Skip to content

Commit ff1a2d7

Browse files
authored
Added curated spaces to tasks (#589)
* added curated spaces * Added more apps!
1 parent 6381f94 commit ff1a2d7

File tree

28 files changed

+278
-28
lines changed

28 files changed

+278
-28
lines changed

tasks/src/audio-classification/data.ts

Lines changed: 6 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -58,7 +58,12 @@ const taskData: TaskDataCustom = {
5858
id: "superb/hubert-large-superb-er",
5959
},
6060
],
61-
spaces: [],
61+
spaces: [
62+
{
63+
description: "An application that can predict the language spoken in a given audio.",
64+
id: "akhaliq/Speechbrain-audio-classification",
65+
},
66+
],
6267
summary:
6368
"Audio classification is the task of assigning a label or class to a given audio. It can be used for recognizing which command a user is giving or the emotion of a statement, as well as identifying a speaker.",
6469
widgetModels: ["speechbrain/google_speech_command_xvector"],

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

Lines changed: 10 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -41,7 +41,16 @@ const taskData: TaskDataCustom = {
4141
id: "speechbrain/metricgan-plus-voicebank",
4242
},
4343
],
44-
spaces: [],
44+
spaces: [
45+
{
46+
description: "An application that can separate speech.",
47+
id: "akhaliq/speechbrain-speech-seperation",
48+
},
49+
{
50+
description: "An application that can translate from speech to speech between Hokkien and English.",
51+
id: "facebook/Hokkien_Translation",
52+
},
53+
],
4554
summary: "Audio-to-Audio is a family of tasks in which the input is an audio and the output is one or multiple generated audios. Some example tasks are speech enhancement and source separation.",
4655
widgetModels: ["speechbrain/sepformer-wham"],
4756
youtubeId: "iohj7nCCYoM",

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

Lines changed: 10 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -51,7 +51,16 @@ const taskData: TaskDataCustom = {
5151
id: "facebook/s2t-small-mustc-en-fr-st",
5252
},
5353
],
54-
spaces: [],
54+
spaces: [
55+
{
56+
description: "A powerful general-purpose speech recognition application.",
57+
id: "openai/whisper",
58+
},
59+
{
60+
description: "An application that transcribes speeches in YouTube videos.",
61+
id: "jeffistyping/Youtube-Whisperer",
62+
},
63+
],
5564
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.",
5665
widgetModels: ["facebook/wav2vec2-base-960h"],
5766
youtubeId: "TksaY_FDgnk",

tasks/src/conversational/data.ts

Lines changed: 6 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -48,7 +48,12 @@ const taskData: TaskDataCustom = {
4848
id: "microsoft/DialoGPT-large",
4949
},
5050
],
51-
spaces: [],
51+
spaces: [
52+
{
53+
description: "A chatbot based on Blender model.",
54+
id: "EXFINITE/BlenderBot-UI",
55+
},
56+
],
5257
summary: "Conversational response modelling is the task of generating conversational text that is relevant, coherent and knowledgable given a prompt. These models have applications in chatbots, and as a part of voice assistants",
5358
widgetModels: ["facebook/blenderbot-400M-distill"],
5459
youtubeId: "",

tasks/src/depth-estimation/data.ts

Lines changed: 10 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -29,7 +29,16 @@ const taskData: TaskDataCustom = {
2929
id: "vinvino02/glpn-kitti",
3030
},
3131
],
32-
spaces: [],
32+
spaces: [
33+
{
34+
description: "An application that predicts the depth of an image and then reconstruct the 3D model as voxels.",
35+
id: "radames/dpt-depth-estimation-3d-voxels",
36+
},
37+
{
38+
description: "An application that can estimate the depth in a given image.",
39+
id: "keras-io/Monocular-Depth-Estimation",
40+
},
41+
],
3342
summary: "Depth estimation is the task of predicting depth of the objects present in an image.",
3443
widgetModels: [""],
3544
youtubeId: "",

