Getting Started#

Prerequisites#

Setup#

NVIDIA AI Enterprise License: Riva ASR NIM is available for self-hosting under the NVIDIA AI Enterprise (NVAIE) License.
NVIDIA GPU(s): Riva ASR NIM runs on any NVIDIA GPU with sufficient GPU memory, but some model/GPU combinations are optimized. See the Supported Models for more information.
CPU: x86_64 architecture only for this release
OS: any Linux distributions which:
- Are supported by the NVIDIA Container toolkit
- Have glibc >= 2.35 in the output of ld -v
CUDA Drivers: Follow the installation guide. We recommend:
- Using a network repository as part of a package manager installation, skipping the CUDA toolkit installation as the libraries are available within the NIM container
- Installing the open kernels for a specific version:
  
  Major Version
  
  EOL
  
  Data Center & RTX/Quadro GPUs
  
  GeForce GPUs
  
  > 550
  
  TBD
  
  X
  
  X
  
  550
  
  Feb 2025
  
  X
  
  X
  
  545
  
  Oct 2023
  
  X
  
  X
  
  535
  
  June 2026
  
  X
  
  525
  
  Nov 2023
  
  X
  
  470
  
  Sept 2024
  
  X

Install Docker.
Install the NVIDIA Container Toolkit.

After installing the toolkit, follow the instructions in the Configure Docker section in the NVIDIA Container Toolkit documentation.

To ensure that your setup is correct, run the following command:

docker run --rm --runtime=nvidia --gpus all ubuntu nvidia-smi

This command should produce output similar to the following, where you can confirm the CUDA driver version and available GPUs.

   +-----------------------------------------------------------------------------------------+
   | NVIDIA-SMI 550.54.14              Driver Version: 550.54.14      CUDA Version: 12.4     |
   |-----------------------------------------+------------------------+----------------------+
   | GPU  Name                 Persistence-M | Bus-Id          Disp.A | Volatile Uncorr. ECC |
   | Fan  Temp   Perf          Pwr:Usage/Cap |           Memory-Usage | GPU-Util  Compute M. |
   |                                         |                        |               MIG M. |
   |=========================================+========================+======================|
   |   0  NVIDIA H100 80GB HBM3          On  |   00000000:1B:00.0 Off |                    0 |
   | N/A   36C    P0            112W /  700W |   78489MiB /  81559MiB |      0%      Default |
   |                                         |                        |             Disabled |
   +-----------------------------------------+------------------------+----------------------+

   +-----------------------------------------------------------------------------------------+
   | Processes:                                                                              |
   |  GPU   GI   CI        PID   Type   Process name                              GPU Memory |
   |        ID   ID                                                               Usage      |
   |=========================================================================================|
   |  No running processes found                                                             |
   +-----------------------------------------------------------------------------------------+

Installing WSL2 for Windows#

Refer NIM on WSL2 documentation for setup instructions.

NGC Authentication#

Generate an API key#

To access NGC resources, you need an NGC API key. You can generate a key here: Generate Personal Key.

When creating an NGC API Personal key, ensure that at least “NGC Catalog” is selected from the “Services Included” dropdown. More Services can be included if this key is to be reused for other purposes.

Note

Personal keys allow you to configure an expiration date, revoke or delete the key using an action button, and rotate the key as needed. For more information about key types, please refer to the NGC User Guide.

Export the API key#

Pass the value of the API key to the docker run command in the next section as the NGC_API_KEY environment variable to download the appropriate models and resources when starting the NIM.

If you’re not familiar with how to create the NGC_API_KEY environment variable, the simplest way is to export it in your terminal:

export NGC_API_KEY=<value>

Run one of the following commands to make the key available at startup:

# If using bash
echo "export NGC_API_KEY=<value>" >> ~/.bashrc

# If using zsh
echo "export NGC_API_KEY=<value>" >> ~/.zshrc

Note

Other, more secure options include saving the value in a file, so that you can retrieve with cat $NGC_API_KEY_FILE, or using a password manager.

