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
    Kaldi ASR Integration With Triton Inference Server
    Resource
    NVIDIA
    NVIDIA
    Kaldi ASR Integration With Triton Inference Server

    Kaldi ASR custom backend for the NVIDIA Triton Inference Server.

    1. Clone the repository.
    git clone https://github.com/NVIDIA/DeepLearningExamples.git
cd DeepLearningExamples/Kaldi/SpeechRecognition
    1. Build the client and server containers.

    scripts/docker/build.sh

    1. Download and set up the pre-trained model and eval dataset.

    scripts/docker/launch_download.sh

    The model and dataset are downloaded in the data/ folder.

    1. Start the server.

    scripts/docker/launch_server.sh

    Once you see the line Starting Metrics Service at 0.0.0.0:8002, the server is ready to be used. You can then start the client.

    Currently, multi-GPU is not supported. By default GPU 0 is used. You can use a specific GPU by using NVIDIA_VISIBLE_DEVICES:

    NVIDIA_VISIBLE_DEVICES=<GPUID> scripts/docker/launch_server.sh

    1. Start the client.

    The following command will stream 1000 parallel streams to the server. The -p option prints the inferred TEXT sent back from the server.

    scripts/docker/launch_client.sh -p

    NVIDIA uses cookies to improve your experience on our web site. We and our third-party partners also use cookies and other tools to collect and record information you provide as well as information about your interactions with our websites for performance improvement, analytics, and to assist in marketing efforts. By clicking "Accept All", you consent to our use of cookies and other tools as described in our Cookie Policy. You can manage your cookie settings by clicking on "Manage Settings." By continuing to use this site or by clicking one of the buttons below, you agree to our Terms of Service (which contains important waivers). Please see our Privacy Policy for more information on our privacy practices.