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 Medium
Model
NVIDIA
NVIDIA
STT En Conformer-Transducer Medium

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

2 Versions
1.6.0
03/16/2022 12:21 AM UTC124.61 MB
Accuracy
KeyValue
LibriSpeech Dev-clean2.0
LibriSpeech Test-other4.7
LibriSpeech Dev-other4.6
LibriSpeech Test-clean2.1
Model
KeyValue
Encoder Dimension256
Number of Layers16
ArchitectureConformer-Transducer-Medium
DatasetNeMo ASRSET 2.0
OutputsText in English
InputsSpeech in English
Number of Weights32M
1.4.0Selected
09/21/2021 10:19 PM UTC115.46 MB
Accuracy
KeyValue
LibriSpeech Dev-clean2.4
LibriSpeech Test-other5.8
LibriSpeech Dev-other5.5
LibriSpeech Test-clean2.6
Model
KeyValue
Encoder Dimension256
Number of Layers16
ArchitectureConformer-Transducer-Medium
DatasetNeMo ASRSET 1.4.1
OutputsText in English
InputsSpeech in English
Number of Weights32M