xrenaa/Retriever

[ICLR2022] Code for "Retriever: Learning Content-Style Representation as a Token-Level Bipartite Graph"

21
/ 100
Experimental

This project helps researchers and developers explore the core components of various media, like speech or images, by separating 'what it is' from 'how it looks or sounds.' It takes input data (e.g., an audio clip, an image) and outputs disentangled content and style representations. Scientists and engineers working on advanced media manipulation or generation tasks would use this.

No commits in the last 6 months.

Use this if you need to perform unsupervised disentanglement of content and style from various media types, for applications like zero-shot voice conversion, co-part segmentation, or style transfer.

Not ideal if you're looking for a ready-to-use application for end-users, as this provides research code for underlying representation learning.

voice-conversion style-transfer media-synthesis unsupervised-learning computer-vision
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 5 / 25

How are scores calculated?

Stars

54

Forks

2

Language

License

Last pushed

Oct 19, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/xrenaa/Retriever"

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