Effective bug detection is vital in software development, as the identification and localization of defects are crucial for creating robust applications. In Python-based programs, the traditional bug detection process depends on a Python interpreter, leading to workflow interruptions because of sequential error detection. As Python’s popularity increases, so does the demand for more efficient bug detection tools. The proposed method focuses on error detection within Python code. Leveraging advanced transformer models, we aim to enhance the accuracy and efficiency of identifying errors, such as syntax errors, logical errors, and runtime errors, within Python programs. By employing transformer-based techniques, we seek to overcome the limitations of conventional error detection methods and provide developers with a robust tool for ensuring the reliability and stability of their Python applications.