Text Normalization: Weighted Finite State Transducer

Model Overview

This model is an OpenFST finite state archive (.far) for use within the opensource Sparrowhawk normalization engine [2]. This model has been created for English (en-US) text.

Model Architecture

This model uses weighted finite-state transducer (WFST) grammars that map strings in written form to strings in spoken form.

Training

The model was constructed using Nemo toolkit as outlined in intro and Text processing

How to Use this Model

To use this model , we can use Riva Skills Quick start guide , it is a starting point to try out Riva models . Information regarding Quick start guide can be found : here.

Input

This model is part of a pipeline for text to speech and accepts text as input.

Output

The output is normalized text which is then passed to the next stage in the text to speech pipeline.

References

[1] NeMo Inverse Text Normalization: From Development To Production

[2] [Google Sparrowhawk] (https://github.com/google/sparrowhawk)

License

By downloading and using the models and resources packaged with Riva Conversational AI, you would be accepting the terms of the Riva license