NGC | Catalog
CatalogModelsQuartzNet checkpoint (PyTorch, AMP, LibriSpeech)

QuartzNet checkpoint (PyTorch, AMP, LibriSpeech)

Logo for QuartzNet checkpoint (PyTorch, AMP, LibriSpeech)
QuartzNet PyTorch checkpoint trained on LibriSpeech (test-other 10.41% WER)
NVIDIA Deep Learning Examples
Latest Version
April 4, 2023
72.72 MB

Pre-trained model in checkpoint format.

How to use

For a quick start:

Download this model

In order to download the most recently uploaded version, click the Download button in the top right of this page. You can also browse through other versions of this pre-trained model in the Version history tab.

To preview the contents of the download go to File Browser tab and select your version.

Browse to the corresponding model-script

This model was trained using a script also available here in the NGC and on Github and executed in a container. We do not recommended to use this model without its corresponding model-script which contains the definition of the model architecture, preprocessing applied to the input data, as well as accuracy and performance results.

You can access the most recent model-script via NGC or GitHub.

Build the proper NGC container and start an interactive session

You can support yourself with the steps described in the Quick Start Guide of the corresponding model-script. Note that you might want to skip some steps (eg. training - as you have just downloaded an already trained model).

Run inference/evaluation

Within the container and with the support of the model-script, you can evaluate your model and use it for inference. Refer to sub-sections on inference in the Quick Start Guide and Advanced tabs of the model-script

What can you do with a pre-trained model?

A few examples of what you can do with a pre-trained model are:

  • running inference/predictions using the model directly
  • building more efficient inference engines
  • resuming training from the downloaded checkpoint
  • transfer learning
  • training a student network

Compatibility with other scripts

All available versions of this model were trained using corresponding model-scripts optimized for DGX usage. Although possible, usage of the model in different configurations is not supported.


"Model-script": a set of scripts containing the definition of the model architecture, training methods, preprocessing applied to the input data, as well as documentation covering usage and accuracy and performance results

"Model": a shorthand for (pre)trained-model. It is a saved state of the internal parameters of the model.

"Pre-trained model": see "Model"

"Trained model": see "Model"

"Checkpoint": A "model" representation saved by a framework during training.