typo fix

chapters/en/unit7/video-processing/multimodal-based-video-models.mdx

@@ -29,7 +29,7 @@ Beyond the modalities mentioned above, videos can incorporate even more diverse
     <img src="https://huggingface.co/datasets/hf-vision/course-assets/resolve/main/Multimodal_Based_Video_Models/Overview_VideoBERT.png" alt="VideoBERT model architecture.">
 </div>
 
-[VideoBERT](https://arxiv.org/abs/1904.01766) is an attempt to apply the BERT architecture directly to video data. Just like BERT in language models, the goal is to learn good visual-linguistic representation without any supervsion. For the text modality, VideoBERT uses ASR (Automatic Speech Recognition) to convert audio into text, and then obtains BERT token embeddings. For the video, it uses S3D to get token embeddings for each frame. 
+[VideoBERT](https://arxiv.org/abs/1904.01766) is an attempt to apply the BERT architecture directly to video data. Just like BERT in language models, the goal is to learn good visual-linguistic representation without any supervision. For the text modality, VideoBERT uses ASR (Automatic Speech Recognition) to convert audio into text, and then obtains BERT token embeddings. For the video, it uses S3D to get token embeddings for each frame. 
 
 **Key Features**