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

Lines changed: 10 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -48,7 +48,16 @@ const taskData: TaskDataCustom = {
4848
id: "naver-clova-ix/donut-base-finetuned-docvqa",
4949
},
5050
],
51-
spaces: [],
51+
spaces: [
52+
{
53+
description: "A robust document question answering application.",
54+
id: "impira/docquery",
55+
},
56+
{
57+
description: "An application that can answer questions from invoices.",
58+
id: "impira/invoices",
59+
},
60+
],
5261
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.",
5362
widgetModels: ["impira/layoutlm-document-qa"],
5463
youtubeId: "",

tasks/src/image-classification/data.ts

Lines changed: 7 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -71,7 +71,13 @@ const taskData: TaskDataCustom = {
7171
id: "facebook/deit-base-distilled-patch16-224",
7272
},
7373
],
74-
spaces: [],
74+
spaces: [
75+
{
76+
// TO DO: write description
77+
description: "An application that classifies what a given image is about.",
78+
id: "nielsr/perceiver-image-classification",
79+
},
80+
],
7581
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.",
7682
widgetModels: ["google/vit-base-patch16-224"],
7783
youtubeId: "tjAIM7BOYhw",

tasks/src/image-segmentation/data.ts

Lines changed: 10 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -50,7 +50,16 @@ const taskData: TaskDataCustom = {
5050
id: "microsoft/beit-large-finetuned-ade-640-640",
5151
},
5252
],
53-
spaces: [],
53+
spaces: [
54+
{
55+
description: "A semantic segmentation application that can predict unseen instances out of the box.",
56+
id: "facebook/ov-seg",
57+
},
58+
{
59+
description: "A semantic segmentation application that predicts human silhouettes.",
60+
id: "keras-io/Human-Part-Segmentation",
61+
},
62+
],
5463
summary: "Image Segmentation divides an image into segments where each pixel in the image is mapped to an object. This task has multiple variants such as instance segmentation, panoptic segmentation and semantic segmentation.",
5564
widgetModels: ["facebook/detr-resnet-50-panoptic"],
5665
youtubeId: "dKE8SIt9C-w",

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

Lines changed: 18 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -54,7 +54,24 @@ const taskData: TaskDataCustom = {
5454
id: "lambdalabs/sd-image-variations-diffusers",
5555
},
5656
],
57-
spaces: [],
57+
spaces: [
58+
{
59+
description: "Image enhancer application for low light.",
60+
id: "keras-io/low-light-image-enhancement",
61+
},
62+
{
63+
description: "Style transfer application.",
64+
id: "keras-io/neural-style-transfer",
65+
},
66+
{
67+
description: "An application that prettifies your drawings.",
68+
id: "huggingface-projects/diffuse-the-rest",
69+
},
70+
{
71+
description: "Image colorization application for anime drawings.",
72+
id: "Gradio-Blocks/anime-colorization",
73+
},
74+
],
5875
summary: "Image to image is the task of transforming a source image to match the characteristics of a target image or a target image domain. Any image manipulation and enhancement is possible with image to image models.",
5976
widgetModels: [""],
6077
youtubeId: "",

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

Lines changed: 14 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -49,7 +49,20 @@ const taskData: TaskDataCustom = {
4949
id: "nlpconnect/vit-gpt2-image-captioning",
5050
},
5151
],
52-
spaces: [],
52+
spaces: [
53+
{
54+
description: "A robust image captioning application.",
55+
id: "flax-community/image-captioning",
56+
},
57+
{
58+
description: "An application that transcribes handwritings into text.",
59+
id: "nielsr/TrOCR-handwritten",
60+
},
61+
{
62+
description: "An application that can caption images and answer questions about a given image.",
63+
id: "Salesforce/BLIP",
64+
},
65+
],
5366
summary: "",
5467
widgetModels: ["nlpconnect/vit-gpt2-image-captioning"],
5568
youtubeId: "",

0 commit comments

Comments
 (0)