Skip to main content
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
    STT Es Conformer Transducer Large
    Model
    NVIDIA
    STT Es Conformer Transducer Large

    Conformer-Transducer-Large model for Spanish Automatic Speech Recognition, Trained on NeMo ASRSET 2.0

  • 1 Version
    1.8.0Selected
    03/02/2022 2:28 AM UTC421.53 MB
  • Accuracy (greedy)
    KeyValue
    MCV7.0 dev4.6 %
    MLS test3.2 %
    CALLHOME train17.2 %
    CALLHOME devtest18.0 %
    MLS dev2.7 %
    CALLHOME evltest19.4 %
    Voxpopuli dev4.7 %
    MCV7.0 test5.2 %
    Fisher test14.8 %
    Voxpopuli test6.0 %
    Fisher dev14.7 %
    Model
    KeyValue
    ArchitectureConformer Transducer
    OutputsTranscribed speech
    Inputs16 kHz Mono-channel