@huggingface/tasks 0.0.6 → 0.0.7

package/src/{text-to-image → tasks/text-to-image}/data.ts

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

package/src/{text-to-speech → tasks/text-to-speech}/about.md

@@ -25,7 +25,7 @@ def query(payload):
 	response = requests.post(API_URL, headers=headers, json=payload)
 	return response
 
-output = query({"text_inputs": "This is a test"})
+output = query({"text_inputs": "Max is the best doggo."})
 ```
 
 You can also use libraries such as [espnet](https://huggingface.co/models?library=espnet&pipeline_tag=text-to-speech&sort=downloads) or [transformers](https://huggingface.co/models?pipeline_tag=text-to-speech&library=transformers&sort=trending) if you want to handle the Inference directly.
@@ -56,6 +56,7 @@ await inference.textToSpeech({
 
 ## Useful Resources
 
+- [Hugging Face Audio Course](https://huggingface.co/learn/audio-course/chapter6/introduction)
 - [ML for Audio Study Group - Text to Speech Deep Dive](https://www.youtube.com/watch?v=aLBedWj-5CQ)
 - [An introduction to SpeechT5, a multi-purpose speech recognition and synthesis model](https://huggingface.co/blog/speecht5).
 - [A guide on Fine-tuning Whisper For Multilingual ASR with 🤗Transformers](https://huggingface.co/blog/fine-tune-whisper)

package/src/{text-to-speech → tasks/text-to-speech}/data.ts

@@ -1,4 +1,4 @@
-import type { TaskDataCustom } from "../Types";
+import type { TaskDataCustom } from "..";
 
 const taskData: TaskDataCustom = {
 	datasets: [
@@ -52,8 +52,8 @@ const taskData: TaskDataCustom = {
 			id: "suno/bark",
 		},
 		{
-			description: "An application that contains multiple speech synthesis models for various languages and accents.",
-			id: "coqui/CoquiTTS",
+			description: "XTTS is a Voice generation model that lets you clone voices into different languages.",
+			id: "coqui/xtts",
 		},
 		{
 			description: "An application that synthesizes speech for various speaker types.",
@@ -62,7 +62,7 @@ const taskData: TaskDataCustom = {
 	],
 	summary:
 		"Text-to-Speech (TTS) is the task of generating natural sounding speech given text input. TTS models can be extended to have a single model that generates speech for multiple speakers and multiple languages.",
-	widgetModels: ["microsoft/speecht5_tts"],
+	widgetModels: ["suno/bark"],
 	youtubeId: "NW62DpzJ274",
 };
 

package/src/{text-to-video → tasks/text-to-video}/data.ts

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

package/src/{token-classification → tasks/token-classification}/data.ts

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

package/src/{translation → tasks/translation}/data.ts

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

package/src/{unconditional-image-generation → tasks/unconditional-image-generation}/data.ts

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

package/src/{video-classification → tasks/video-classification}/about.md

@@ -15,34 +15,14 @@ Models trained in video classification can improve user experience by organizing
 Below you can find code for inferring with a pre-trained video classification model.
 
