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
    English Tagger-based Inverse Text Normalization
    Model
    NVIDIA
    English Tagger-based Inverse Text Normalization

    English single-pass tagger-based model for inverse text normalization based on bert-base-uncased, trained on 2 mln sentences from Google Text Normalization Dataset, achieves 3.75% WER on Google default test set

  • 1 Version
    1.9.0Selected
    05/12/2022 3:37 PM UTC424.78 MB5 EpochsBatch Size: 128GPU: V100
  • Accuracy
    KeyValue
    default test (from Google Text Normalization Dataset)3.75% WER, 97.47% Sentence Accuracy
    Model
    KeyValue
    ArchitectureBERT
    OutputsList of tab-separated text records, consisting of 5 columns, first column is the final text after ITN
    InputsList of spoken-domain sentences without punctuation, as in ASR output