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
NVIDIA
English T5-based Inverse Text Normalization
Model
NVIDIA
NVIDIA
English T5-based Inverse Text Normalization

English inverse text normalization model based on albert-base-v2 tagger and t5-small decoder.

1 Version
1.11.0Selected
08/16/2022 4:58 PM UTC273.25 MB
Accuracy
KeyValue
DEFAULT TEST (FROM GOOGLE TEXT NORMALIZATION DATASET)2.9% WER, 97.31% SENTENCE ACCURACY
Model
KeyValue
ARCHITECTUREBERT
INPUTSLIST OF SPOKEN-DOMAIN SENTENCES WITHOUT PUNCTUATION, AS IN ASR OUTPUT
OUTPUTSLIST OF TAB-SEPARATED TEXT RECORDS, CONSISTING OF 5 COLUMNS, FIRST COLUMN IS THE FINAL WRITTEN-DOMAIN SENTENCE