Predictive text is an input technology that facilitates typing on a mobile device by suggesting words the end user may wish to insert in a text field. Predictions are based on the context of other words in the message and the first letters typed. Because the end user simply taps on a word instead of typing it it out on a soft keyboard, predictive text can significantly speed up the input process.
Here , I have used Project Gutenberg as dataset and vocabulary corpus for the model. Project Gutenberg is a library of over 60,000 free eBooks. For model creation , Keras Sequential model is used (Model Summary in png picture above). The vocabulary of model is only in the 2000s because of small corpus file , but you can use many other corpus available on the internet and better data preprocessing steps to improve upon this model. Weights and Biases (.h5 file) was too big (179MB) to upload to Github.
The user can also take their own email and messages corpus and create own personal assistance predictive text software that mimics you.