Fix typo in README.md

README.md

@@ -45,7 +45,7 @@ This repo is the official implementation of ["Swin Transformer: Hierarchical Vis
 
 `News`: 
 
-1. SwinV2-G achieves `61.4 mIoU` on ADE20K semantic segmentation (+1.5 mIoU over the previous SwinV2-G model), using an additional [feature distillation (FD)](https://github.com/SwinTransformer/Feature-Distillation) approach, **setting a new recrod** on this benchmark. FD is an approach that can generally improve the fine-tuning performance of various pre-trained models, including DeiT, DINO, and CLIP. Particularly, it improves CLIP pre-trained ViT-L by +1.6% to reach `89.0%` on ImageNet-1K image classification, which is **the most accurate ViT-L model**.
+1. SwinV2-G achieves `61.4 mIoU` on ADE20K semantic segmentation (+1.5 mIoU over the previous SwinV2-G model), using an additional [feature distillation (FD)](https://github.com/SwinTransformer/Feature-Distillation) approach, **setting a new record** on this benchmark. FD is an approach that can generally improve the fine-tuning performance of various pre-trained models, including DeiT, DINO, and CLIP. Particularly, it improves CLIP pre-trained ViT-L by +1.6% to reach `89.0%` on ImageNet-1K image classification, which is **the most accurate ViT-L model**.
 2. Merged a PR from **Nvidia** that links to faster Swin Transformer inference that have significant speed improvements on `T4 and A100 GPUs`.
 3. Merged a PR from **Nvidia** that enables an option to use `pure FP16 (Apex O2)` in training, while almost maintaining the accuracy.