| Wav2Vec2 for audio classification and automatic speech recognition (ASR) | |
| Vision Transformer (ViT) and ConvNeXT for image classification | |
| DETR for object detection | |
| Mask2Former for image segmentation | |
| GLPN for depth estimation | |
| BERT for NLP tasks like text classification, token classification and question answering that use an encoder | |
| GPT2 for NLP tasks like text generation that use a decoder | |
| BART for NLP tasks like summarization and translation that use an encoder-decoder | |
| Before you go further, it is good to have some basic knowledge of the original Transformer architecture. |