sisinflab/Ducho
Ducho is a Python framework aimed to extract multimodal features used in multimodal recommendation settings through a highly-customizable processing and extraction pipeline.
This tool helps developers and researchers working on recommendation systems to better understand items and user preferences. It takes various forms of data, such as audio, images, and text descriptions of items, along with user interaction data. It then extracts detailed features from these diverse data types, providing a richer input for building more effective recommendation algorithms.
Use this if you are a machine learning engineer or researcher looking to enhance your recommendation models by leveraging information from multiple data modalities beyond simple item IDs or ratings.
Not ideal if you are looking for a ready-to-deploy recommendation system or if you only work with single-modal data and require no complex feature extraction.
Stars
26
Forks
5
Language
Python
License
—
Category
Last pushed
Feb 20, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/sisinflab/Ducho"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
dorarad/gansformer
Generative Adversarial Transformers
j-min/VL-T5
PyTorch code for "Unifying Vision-and-Language Tasks via Text Generation" (ICML 2021)
invictus717/MetaTransformer
Meta-Transformer for Unified Multimodal Learning
rkansal47/MPGAN
The message passing GAN https://arxiv.org/abs/2106.11535 and generative adversarial particle...
Yachay-AI/byt5-geotagging
Confidence and Byt5 - based geotagging model predicting coordinates from text alone.