canva-copy
transformers.js
canva-copy | transformers.js | |
---|---|---|
1 | 40 | |
5 | 14,423 | |
- | 1.6% | |
9.3 | 9.2 | |
4 days ago | 8 days ago | |
HTML | JavaScript | |
- | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
canva-copy
-
A new way to remove backgrounds images
If you want to know more about the projet: Look at my GitHub canva-copy repository.
transformers.js
-
Building an AI Tokenization Demo: From Workshop to App
Hugging Face's Transformers.js library.
-
WebGPU enables local LLM in the browser. Demo site with AI chat
Very cool!
For some awesome examples of running different types of models in webgpu check out the examples folder here. https://github.com/huggingface/transformers.js
-
A new way to remove backgrounds images
Thanks a new library Hugging Face's Transformers.js it is possible now.
-
OpenAI Charges by the Minute, So Make the Minutes Shorter
I built a chrome extension with one feature that transcribes audio to text in the browser using huggingface/transformersjs running the OpenAI Whisper model with WebGPU. It works perfect! Here is a list of examples of all the things you can do in the browser with webgpu for free. [0]
The last thing in the world I want to do is listen or watch presidential social media posts, but, on the hand, sometimes enormously stupid things are said which move the SP500 up or down up $60 in a session. So this feature queries for new posts every minute, does ORC image to text and transcribe video audio to text locally, sends the post with text for analysis, all in the background inside a Chrome extension before notify me of anything economically significant.
[0] https://github.com/huggingface/transformers.js/tree/main/exa...
[1] https://github.com/adam-s/doomberg-terminal
-
How to Create a VSCode Extension That Uses a Machine Learning Model Under the Hood
By the way, you can do much more with @xenova/transformers.js in the browser. There are plenty of opportunities to experiment with in natural language processing, computer vision, audio, and more.
-
VideoSnap Vision: Real-Time Object Recognition PWA Architecture
If you're inspired to build something similar, I highly recommend diving into the documentation for Hugging Face Transformers.js and TensorFlow.js. The possibilities are incredible.
-
Embeddings Are Underrated
Another very cool attribute of embeddings and embedding search is that they are resource cheap enough that you can perform them client side.
ONNX models can be loaded and executed with transformer.js https://github.com/huggingface/transformers.js/
You can even build and statically host indices like hnsw for embeddings.
I put together a little open source demo for this here https://jasonjmcghee.github.io/portable-hnsw/
Long story short, represent indices as queryable parquet files and use duckdb to query them.
Depending on how you host, it's either free or nearly free. I used Github Pages so it's free. R2 with cloudflare would only cost the size what you store (very cheap- no egress fees).
-
Building an AI-Powered Background Remover with React and Transformers.js
Transformers.js Documentation
-
State of JavaScript 2024 Results, GitHub Copilot Now Free, EPIC Developer Tools, and more
The State of JavaScript 2024 survey results GitHub Copilot is now Free Tailwind CSS 4 JerryScript 3.0 Transformers.js v3.2 Bun 1.1.39 & 1.1.40 pnpm Update ESLint v9.17.0
- Transformers.js 3.0 Released with WebGPU Support
What are some alternatives?
web-llm - High-performance In-browser LLM Inference Engine
transformers-js - Browser-compatible JS library for running language models
onnxruntime - ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
WebGPT - Run GPT model on the browser with WebGPU. An implementation of GPT inference in less than ~1500 lines of vanilla Javascript.
pglite - Embeddable Postgres with real-time, reactive bindings.