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 Kab Conformer-Transducer Large
Model
NVIDIA
NVIDIA
STT Kab Conformer-Transducer Large

Conformer-Transducer-Large model for Kabyle Automatic Speech Recognition, trained on Mozilla Common Voice 10.0 Kabyle train set.

1 Version
1.12.0Selected
08/23/2022 8:04 PM UTC455.73 MBAccuracy: 18.8643 EpochsBatch Size: 8GPU: V100
Accuracy
KeyValue
MCV 10.0 test set18.86
model
KeyValue
ARCHITECTURECONFORMER-TRANSDUCER
OutputsTRANSCRIBED SPEECH
INPUTS16000 KHZ MONO-CHANNEL AUDIO (WAV FILES)