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 Eo Conformer-Transducer Large
Model
NVIDIA
NVIDIA
STT Eo Conformer-Transducer Large

Conformer-Transducer-Large model for Esperanto Automatic Speech Recognition, finetuning from English SSL model on Mozilla Common Voice Esperanto 11.0 dataset.

1 Version
1.14.0Selected
12/14/2022 12:42 AM UTC455.65 MB
Accuracy
KeyValue
Mozilla_Common_Voice_11.00_test4.0 %
Mozilla_Common_Voice_11.00_dev2.4 %
Model
KeyValue
ARCHITECTUREConformer-Transducer
INPUTS16000 KHZ MONO-CHANNEL AUDIO (WAV FILES)
OUTPUTSTRANSCRIBED SPEECH