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-CTC Medium
Model
NVIDIA
NVIDIA
STT En Conformer-CTC Medium

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

3 Versions
1.6.0
02/15/2022 10:43 PM UTC108.97 MB
Accuracy
KeyValue
LibriSpeech Dev-clean2.5
LibriSpeech Test-other5.9
LibriSpeech Dev-other5.8
LibriSpeech Test-clean2.6
Model
KeyValue
Encoder Dimension256
Number of Layers18
ArchitectureConformer-CTC-Medium
DatasetNeMo ASRSET 2.0
OutputsText in English
InputsSpeech in English
Number of Weights30M
1.0.0
06/02/2021 12:32 AM UTC108.45 MB
Accuracy
KeyValue
LibriSpeech Dev-clean2.9
LibriSpeech Test-other7.0
LibriSpeech Dev-other7.0
LibriSpeech Test-clean2.9
Model
KeyValue
Encoder Dimension256
Number of Layers18
ArchitectureConformer-CTC-Medium
DatasetNeMo ASRSET 1.4.1
OutputsText in English
InputsSpeech in English
Number of Weights30M
1.0.0rc1Selected
03/31/2021 12:09 AM UTC108.16 MB
Accuracy
KeyValue
LibriSpeech Dev-clean2.7
LibriSpeech Test-other7.4
LibriSpeech Dev-other7.4
LibriSpeech Test-clean3.0
Model
KeyValue
Encoder Dimension256
Number of Layers18
ArchitectureConformer-CTC-Medium
DatasetLibriSpeech
OutputsText in English
InputsSpeech in English
Number of Weights30M