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
STT En Es ContextNet Large
Model
NVIDIA
NVIDIA
STT En Es ContextNet Large

English and Spanish ASR Contextnet Transducer Large Model

1 Version
1.0.0Selected
03/29/2022 11:34 PM UTC559.92 MB
Accuracy
KeyValue
Fisher dev (es)14.8 %
LibrispeechDevClean (en)2.2 %
MLS dev (es)3.0 %
LibrispeechTestClean (en)2.3 %
Voxpopuli dev (es)5.0 %
LibrispeechTestOther (en)5.5 %
LibrispeechDevOther (en)5.6 %
MCV7.0 (dev)4.7 %
Model
KeyValue
ARCHITECTUREContextNet
INPUTS16000 KHZ MONO-CHANNEL AUDIO (WAV FILES)
OUTPUTSTRANSCRIBED SPEECH