Handwritten Text Recognition (HTR) has emerged as a critical technology with numerous applications in various domains, including document digitization, historical document preservation, and human-computer interaction. This paper presents a deep learning-based approach for handwritten text recognition, focusing on the IAM Words dataset. This model combines convolutional and recurrent neural networks and utilizes Connectionist Temporal Classification (CTC) for sequence labeling. The paper outlines data pre-processing techniques, training processes, and performance evaluation. The presented results in this paper demonstrate the model’s ability to accurately transcribe handwritten text and achieve promising accuracy in noisy conditions. This work not only contributes to the field of HTR but also highlights the potential for deploying this technology in real-world applications.