Stock market prediction is a longstanding challenge in financial analysis, influenced by myriad factors such as market sentiment, economic data, corporate performance, and geopolitical events. Traditional models like econometric methods and machine learning techniques have limitations in capturing the intricate temporal dependencies and stochastic nature of financial data. Recently, transformers, a deep learning architecture introduced in natural language processing (NLP), have shown significant promise for time-series forecasting, including stock market prediction. In our research used transformer models in stock market prediction and explored the trends and results are presented for the five days for Apple stock.