Our project employs deep learning methods to digitize handwritten pages into text. The process has a number of steps, ranging from identifying individual words, and identifying individual characters. Through the use of convolutional neural networks (CNNs) and other sophisticated machine learning models, the project seeks to perform accurate and efficient recognition of handwritten text. The model is trained on the IAM Handwriting Dataset, which contains a diverse collection of handwritten text samples, allowing the system to generalize well across different handwriting styles. Key components of the project include preprocessing the input images, extracting features using CNN layers, and optimizing the model over multiple training epochs. The result is a robust handwriting recognition system capable of converting handwritten words into editable digital text, with applications in document digitization, historical manuscript preservation, and automated data entry systems. Keywords: Handwritten Text Recognition, Deep Learning Methods, Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs)