Transformers.js

A JavaScript library that runs AI models in the browser through ONNX Runtime, with CPU execution by default and optional WebGPU acceleration.

Transformers.js is a JavaScript library for developers adding on-device AI to web apps. It runs models in the browser, so processing inputs doesn't require a separate inference server.

Text processing. Generate text, summarize documents, translate languages, classify sentiment or answer questions using supplied text.
Image analysis. Detect objects, segment images, remove backgrounds and estimate depth with compatible models.
Speech and audio. Transcribe speech, classify audio or generate speech from text.
Embeddings and documents. Compare text through embeddings, produce text from images and answer questions about document images.

Its API resembles Hugging Face's Python Transformers library, including a pipeline interface that handles input preparation and output processing. Compatible models are available through the Hugging Face Hub; supported architectures include BERT, BART and CLIP.

The library is open source under Apache 2.0. ONNX Runtime executes models on the CPU through WebAssembly by default, with optional WebGPU acceleration where the browser supports it. Quantized models can reduce download size and resource demands. Developers can also use compatible PyTorch, TensorFlow or JAX models converted to ONNX through Hugging Face Optimum.

LLM Libraries and SDKs Inference Libraries and Bindings On-Device and In-Browser AI Web Hugging Face integration Image-to-image Multilingual Multimodal input ONNX Quantization

Nobody has claimed Transformers.js yet

Work on Transformers.js? Claim this page and we'll verify you by hand. Transformers.js gets the verified checkmark, and you can upgrade the listing.

Want more people to find it? Promote it

Something wrong or outdated on this page?

Logotyper

Got an idea for an AI tool? I'm Eugene, the designer and developer behind Localhosted. I'll help you build it, from the first sketch to launch.

Start your project

Videos about Transformers.js

View all Transformers.js videos

Transformers.js 4.3: browser structured output tutorial

WebLLM

2 videos

An open-source local LLM engine that runs models in the browser with WebGPU acceleration, an OpenAI-compatible API and custom MLC models.

19.4KUpdated 4 days agoApache-2.0

Web · Browser Extension#OpenAI-compatible API#Streaming inference#Structured output

WebLLM is an engine for developers building browser-based AI assistants and Chrome extensions. It runs language models on the user's device, so applications don't need a separate inference server to process prompts.

Inference Libraries and BindingsLLM Libraries and SDKsOn-Device and In-Browser AI

ONNX Runtime

11 videos

An open source AI runtime runs ONNX models on desktop, mobile and web platforms, with CPU, GPU and NPU acceleration.

22.3KUpdated 20 hours agoMIT

macOS · Windows · Linux · iOS · Android · Web#Distributed execution#ONNX

ONNX Runtime is an AI inference and training engine for developers adding models to apps and services. It supports deployment on a user's device or a server, including applications that need the same model format across platforms.

Inference Libraries and BindingsOn-Device and In-Browser AITraining Frameworks

LiteRT

3 videos

An open-source on-device AI framework runs models on mobile, desktop and web, with CPU, GPU and NPU acceleration and offline LLM support.

3.6KUpdated 22 hours agoApache-2.0

macOS · Windows · Linux · iOS · Android · Web#Agent Skills#Hugging Face integration#Multimodal input

LiteRT is Google's framework for developers adding machine learning and generative AI to apps that run on users' devices. It succeeds TensorFlow Lite and supports local inference without a server round trip.

Edge and Embedded AIInference Libraries and BindingsLLM Libraries and SDKsOn-Device and In-Browser AIQuantization and Model Conversion

Transformers.js

A JavaScript library that runs AI models in the browser through ONNX Runtime, with CPU execution by default and optional WebGPU acceleration.