README.md

Swe-CLIP 2M

Github Model Card

Usage

To use this model along with the original CLIP vision encoder you need to download the code and additional linear weights from the Multilingual-CLIP Github. Once this is done, you can load and use the model with the following code

from src import multilingual_clip

model = multilingual_clip.load_model('Swe-CLIP-500k')
embeddings = model(['Älgen är skogens konung!', 'Alla isbjörnar är vänsterhänta'])
print(embeddings.shape)
# Yields: torch.Size([2, 640])

About

A KB/Bert-Swedish-Cased tuned to match the embedding space of the CLIP text encoder which accompanies the Res50x4 vision encoder.

Training data pairs was generated by sampling 2 Million sentences from the combined descriptions of GCC + MSCOCO + VizWiz, and translating them into Swedish. All translation was done using the Huggingface Opus Model, which seemingly procudes higher quality translations than relying on the AWS translate service.