# Cross-modal Pretraining

ViT image encoder based on SigLIP 2, designed for timm, suitable for vision-language tasks

ViT-B-16 vision Transformer model based on SigLIP, containing only the image encoder, utilizing raw attention pooling

A SpeechT5 text-to-speech fine-tuned model optimized for Croatian, trained on Microsoft's SpeechT5 architecture and the VoxPopuli dataset

A SpeechT5 automatic speech recognition model fine-tuned on the LibriSpeech dataset, supporting speech-to-text conversion.

X-CLIP is an extended version of CLIP for general video-language understanding, trained through contrastive learning on video-text pairs, suitable for video classification and video-text retrieval tasks.

UniXcoder is a unified multimodal pretraining model that leverages multimodal data (such as code comments and abstract syntax trees) to pretrain code representations.

UniXcoder is a unified multimodal pretrained model that leverages multimodal data such as code comments and abstract syntax trees for pretraining code representations.