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 Conformer-Transducer Small
Model
NVIDIA
NVIDIA
STT En Conformer-Transducer Small

Conformer-Transducer-Small model for English Automatic Speech Recognition, Trained on NeMo ASRSET

2 Versions
1.6.0
02/15/2022 10:41 PM UTC51.96 MB
Accuracy
KeyValue
LibriSpeech Dev-clean2.8
LibriSpeech Test-other6.6
LibriSpeech Dev-other6.6
LibriSpeech Test-clean2.5
Model
KeyValue
Encoder Dimension176
Number of Layers16
ArchitectureConformer-Transducer-Small
DatasetNeMo ASRSET 2.0
OutputsText in English
InputsSpeech in English
Number of Weights14M
1.4.0Selected
09/16/2021 12:17 AM UTC52 MB
Accuracy
KeyValue
LibriSpeech Dev-clean3.2
LibriSpeech Dev-other7.5
LibriSpeech Test-clean3.4
LibriSpeech Test-other7.5
Model
KeyValue
ArchitectureConformer-Transducer-Small
DatasetNeMo ASRSET 1.4.1
Encoder Dimension176
InputsSpeech in English
Number of Layers16
Number of Weights14M
OutputsText in English