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 XLarge
Model
NVIDIA
NVIDIA
STT En Conformer-CTC XLarge

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

1 Version
1.10.0Selected
05/26/2022 9:12 PM UTC2.37 GB
Accuracy
KeyValue
SLR835.50 %
Librispeech test-other3.74 %
Librispeech dev-other3.79 %
NSC Part 6 long6.44 %
WSJ Dev 932.36 %
Peoples Speech22.90 %
Librispeech dev-clean1.77 %
Librispeech test-clean2.00 %
Mozilla Common Voice 8.0 test7.88 %
Multilingual Librispeech test (EN)5.99 %
Model
KeyValue
Encoder Dimension1024
Number of Encoder Layers24
DatasetNeMo ASRSET 3.0
ARCHITECTUREConformer-CTC
INPUTS16000 KHZ MONO-CHANNEL AUDIO (WAV FILES)
Number of Weights0.6B
OUTPUTSTRANSCRIBED SPEECH