Docker Login to NGC#

To pull the NIM container image from NGC, first authenticate with the NVIDIA Container Registry with the following command:

echo "$NGC_API_KEY" | docker login nvcr.io --username '$oauthtoken' --password-stdin

Use $oauthtoken as the username and NGC_API_KEY as the password. The $oauthtoken username is a special name that indicates that you will authenticate with an API key and not a user name and password.

Launching the NIM#

Models are available in two formats:

Prebuilt: Prebuilt models use TensorRT engines for optimized inference. ONNX or PyTorch models are used in cases where TensorRT engine is not available. You can download and use them directly on the corresponding GPU.
RMIR: This intermediate model format requires an additional deployment step before you can use it. You can optimize this model with TensorRT and deploy it on any supported GPU. This model format is automatically chosen if a prebuilt model is not available for your GPU.

NIM automatically downloads the prebuilt model on supported GPUs or generates an optimized model on-the-fly using RMIR model on other GPUs.

For WSL2 deployment, supported models are listed in the Supported Models. We recommend using the profile with smallest Batch Size, as it is optimized for lower memory usage.

Refer to the Supported Models section to choose the desired model and set the appropriate values for CONTAINER_ID and NIM_TAGS_SELECTOR. NIM_TAGS_SELECTOR allows you to select a specific profile from the available options.

For example, the following commands deploy the Parakeet 1.1b en-US model in streaming mode with the default batch size.

export CONTAINER_ID=riva-asr
export NIM_TAGS_SELECTOR="name=parakeet-1-1b-ctc-riva-en-us,mode=str"

docker run -it --rm --name=$CONTAINER_ID \
   --runtime=nvidia \
   --gpus '"device=0"' \
   --shm-size=8GB \
   -e NGC_API_KEY \
   -e NIM_HTTP_API_PORT=9000 \
   -e NIM_GRPC_API_PORT=50051 \
   -p 9000:9000 \
   -p 50051:50051 \
   -e NIM_TAGS_SELECTOR \
   nvcr.io/nim/nvidia/$CONTAINER_ID:latest

If deploying in a WSL2 environment, you may need to use podman instead of docker in the respective commands.

It may take up to 30 minutes for the Docker container to be ready and start accepting requests, depending on your network speed.

Runtime Parameters for the Container#

Flags	Description
`-it`	`--interactive` + `--tty` (see Docker docs)
`--rm`	Delete the container after it stops (see Docker docs)
`--name=<container-name>`	Give a name to the NIM container. Use any preferred value.
`--runtime=nvidia`	Ensure NVIDIA drivers are accessible in the container.
`--gpus '"device=0"'`	Expose NVIDIA GPU 0 inside the container. If you are running on a host with multiple GPUs, you need to specify which GPU to use. See GPU Enumeration for further information on mounting specific GPUs.
`--shm-size=8GB`	Allocate host memory for multi-GPU communication.
`-e NGC_API_KEY=$NGC_API_KEY`	Provide the container with the token necessary to download adequate models and resources from NGC. See NGC Authentication.
`-e NIM_HTTP_API_PORT=<port>`	Specify the port to use for HTTP endpoint. Port can have any value except 8000. Default 9000.
`-e NIM_GRPC_API_PORT=<port>`	Specify the port to use for GRPC endpoint. Default 50051.
`-p 9000:9000`	Forward the port where the NIM HTTP server is published inside the container to access from the host system. The left-hand side of `:` is the host system ip:port (`9000` here), while the right-hand side is the container port where the NIM HTTP server is published. Container port can be any value except 8000.
`-p 50051:50051`	Forward the port where the NIM gRPC server is published inside the container to access from the host system. The left-hand side of `:` is the host system ip:port (`50051` here), while the right-hand side is the container port where the NIM gRPC server is published.
`-e NIM_TAGS_SELECTOR=<key=value,...>`	Use this to filter tags in the auto profile selector. This can be a list of key-value pairs, where the key is the profile property name and the value is the desired property value. For example: `name=conformer-ctc-riva-es-us,mode=str`. Default value can be queried by starting the NIM and then running command `docker exec <container_id> env \| grep NIM_TAGS_SELECTOR` with appropriate `container_id`.

