Update README.md

README.md

@@ -84,7 +84,7 @@ print(model.config.id2label[predicted_class])
 
 ### Training Data
 
-The dataset consisted of 190,335 real and deepfake face images, with RandomOverSampler used to balance the two classes. The data was split into 60% training and 40% testing, maintaining class stratification.
+The dataset consisted of 190,335 self-collected real and deepfake face images, with RandomOverSampler used to balance the two classes. The data was split into 60% training and 40% testing, maintaining class stratification.
 
 ### Training Procedure
 
@@ -158,4 +158,4 @@ Agasta. (2025). *Virtus: Deepfake Detection using Vision Transformers*. Hugging
 
 ## Model Card Contact
 
-For questions or feedback, reach out via [GitHub](https://github.com/Itz-Agasta) or open an issue on the [model repository](https://github.com/Itz-Agasta/Lopt/tree/main/models/image). or main me at [email protected]
+For questions or feedback, reach out via [GitHub](https://github.com/Itz-Agasta) or open an issue on the [model repository](https://github.com/Itz-Agasta/Lopt/tree/main/models/image). or mail me at [email protected]