ashutosh1919/data2vec-pytorch

Ready to run PyTorch implementation of Data2Vec 2.0: Highly efficient self-supervised representation learning for vision, speech and text.

35
/ 100
Emerging

This project helps machine learning researchers and engineers quickly set up and train self-supervised models for various data types. It takes raw image datasets like ImageNet, speech audio like LibriSpeech, or text corpora like OpenWebText as input. The output is a trained representation model ready for further downstream tasks in computer vision, speech recognition, or natural language processing.

No commits in the last 6 months.

Use this if you are a machine learning researcher or engineer looking for a ready-to-use, efficient implementation to train self-supervised representation models for images, speech, or text.

Not ideal if you are not familiar with training deep learning models or do not have access to a CUDA-enabled GPU.

self-supervised-learning computer-vision speech-recognition natural-language-processing representation-learning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

16

Forks

3

Language

Python

License

MIT

Last pushed

Mar 29, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ashutosh1919/data2vec-pytorch"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.