xplip/pixel
Research code for pixel-based encoders of language (PIXEL)
PIXEL helps natural language processing engineers and researchers build AI models that understand text by looking at it as an image, rather than relying on a fixed set of words. This means you can input text in virtually any language or script your computer can display, and it will output language embeddings or reconstructed text. It's especially useful for working with languages and scripts that are less commonly found in typical AI training data.
346 stars. No commits in the last 6 months.
Use this if you need to process text in a wide variety of scripts and languages, especially those not well-represented in standard vocabulary-based language models.
Not ideal if your primary focus is on Latin-script languages like English, where traditional models like BERT might offer slightly stronger performance.
Stars
346
Forks
39
Language
Python
License
Apache-2.0
Category
Last pushed
Jul 15, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/xplip/pixel"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
huggingface/pytorch-pretrained-BigGAN
🦋A PyTorch implementation of BigGAN with pretrained weights and conversion scripts.
torchgan/torchgan
Research Framework for easy and efficient training of GANs based on Pytorch
metal3d/keras-video-generators
Keras generators to generate sequences from videos as input
GANs-in-Action/gans-in-action
Companion repository to GANs in Action: Deep learning with Generative Adversarial Networks
junyanz/pytorch-CycleGAN-and-pix2pix
Image-to-Image Translation in PyTorch