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 En Es Conformer Transducer Large
    Model
    NVIDIA
    STT En Es Conformer Transducer Large

    English and Spanish ASR Conformer Transducer Large Model

  • 1 Version
    1.0.0Selected
    03/29/2022 11:34 PM UTC465.43 MB
  • Accuracy
    KeyValue
    Fisher dev (es)16.2 %
    LibrispeechDevClean (en)2.0 %
    MLS dev (es)3.3 %
    LibrispeechTestClean (en)2.2 %
    Voxpopuli dev (es)5.3 %
    LibrispeechTestOther (en)4.6 %
    LibrispeechDevOther (en)4.6 %
    MCV7.0 (dev)5.0 %
    Model
    KeyValue
    ARCHITECTUREConformer
    INPUTS16000 KHZ MONO-CHANNEL AUDIO (WAV FILES)
    OUTPUTSTRANSCRIBED SPEECH