "./text-classification/inference.js";
 export type {
 	TextGenerationOutputFinishReason,
 	TextGenerationOutputPrefillToken,
@@ -94,20 +94,20 @@ export type {
 	TextGenerationOutputToken,
 	TextGenerationStreamOutputStreamDetails,
 	TextGenerationStreamOutput,
-} from "./text-generation/inference";
-export type * from "./video-classification/inference";
-export type * from "./visual-question-answering/inference";
-export type * from "./zero-shot-classification/inference";
-export type * from "./zero-shot-image-classification/inference";
+} from "./text-generation/inference.js";
+export type * from "./video-classification/inference.js";
+export type * from "./visual-question-answering/inference.js";
+export type * from "./zero-shot-classification/inference.js";
+export type * from "./zero-shot-image-classification/inference.js";
 export type {
 	BoundingBox,
 	ZeroShotObjectDetectionInput,
 	ZeroShotObjectDetectionInputData,
 	ZeroShotObjectDetectionOutput,
 	ZeroShotObjectDetectionOutputElement,
-} from "./zero-shot-object-detection/inference";
+} from "./zero-shot-object-detection/inference.js";
 
-import type { ModelLibraryKey } from "../model-libraries";
+import type { ModelLibraryKey } from "../model-libraries.js";
 
 /**
  * Model libraries compatible with each ML task
@@ -116,6 +116,7 @@ export const TASKS_MODEL_LIBRARIES: Record<PipelineType, ModelLibraryKey[]> = {
 	"audio-classification": ["speechbrain", "transformers", "transformers.js"],
 	"audio-to-audio": ["asteroid", "fairseq", "speechbrain"],
 	"automatic-speech-recognition": ["espnet", "nemo", "speechbrain", "transformers", "transformers.js"],
+	"audio-text-to-text": [],
 	"depth-estimation": ["transformers", "transformers.js"],
 	"document-question-answering": ["transformers", "transformers.js"],
 	"feature-extraction": ["sentence-transformers", "transformers", "transformers.js"],
@@ -197,6 +198,7 @@ export const TASKS_DATA: Record<PipelineType, TaskData | undefined> = {
 	"any-to-any": getData("any-to-any", placeholder),
 	"audio-classification": getData("audio-classification", audioClassification),
 	"audio-to-audio": getData("audio-to-audio", audioToAudio),
+	"audio-text-to-text": getData("audio-text-to-text", placeholder),
 	"automatic-speech-recognition": getData("automatic-speech-recognition", automaticSpeechRecognition),
 	"depth-estimation": getData("depth-estimation", depthEstimation),
 	"document-question-answering": getData("document-question-answering", documentQuestionAnswering),

package/src/tasks/keypoint-detection/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	datasets: [

package/src/tasks/mask-generation/about.md

@@ -12,6 +12,16 @@ Generating masks can facilitate learning, especially in semi or unsupervised lea
 
 For applications where humans are in the loop, masks highlight certain regions of images for humans to validate.
 
+### Medical Imaging
+
+Mask generation models are used in medical imaging to aid in segmenting and analyzing specific regions.
+
+### Autonomous Vehicles
+
+Mask generation models are used to create segments and masks for obstacles and other objects in view.
+
+This page was made possible thanks to the efforts of [Raj Aryan](https://huggingface.co/thatrajaryan) and other contributors.
+
 ## Task Variants
 
 ### Segmentation

package/src/tasks/mask-generation/data.ts

@@ -1,7 +1,16 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
-	datasets: [],
+	datasets: [
+		{
+			description: "Widely used benchmark dataset for multiple Vision tasks.",
+			id: "merve/coco2017",
+		},
+		{
+			description: "Medical Imaging dataset of the Human Brain for segmentation and mask generating tasks",
+			id: "rocky93/BraTS_segmentation",
+		},
+	],
 	demo: {
 		inputs: [
 			{
@@ -16,7 +25,12 @@ const taskData: TaskDataCustom = {
 			},
 		],
 	},
-	metrics: [],
+	metrics: [
+		{
+			description: "IoU is used to measure the overlap between predicted mask and the ground truth mask.",
+			id: "Intersection over Union (IoU)",
+		},
+	],
 	models: [
 		{
 			description: "Small yet powerful mask generation model.",

package/src/tasks/object-detection/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	datasets: [

package/src/tasks/placeholder/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	datasets: [],

package/src/tasks/question-answering/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	datasets: [

package/src/tasks/reinforcement-learning/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	datasets: [

package/src/tasks/sentence-similarity/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	datasets: [

package/src/tasks/summarization/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	canonicalId: "text2text-generation",

package/src/tasks/table-question-answering/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	datasets: [

package/src/tasks/tabular-classification/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	datasets: [

package/src/tasks/tabular-regression/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	datasets: [

package/src/tasks/text-classification/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	datasets: [

package/src/tasks/text-generation/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	datasets: [

package/src/tasks/text-to-3d/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	datasets: [

package/src/tasks/text-to-image/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	datasets: [

package/src/tasks/text-to-speech/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	canonicalId: "text-to-audio",

package/src/tasks/text-to-video/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	datasets: [

package/src/tasks/token-classification/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	datasets: [

package/src/tasks/translation/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	canonicalId: "text2text-generation",

package/src/tasks/unconditional-image-generation/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	datasets: [

package/src/tasks/video-classification/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	datasets: [

package/src/tasks/video-text-to-text/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	datasets: [

package/src/tasks/visual-question-answering/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	datasets: [

package/src/tasks/zero-shot-classification/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	datasets: [

package/src/tasks/zero-shot-image-classification/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	datasets: [

package/src/tasks/zero-shot-object-detection/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "..";
+import type { TaskDataCustom } from "../index.js";
 
 const taskData: TaskDataCustom = {
 	datasets: [],

package/src/widget-example.ts

@@ -2,7 +2,7 @@
  * See default-widget-inputs.ts for the default widget inputs, this files only contains the types
  */
 
-import type { ChatCompletionInputMessage } from "./tasks";
+import type { ChatCompletionInputMessage } from "./tasks/index.js";
 
 type TableData = Record<string, (string | number)[]>;
 

package/tsconfig.json

@@ -2,9 +2,9 @@
 	"compilerOptions": {
 		"allowSyntheticDefaultImports": true,
 		"lib": ["ES2022", "DOM"],
-		"module": "ESNext",
+		"module": "NodeNext",
 		"target": "ESNext",
-		"moduleResolution": "node",
+		"moduleResolution": "nodenext",
 		"forceConsistentCasingInFileNames": true,
 		"strict": true,
 		"noImplicitAny": true,
@@ -15,6 +15,6 @@
 		"declaration": true,
 		"declarationMap": true
 	},
-	"include": ["src", "scripts"],
+	"include": ["src"],
 	"exclude": ["dist"]
 }