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 Be Conformer-CTC Large
Model
NVIDIA
NVIDIA
STT Be Conformer-CTC Large

Conformer-CTC-Large model for Belarusian Automatic Speech Recognition, trained on Mozilla Common Voice 10.0 Belarusian dataset.

2 Versions
1.11.0Selected
02/14/2023 9:49 PM UTC464.61 MB
Accuracy
KeyValue
mcv10-be4.7 %
Model
KeyValue
ARCHITECTUREConformer-CTC
INPUTS16000 KHZ MONO-CHANNEL AUDIO (WAV FILES)
OUTPUTSTRANSCRIBED SPEECH
1.12.0
08/31/2022 7:14 PM UTC464.61 MB
Accuracy
KeyValue
mcv10-be4.7 %
Model
KeyValue
ARCHITECTUREConformer-CTC
INPUTS16000 HZ MONO-CHANNEL AUDIO (WAV FILES)
OUTPUTSTRANSCRIBED SPEECH