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.
1from src import multilingual_clip
2
3model = multilingual_clip.load_model('M-BERT-Base-40')
4embeddings = model(['Älgen är skogens konung!', 'Wie leben Eisbären in der Antarktis?', 'Вы знали, что все белые медведи левши?'])
5print(embeddings.shape)
6# Yields: torch.Size([3, 640])
A
BERT-base-multilingual tuned to match the embedding space for
69 languages, to the embedding space of the CLIP text encoder which accompanies the Res50x4 vision encoder.
A full list of the 100 languages used during pre-training can be found
here, and a list of the 4069languages used during fine-tuning can be found in
SupportedLanguages.md.
Training data pairs was generated by sampling 40k sentences for each language from the combined descriptions of
GCC +
MSCOCO +
VizWiz, and translating them into the corresponding language.
All translation was done using the
AWS translate service, the quality of these translations have currently not been analyzed, but one can assume the quality varies between the 69 languages.
