Riva TTS English US Auxiliary Files

Model Overview

This repo contains the files used by the Riva team in creating TTS rmirs. Included are:

• cmudict-0.7b_nv22.08
• ipa_cmudict-0.7b_nv22.08
• abbr.txt

Model Architecture

cmudict-0.7b_nv22.08: A text file where each line indicates a mapping from an English word to ARPAbet phone(s).
ipa_cmudict-0.7b_nv22.08: A text file where each line indicates a mapping from an English word to IPA phone(s).
abbr.txt: A text file where each line indicates a mapping from an abbreviation to the expanded word.

Intended Use

Primary use case intended for these models is speech synthesis.

How to Use This Model

These files are meant to be used at the riva-build step when building TTS rmirs for use with Riva. For more details, please see the Riva TTS documentation.

Training Information

N/A

Limitations

N/A

License

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

Ethical AI

NVIDIA’s platforms and application frameworks enable developers to build a wide array of AI applications. Consider potential algorithmic bias when choosing or creating the models being deployed. Work with the model’s developer to ensure that it meets the requirements for the relevant industry and use case; that the necessary instruction and documentation are provided to understand error rates, confidence intervals, and results; and that the model is being used under the conditions and in the manner intended.