transformers.js

Run advanced machine learning models directly in the browser.

CommonProductProgrammingMachine LearningTransformers

transformers.js is a JavaScript library designed to offer advanced machine learning capabilities to web applications. It allows users to run pre-trained Transformers models directly in the browser without server support. The library utilizes ONNX Runtime as the backend, supporting the conversion of PyTorch, TensorFlow, or JAX models into ONNX format. transformers.js is equivalent in functionality to the Hugging Face transformers Python library, providing similar APIs to ease the migration of existing code to the web side.

Supports various natural language processing tasks such as text classification
named entity recognition
question answering
language models
summarization
and translation.
Supports computer vision tasks including image classification
object detection
and segmentation.
Supports audio tasks such as automatic speech recognition and audio classification.

Targeted at developers who wish to integrate machine learning capabilities into web applications
particularly those who need to perform model inference on the client side to reduce server load or handle privacy-sensitive data.

Implement real-time language translation on a webpage.
Perform automatic annotation and classification of image content through the browser.
Develop a web application with support for voice-to-text conversion.

Install the transformers.js library by running 'npm install @xenova/transformers' through npm.
Import the library into your project
for example using ES modules 'import { pipeline } from '@xenova/transformers';'.
Choose or configure the required model. Use the pipeline function to specify the model ID or path.
Perform model inference using the pipeline API by传入 the text

Visit

transformers.js Visit Over Time

Monthly Visits

494758773

Bounce Rate

37.69%

Page per Visit

5.7

Visit Duration

00:06:29

transformers.js Visit Trend

transformers.js Visit Geography

transformers.js Traffic Sources

transformers.js Alternatives

AlphaQubit — AI-based decoder for quantum computing error correction

Programming•Quantum Computing•Artificial Intelligence

Aya Expanse 32B — A multilingual large language model supporting 23 languages

Productivity•multilingual•text generation

Imagenie — An AI-driven desktop application that provides stunning image transformation effects.

Image•onnx•vue3

EXAONE-3.5-7.8B-Instruct — A multilingual generation model developed by LG AI Research

Productivity•Text Generation•Transformers

EXAONE-3.5-2.4B-Instruct — A bilingual text generation model developed by LG AI Research.

Productivity•Text Generation•Transformers

Ruyi-Mini-7B — Open-source image to video generation model

Video•Image to Video•Video Generation

PromptWizard — Task-aware prompt optimization framework

Programming•Microsoft•LLM

246

EXAONE-3.5-7.8B-Instruct-GGUF — EXAONE 3.5 series 7.8B parameter bilingual generation model

Productivity•Text Generation•Transformers

Gemini 2.0 Flash Thinking — An AI model developed by Google, offering responses with enhanced reasoning capabilities.

InternationalSelection•Machine Learning•Reasoning

366

Gemini 2.0 Flash Experimental — A high-performance AI model developed by Google DeepMind

InternationalSelection•Machine Learning•Natural Language Processing

186

Astris AI — Astris AI is a division launched by Lockheed Martin that focuses on secure artificial intelligence solutions.

Others•Artificial Intelligence•Machine Learning

102

Phi Open Models — Phi Open Models are powerful, cost-effective, low-latency small language models.

Productivity•Machine Learning•Small Language Models

Recursal AI — Making artificial intelligence accessible

Productivity•Artificial Intelligence•Machine Learning

Apollo-LMMs — Exploration of Video Understanding in Large Multimodal Models

Video•Video Understanding•Multimodal Models

RWKV-6 Mixture of Experts — The largest model in the RWKV family, utilizing MoE technology to enhance efficiency.

Programming•Machine Learning•MoE

Q-RWKV-6 32B Instruct Preview — The most powerful variant of the RWKV model, breaking multiple English benchmark tests.

Programming•Machine Learning•Natural Language Processing

CosyVoice Speech Generation Model 2.0-0.5B — Efficient, multilingual speech synthesis model

Music•Speech Synthesis•Artificial Intelligence

186

Procyon AI Inference Benchmark for Android — A benchmarking tool for measuring AI performance and quality on Android devices.

Others•AI Performance•Benchmarking

InternVL2_5-4B — A multimodal large language model that integrates visual and language understanding.

Image•Multimodal•Large Language Model

Trillium TPU — The sixth-generation Tensor Processing Unit from Google, providing exceptional performance for AI workloads.

Productivity•Machine Learning•High-Performance Computing

OLMo-2-1124-7B-RM — A large language model for text generation and classification.

Productivity•Artificial Intelligence•Natural Language Processing

InternVL2_5-1B — A large multimodal language model that supports image and text understanding.

Image•Multimodal•Large Language Model

SPDL — A thread-based data loading solution that accelerates AI model training.

Productivity•Machine Learning•Data Loading

Countless.dev — AI model comparison tool, free and open-source

Productivity•AI models•comparison tool

Best AI Websites & Tools

transformers.js

transformers.js Visit Over Time

transformers.js Visit Trend

transformers.js Visit Geography

transformers.js Traffic Sources

transformers.js Alternatives

AlphaQubit — AI-based decoder for quantum computing error correction

Aya Expanse 32B — A multilingual large language model supporting 23 languages

Imagenie — An AI-driven desktop application that provides stunning image transformation effects.

EXAONE-3.5-7.8B-Instruct — A multilingual generation model developed by LG AI Research

EXAONE-3.5-2.4B-Instruct — A bilingual text generation model developed by LG AI Research.

Ruyi-Mini-7B — Open-source image to video generation model

PromptWizard — Task-aware prompt optimization framework

EXAONE-3.5-7.8B-Instruct-GGUF — EXAONE 3.5 series 7.8B parameter bilingual generation model

Gemini 2.0 Flash Thinking — An AI model developed by Google, offering responses with enhanced reasoning capabilities.

Gemini 2.0 Flash Experimental — A high-performance AI model developed by Google DeepMind

Astris AI — Astris AI is a division launched by Lockheed Martin that focuses on secure artificial intelligence solutions.

Phi Open Models — Phi Open Models are powerful, cost-effective, low-latency small language models.

Recursal AI — Making artificial intelligence accessible

Apollo-LMMs — Exploration of Video Understanding in Large Multimodal Models

RWKV-6 Mixture of Experts — The largest model in the RWKV family, utilizing MoE technology to enhance efficiency.

Q-RWKV-6 32B Instruct Preview — The most powerful variant of the RWKV model, breaking multiple English benchmark tests.

CosyVoice Speech Generation Model 2.0-0.5B — Efficient, multilingual speech synthesis model

Command R7B — Fast and Efficient Generative AI Model

CausVid — A fast causal video generator that enables instant video generation.

Phi-4 — Microsoft's latest small language model focused on complex reasoning.

tulu-3-sft-olmo-2-mixture — A large-scale multilingual text dataset.

InternVL 2.5 — Open-source multimodal large language model series

Procyon AI Inference Benchmark for Android — A benchmarking tool for measuring AI performance and quality on Android devices.

InternVL2_5-4B — A multimodal large language model that integrates visual and language understanding.

Trillium TPU — The sixth-generation Tensor Processing Unit from Google, providing exceptional performance for AI workloads.

OLMo-2-1124-7B-RM — A large language model for text generation and classification.

InternVL2_5-1B — A large multimodal language model that supports image and text understanding.

SPDL — A thread-based data loading solution that accelerates AI model training.

Countless.dev — AI model comparison tool, free and open-source