ContainersNVIDIADeepSeek-R1NVIDIALlama-3.1-Nemotron-70B-InstructNVIDIAPyTorch
CollectionsNVIDIAOmniverse Kit (FB)NVIDIADeepStream SDKNVIDIAOmniverse Kit App Streaming
ModelsNVIDIAStyleGAN3 pretrained modelsNVIDIAPeopleNetNVIDIATrafficCamNet
ResourcesNVIDIARiva Skills Quick Start
Helm ChartsNVIDIAGPU OperatorNVIDIANVIDIA NIM Operator
  • NVIDIA Deep Learning Examples
    QuartzNet checkpoint (PyTorch, AMP, LibriSpeech)
    Model
    NVIDIA Deep Learning Examples
    QuartzNet checkpoint (PyTorch, AMP, LibriSpeech)

    QuartzNet PyTorch checkpoint trained on LibriSpeech (test-other 10.41% WER)

  • 1 Version
    21.03.0Selected
    09/21/2021 10:22 PM UTC72.72 MBAccuracy: 0260 EpochsBatch Size: 1152GPU: A100
  • architecture
    KeyValue
    typequartznet10x5_speedp-online-1.15_speca: SpecAugment (2x15, 2x55); Speed perturbation U(0.85, 1.15)
    performance
    KeyValue
    dev_clean_wer3.51
    dev_other_wer10.67
    test_clean_wer3.82
    test_other_wer10.41
    training
    KeyValue
    batch_size1152
    datasetLibriSpeech
    epochs260
    training_precisionAMP