diff --git a/README.md b/README.md
index d5cd892..9280f0a 100644
--- a/README.md
+++ b/README.md
@@ -12,7 +12,7 @@ Disclaimer: The team releasing Audio Spectrogram Transformer did not write a mod
 
 ## Model description
 
-The Audio Spectrogram Transformer is equivalent to [ViT](https://huggingface.co/docs/transformers/model_doc/detr), but applied on audio. Audio is first turned into an image (as a spectrogram), after which a Vision Transformer is applied. The model gets state-of-the-art results on several audio classification benchmarks.
+The Audio Spectrogram Transformer is equivalent to [ViT](https://huggingface.co/docs/transformers/model_doc/vit), but applied on audio. Audio is first turned into an image (as a spectrogram), after which a Vision Transformer is applied. The model gets state-of-the-art results on several audio classification benchmarks.
 
 ## Usage