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 Fast Conformer-Transducer XXLarge
Model
NVIDIA
NVIDIA
STT En Fast Conformer-Transducer XXLarge

Fast Conformer-Transducer-XXLarge model for English Automatic Speech Recognition, trained on NeMo ASRSET 3.0

2 Versions
1.20.1Selected
07/28/2023 9:09 PM UTC3.99 GB98 EpochsBatch Size: 4096GPU: A100
Accuracy
KeyValue
WSJ Eval-921.09
Librispeech test-other2.71
MCV Test 8.06.45
Librispeech test-clean1.50
MLS Test4.58
NSC Part-14.48
Model
KeyValue
Encoder Dimension1024
Number of Layers42
ArchitectureFastConformer Transducer
DatasetNeMo ASRSET 3.0
OutputsText in English
InputsSpeech in English
Number of Weights1.1B
1.20.0
06/07/2023 7:50 PM UTC3.99 GB102 EpochsBatch Size: 2048
Accuracy
KeyValue
LibriSpeech Test-other3.04
LibriSpeech Test-clean1.59
Model
KeyValue
Encoder Dimension1024
Number of Layers42
ArchitectureFast-Conformer-Transducer
DatasetNeMo ASRSET 3.0
OutputsText in English
InputsSpeech in English
Number of Weights1.1B