Model Caching#

On initial startup, the container will download the models from NGC. You can skip this download step on future runs by caching the model locally using a cache directory as shown below.

Prebuilt models

# Create the cache directory on the host machine:
export LOCAL_NIM_CACHE=~/.cache/nim
mkdir -p $LOCAL_NIM_CACHE
chmod 777 $LOCAL_NIM_CACHE

# Set the appropriate values
export CONTAINER_ID=riva-asr
export MODEL_ID=parakeet-1-1b-ctc-riva-en-us
export NIM_TAGS_SELECTOR="name=$MODEL_ID,mode=str,model_type=prebuilt"

# Run the container with the cache directory mounted in the appropriate location:
docker run -it --rm --name=$CONTAINER_ID \
      --runtime=nvidia \
      --gpus '"device=0"' \
      --shm-size=8GB \
      -e NGC_API_KEY \
      -e NIM_TAGS_SELECTOR \
      -e NIM_HTTP_API_PORT=9000 \
      -e NIM_GRPC_API_PORT=50051 \
      -p 9000:9000 \
      -p 50051:50051 \
      -v $LOCAL_NIM_CACHE:/opt/nim/.cache \
      nvcr.io/nim/nvidia/$CONTAINER_ID:latest

On subsequent runs, the models will be loaded from cache.

RMIR models

Deploy the RMIR models and export the generated models for future use.

# Create the cache directory on the host machine:
export NIM_EXPORT_PATH=~/nim_export
mkdir -p $NIM_EXPORT_PATH
chmod 777 $NIM_EXPORT_PATH

# Set the appropriate values
export CONTAINER_ID=riva-asr
export MODEL_ID=parakeet-1-1b-ctc-riva-en-us
export NIM_TAGS_SELECTOR="name=$MODEL_ID,mode=str,model_type=rmir"

# Run the container with the export directory mounted in the appropriate location:
docker run -it --rm --name=$CONTAINER_ID \
      --runtime=nvidia \
      --gpus '"device=0"' \
      --shm-size=8GB \
      -e NGC_API_KEY \
      -e NIM_TAGS_SELECTOR \
      -e NIM_HTTP_API_PORT=9000 \
      -e NIM_GRPC_API_PORT=50051 \
      -p 9000:9000 \
      -p 50051:50051 \
      -v $NIM_EXPORT_PATH:/opt/nim/export \
      -e NIM_EXPORT_PATH=/opt/nim/export \
      nvcr.io/nim/nvidia/$CONTAINER_ID:latest

Once the model deployment is complete, container terminates with below log.

INFO:inference:Riva model generation completed
INFO:inference:Models exported to /opt/nim/export
INFO:inference:Exiting container

Subsequent runs can be made with below command with NIM_DISABLE_MODEL_DOWNLOAD=true. This command loads the exported models instead of downloading the models from NGC again.

# Run the container with the cache directory mounted in the appropriate location:
docker run -it --rm --name=$CONTAINER_ID \
      --runtime=nvidia \
      --gpus '"device=0"' \
      --shm-size=8GB \
      -e NGC_API_KEY \
      -e NIM_TAGS_SELECTOR \
      -e NIM_DISABLE_MODEL_DOWNLOAD=true \
      -e NIM_HTTP_API_PORT=9000 \
      -e NIM_GRPC_API_PORT=50051 \
      -p 9000:9000 \
      -p 50051:50051 \
      -v $NIM_EXPORT_PATH:/opt/nim/export \
      -e NIM_EXPORT_PATH=/opt/nim/export \
      nvcr.io/nim/nvidia/$CONTAINER_ID:latest

Stopping the Container#

The following commands stop the container by stopping and removing the running docker container.

docker stop riva-asr
docker rm riva-asr

Major Version	EOL	Data Center & RTX/Quadro GPUs	GeForce GPUs
> 550	TBD	X	X
550	Feb 2025	X	X
545	Oct 2023	X	X
535	June 2026	X
525	Nov 2023	X
470	Sept 2024	X