AWS Textract detecting "0" as "O"

Thank you for using Textract. Since, Textract is a machine learning model, it may not always reach expected accuracy on certain documents. The Textract model may not be working for this use case. However, please note that the Textract team continuously updates the model to improve the quality and include more use cases for better accuracy. In order to help us improve the models for your documents, please open a customer support ticket and share your documents with which you are facing the issue to help us analyze this further. Additionally, please look out for announcements regarding our model quality updates that are announced on the AWS Textract public release channel.

Please note that Textract is a built-in Machine Learning model and it does not allow users to train or customize the model as per the use cases. Hence, we cannot train the Textract model to return required results since it uses an internal model which cannot be customized.