# Self-Supervised Learning

This is the ONNX format version of the facebook/dinov2-base model, suitable for computer vision tasks.

AV-HuBERT is an audio-visual speech recognition model trained on the MuAViC multilingual audio-visual corpus, combining audio and visual modalities for robust performance.

DNA sequence embedding model based on Transformer architecture, supporting sequence alignment and genomics applications

TITAN is a multimodal whole slide foundation model pre-trained through visual self-supervised learning and vision-language alignment for pathology image analysis.

A multilingual audio-visual speech recognition model based on the MuAViC dataset, combining audio and visual modalities for robust performance

DINOv2 is a vision transformer-based image feature extraction model that enhances feature extraction capabilities through the introduction of register mechanisms.

DINOv2 is a visual model released by Facebook Research that extracts general visual features through self-supervised learning, suitable for various downstream tasks.

ELECTRA is an efficient text encoder that achieves excellent performance with lower computational power through discriminative pretraining rather than generative pretraining

A wav2vec2 base model trained on 2.9K hours of French speech, supporting spontaneous, read, and broadcast speech