NGC | Catalog
CatalogCollectionsTLT/Jarvis - Speech Recognition

TLT/Jarvis - Speech Recognition

For contents of this collection and more information, please view on a desktop device.
Logo for TLT/Jarvis - Speech Recognition

Description

This collection contains end-to-end neural models and notebooks for Automatic Speech Recognition (ASR) training and deployment using TLT and Jarvis respectively

Curator

NVIDIA

Modified

July 28, 2021
Containers
Helm Charts
Models
Resources

Speech Recognition Collection

Overview

This collection contains end-to-end neural models for Automatic Speech Recognition (ASR) using TLT. The models in this collection can be used for transcribing segments of audio to text, and can be used immediately for fine-tuning, dataset evaluation, or transcription of individual audio files.

Available Models

For instructions on how to use a model, please see its corresponding model card page.

  • Jasper
  • QuartzNet
  • Citrinet

License

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

Suggested Reading

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.