Fix typo in README.md

"recongition" -> "recognition" in the new MedASR description

README.md

@@ -22,7 +22,7 @@ pinned: false
   * **ShieldGemma** is a series of safety content moderation models built upon Gemma 2 that target four harm categories
 * [**Health AI Developer Foundations**](https://huggingface.co/collections/google/health-ai-developer-foundations-hai-def-6744dc060bc19b6cf631bb0f)
   * [**MedGemma**](https://huggingface.co/collections/google/medgemma-release-680aade845f90bec6a3f60c4) collection of open models for medical image and text comprehension to accelerate building healthcare-based AI applications
-  * [**MedASR**](https://huggingface.co/google/medasr) A lightweight automatic speech recongition model pre-trained for medical contexts. 
+  * [**MedASR**](https://huggingface.co/google/medasr) A lightweight automatic speech recognition model pre-trained for medical contexts. 
   * [**MedSigLIP**](https://huggingface.co/google/medsiglip-448) MedGemma's vision encoder; can be used like other embedding models for predictive tasks. 
   * [**TxGemma**](https://huggingface.co/collections/google/txgemma-release-67dd92e931c857d15e4d1e87) collection of open models to accelerate the development of therapeutics
   * **HeAR** ([TensorFlow](https://huggingface.co/google/hear), [PyTorch](https://huggingface.co/google/hear-pytorch)) embedding model for efficiently building AI related to audio originating from the respiratory system