 ```python
-from transformers import VideoMAEFeatureExtractor, VideoMAEForVideoClassification
-from pytorchvideo.transforms import UniformTemporalSubsample
-from pytorchvideo.data.encoded_video import EncodedVideo
-
-
-# Load the video.
-video = EncodedVideo.from_path("path_to_video.mp4")
-video_data = video.get_clip(start_sec=0, end_sec=4.0)["video"]
-
-# Sub-sample a fixed set of frames and convert them to a NumPy array.
-num_frames = 16
-subsampler = UniformTemporalSubsample(num_frames)
-subsampled_frames = subsampler(video_data)
-video_data_np = subsampled_frames.numpy().transpose(1, 2, 3, 0)
-
-# Preprocess the video frames.
-inputs = feature_extractor(list(video_data_np), return_tensors="pt")
-
-# Run inference
-with torch.no_grad():
-    outputs = model(**inputs)
-    logits = outputs.logits
-
-# Model predicts one of the 400 Kinetics 400 classes
-predicted_label = logits.argmax(-1).item()
-print(model.config.id2label[predicted_label])
-# `eating spaghetti` (if you chose this video:
-# https://hf.co/datasets/nielsr/video-demo/resolve/main/eating_spaghetti.mp4)
+from transformers import pipeline
+
+pipe = pipeline(task = "video-classification", model="nateraw/videomae-base-finetuned-ucf101-subset")
+pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/basketball.avi?download=true")
+
+#[{'score': 0.90, 'label': 'BasketballDunk'},
+# {'score': 0.02, 'label': 'BalanceBeam'},
+# ... ]
 ```
 
 ## Useful Resources

package/src/{video-classification → tasks/video-classification}/data.ts

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

package/src/{visual-question-answering → tasks/visual-question-answering}/data.ts

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

package/src/{zero-shot-classification → tasks/zero-shot-classification}/data.ts

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

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

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

package/src/Types.ts

@@ -1,64 +0,0 @@
-import type { ModelLibraryKey } from "./modelLibraries";
-import type { PipelineType } from "./pipelines";
-
-export interface ExampleRepo {
-	description: string;
-	id: string;
-}
-
-export type TaskDemoEntry =
-	| {
-			filename: string;
-			type: "audio";
-	  }
-	| {
-			data: Array<{
-				label: string;
-				score: number;
-			}>;
-			type: "chart";
-	  }
-	| {
-			filename: string;
-			type: "img";
-	  }
-	| {
-			table: string[][];
-			type: "tabular";
-	  }
-	| {
-			content: string;
-			label: string;
-			type: "text";
-	  }
-	| {
-			text: string;
-			tokens: Array<{
-				end: number;
-				start: number;
-				type: string;
-			}>;
-			type: "text-with-tokens";
-	  };
-
-export interface TaskDemo {
-	inputs: TaskDemoEntry[];
-	outputs: TaskDemoEntry[];
-}
-
-export interface TaskData {
-	datasets: ExampleRepo[];
-	demo: TaskDemo;
-	id: PipelineType;
-	isPlaceholder?: boolean;
-	label: string;
-	libraries: ModelLibraryKey[];
-	metrics: ExampleRepo[];
-	models: ExampleRepo[];
-	spaces: ExampleRepo[];
-	summary: string;
-	widgetModels: string[];
-	youtubeId?: string;
-}
-
-export type TaskDataCustom = Omit<TaskData, "id" | "label" | "libraries">;

package/src/const.ts

@@ -1,59 +0,0 @@
-import type { ModelLibraryKey } from "./modelLibraries";
-import type { PipelineType } from "./pipelines";
-
-/**
- * Model libraries compatible with each ML task
- */
-export const TASKS_MODEL_LIBRARIES: Record<PipelineType, ModelLibraryKey[]> = {
-	"audio-classification": ["speechbrain", "transformers"],
-	"audio-to-audio": ["asteroid", "speechbrain"],
-	"automatic-speech-recognition": ["espnet", "nemo", "speechbrain", "transformers", "transformers.js"],
-	conversational: ["transformers"],
-	"depth-estimation": ["transformers"],
-	"document-question-answering": ["transformers"],
-	"feature-extraction": ["sentence-transformers", "transformers", "transformers.js"],
-	"fill-mask": ["transformers", "transformers.js"],
-	"graph-ml": ["transformers"],
-	"image-classification": ["keras", "timm", "transformers", "transformers.js"],
-	"image-segmentation": ["transformers", "transformers.js"],
-	"image-to-image": [],
-	"image-to-text": ["transformers.js"],
-	"video-classification": [],
-	"multiple-choice": ["transformers"],
-	"object-detection": ["transformers", "transformers.js"],
-	other: [],
-	"question-answering": ["adapter-transformers", "allennlp", "transformers", "transformers.js"],
-	robotics: [],
-	"reinforcement-learning": ["transformers", "stable-baselines3", "ml-agents", "sample-factory"],
-	"sentence-similarity": ["sentence-transformers", "spacy", "transformers.js"],
-	summarization: ["transformers", "transformers.js"],
-	"table-question-answering": ["transformers"],
-	"table-to-text": ["transformers"],
-	"tabular-classification": ["sklearn"],
-	"tabular-regression": ["sklearn"],
-	"tabular-to-text": ["transformers"],
-	"text-classification": ["adapter-transformers", "spacy", "transformers", "transformers.js"],
-	"text-generation": ["transformers", "transformers.js"],
-	"text-retrieval": [],
-	"text-to-image": [],
-	"text-to-speech": ["espnet", "tensorflowtts", "transformers"],
-	"text-to-audio": ["transformers"],
-	"text-to-video": [],
-	"text2text-generation": ["transformers", "transformers.js"],
-	"time-series-forecasting": [],
-	"token-classification": [
-		"adapter-transformers",
-		"flair",
-		"spacy",
-		"span-marker",
-		"stanza",
-		"transformers",
-		"transformers.js",
-	],
-	translation: ["transformers", "transformers.js"],
-	"unconditional-image-generation": [],
-	"visual-question-answering": [],
-	"voice-activity-detection": [],
-	"zero-shot-classification": ["transformers", "transformers.js"],
-	"zero-shot-image-classification": ["transformers.js"],
-};