Skip to main content

Transformers.js

Skill Verified Active

Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image classification, object detection), audio (speech recognition, audio classification), and multimodal tasks. Works in browsers and server-side runtimes (Node.js, Bun, Deno) with WebGPU/WASM using pre-trained models from Hugging Face Hub.

Purpose

To empower developers to integrate powerful machine learning capabilities directly into their JavaScript/TypeScript applications without the need for Python-based backend infrastructure.

Features

  • Run NLP models (classification, translation, summarization)
  • Perform computer vision tasks (image classification, object detection)
  • Process audio (speech recognition, classification)
  • Support multimodal AI applications
  • Execute in browsers and server-side runtimes (Node.js, Bun, Deno)

Use Cases

  • Building client-side ML features in web applications
  • Developing serverless ML inference with Node.js
  • Creating offline-capable AI applications
  • Integrating ML models into existing JavaScript projects

Non-Goals

  • Training large-scale machine learning models
  • Replacing dedicated Python ML backends for complex training pipelines
  • Executing models that require specialized hardware not supported by WebGPU/WASM

Workflow

  1. Initialize pipeline with task, model, and optional configurations (device, dtype, etc.)
  2. Process input data through the pipeline
  3. Receive model output (e.g., generated text, classification labels, embeddings)
  4. Dispose of the pipeline to free resources

Practices

  • Model inference
  • JavaScript/TypeScript development
  • Web machine learning

Prerequisites

  • Node.js 18+ (or compatible Bun/Deno runtime) or modern browser with ES modules support
  • WebGPU requires runtime and hardware support; WASM is the broad fallback
  • Internet access for downloading models from Hugging Face Hub (optional if using local models)

Installation

/plugin install skills@huggingface-skills

Quality Score

Verified
99 /100
Analyzed about 16 hours ago

Trust Signals

Last commit2 days ago
Stars10.5k
LicenseApache-2.0
Status
View Source

Similar Extensions

Deepinit

100

Deep codebase initialization with hierarchical AGENTS.md documentation

Skill
Yeachan-Heo

Cleanup Cycles

100

Detect and untangle circular dependencies. Runs madge/skott (TS), pycycle (Py), or compiler-only checks (Go/Rust). Auto-fixes leaf-extractable cycles; reports core cycles for human review. Use when the user asks to find circular imports, fix dependency cycles, or untangle module graph. Example queries — "find circular imports", "fix dependency cycles", "untangle our module graph", "why is madge complaining".

Skill
raintree-technology

Netlify Identity

100

Use when the task involves authentication, user signups, logins, password recovery, OAuth providers, role-based access control, or protecting routes and functions. Always use `@netlify/identity`. Never use `netlify-identity-widget` or `gotrue-js` — they are deprecated.

Skill
netlify

Vue Router Best Practices

100

Vue Router 4 patterns, navigation guards, route params, and route-component lifecycle interactions.

Skill
hyf0

Sentry React Router Framework Sdk

100

Full Sentry SDK setup for React Router Framework mode. Use when asked to "add Sentry to React Router Framework", "install @sentry/react-router", or configure error monitoring, tracing, profiling, session replay, logs, or user feedback for a React Router v7 framework app.

Skill
getsentry

Transformers

98

This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.

Skill
K-Dense-AI

© 2025 SkillRepo · Find the right skill, skip the noise.