Ancient literature, exemplified by texts such as the Bible, carries immense cultural and historical significance, serving as a repository of the ancestors' experiences, triumphs, tragedies, and beliefs. Yet, delving into these ancient texts presents formidable challenges due to their limited accessibility. Over time, numerous historical documents have either vanished or undergone alterations, whether due to natural calamities or deliberate human actions. These obstacles have stymied progress in the field of diplomatics, rendering it a sluggish and occasionally unreliable endeavor. Remarkably, within very words and sentences of these texts lies a treasure trove of information. Properly harnessed, they offer a rich source of records for the advancement of diplomatics. For instance, deep learning techniques hold the promise of uncovering the number of authors who contributed to texts like the Bible. This research employs well-established and straightforward deep learning modelsK-means, Gaussian Mixture Model (GMM), and Density-Based Spatial Clustering of Applications with Noise (DBSCAN)to categorize the diverse writing styles present in the Bible. This methodology can be extended to other ancient English texts with uncertain authorship. The study involves the extraction of text from various versions of the Bible, which is then transformed into strings for analysis using these models. By categorizing different writing styles based on their underlying principles, the analysis facilitates an estimation of the number of authors who contributed to the Bible. Furthermore, the ensuing discussion offers insights into the advantages and limitations of this research project, shedding light on how its methods and findings might impact individuals.