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
  • —
    STT Hr Conformer-Transducer Large
    Model
    —
    STT Hr Conformer-Transducer Large

    Conformer-Transducer-Large model for Croatian automatic speech recognition, trained on ParlaSpeech-HR v1.0 dataset.

  • 1 Version
    1.11.0Selected
    08/04/2022 10:26 PM UTC455.73 MB
  • Accuracy
    KeyValue
    ParlaSpeech-HR v1.0 Test WER(%)4.69
    ParlaSpeech-HR v1.0 Dev WER(%)4.56
    Model
    KeyValue
    Encoder Dimension512
    Number of Layers17
    ArchitectureConformer-Transducer-Large
    DatasetParlaSpeech-HR v1.0
    OutputsText in Croatian
    InputsSpeech in Croatian
    Number of Weights119M