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 Es ContextNet 1024
Model
NVIDIA
NVIDIA
STT Es ContextNet 1024

ContextNet-1024 model for Spanish Automatic Speech Recognition, Trained on NeMo ASRSET 2.0

1 Version
1.8.0Selected
03/02/2022 2:28 AM UTC451.8 MB
Accuracy (greedy)
KeyValue
MCV7.0 dev4.8 %
MLS test3.5 %
CALLHOME train18.2 %
CALLHOME devtest19.1 %
MLS dev3.1 %
CALLHOME evltest20.7 %
Voxpopuli dev5.1 %
MCV7.0 test5.2 %
Fisher test15.1 %
Voxpopuli test6.2 %
Fisher dev15.3 %
Model
KeyValue
ArchitectureContextNet
OutputsTranscribed speech
Inputs16 kHz Mono-channel