metadata
language: es
license: CC-BY 4.0
tags:
- spanish
- roberta
- vit
CLIP-Spanish
CLIP Spanish is a CLIP-like Model for Spanish. It is composed of a RoBERTa-base language encoder and a ViT-B/32 image encoder using Flax, including training scripts (see training.md). This is part of the Flax/Jax Community Week, organised by HuggingFace and TPU usage sponsored by Google.
Spanish WIT
We used a subset of 141,230 Spanish captions from the WIT dataset for training.
Team members
- Eduardo González Ponferrada (edugp)
- Manu Romero (mrm8488)
- María Grandury (mariagrandury)