Getting Started#

Prerequisites#

Check the Support Matrix to make sure that you have the supported hardware and software stack.

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 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#

Supported models are available in two formats:

  • Pre-generated: These optimized models use TensorRT. You can download and use them directly on the corresponding GPU. Choose this model format if it is available for your GPU.

  • RMIR/Generic Model: This intermediate model requires an additional deployment step before you can use it. You can optimize this model with TensorRT and deploy it on any supported GPU. Choose this model format if a pre-generated model is not available for your GPU.

The following table shows how to launch a container for various models.

Note

Refer to the table of Supported Models and specify value for NIM_MANIFEST_PROFILE in below commands, according to model of interest and target GPU.

Download the pre-generated model and start the NIM.

# Set the appropriate profile for the pre-generated model.
export NIM_MANIFEST_PROFILE=<nim_manifest_profile>

# Deploy the pre-generated optimized model.
docker run -it --rm --name=riva-speech \
   --runtime=nvidia \
   --gpus '"device=0"' \
   --shm-size=8GB \
   -e NGC_API_KEY \
   -e NIM_MANIFEST_PROFILE \
   -e NIM_HTTP_API_PORT=9000 \
   -e NIM_GRPC_API_PORT=50051 \
   -p 9000:9000 \
   -p 50051:50051 \
   nvcr.io/nim/nvidia/riva-speech:1.2.0

On startup, the container downloads the pre-generated model from NGC. You can skip this download step on future runs by caching the model locally using a cache directory.

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

# Set the appropriate profile for the pre-generated model.
export NIM_MANIFEST_PROFILE=<nim_manifest_profile>

# Deploy the pre-generated optimized model. The model is stored in the cache directory.
docker run -it --rm --name=riva-speech \
   --runtime=nvidia \
   --gpus '"device=0"' \
   --shm-size=8GB \
   -e NGC_API_KEY \
   -e NIM_MANIFEST_PROFILE \
   -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/riva-speech:1.2.0

Once the initial deployment is successful, subsequent deployments can be performed using the same command to leverage the cached models in the cache directory.

Note

When using model cache, if you change NIM_MANIFEST_PROFILE to load different model, then ensure to clear the contents of the cache directory on host machine before starting the NIM container. This will ensure that only the requested model profile is loaded.

Download the RMIR model, optimize it using TensorRT for the target GPU, and then start the NIM.

# Set the appropriate profile for the RMIR model.
export NIM_MANIFEST_PROFILE=<nim_manifest_profile>

# Generate optimized model using RMIR
docker run -it --rm --name=riva-speech \
   --runtime=nvidia \
   --gpus '"device=0"' \
   --shm-size=8GB \
   -e NGC_API_KEY \
   -e NIM_MANIFEST_PROFILE \
   -e NIM_HTTP_API_PORT=9000 \
   -e NIM_GRPC_API_PORT=50051 \
   -p 9000:9000 \
   -p 50051:50051 \
   -e NIM_OPTIMIZE=True \
   nvcr.io/nim/nvidia/riva-speech:1.2.0
  1. Download the RMIR model and optimize it using TensorRT for the target GPU. The container exits after model generation is complete.

# Create a directory to store the optimized model, then update the directory permissions.
mkdir exported_model
chmod 777 exported_model

# Set the appropriate profile for the RMIR model.
export NIM_MANIFEST_PROFILE=<nim_manifest_profile>

# Generate optimized model using RMIR
docker run -it --rm --name=riva-speech \
   --runtime=nvidia \
   --gpus '"device=0"' \
   --shm-size=8GB \
   -e NGC_API_KEY \
   -e NIM_MANIFEST_PROFILE \
   -e NIM_HTTP_API_PORT=9000 \
   -e NIM_GRPC_API_PORT=50051 \
   -p 9000:9000 \
   -p 50051:50051 \
   -e NIM_OPTIMIZE=True \
   -v $PWD/exported_model:/export \
   -e NIM_EXPORT_URL=/export \
   nvcr.io/nim/nvidia/riva-speech:1.2.0
  1. Start the NIM using the locally exported optimized model.

# Start the NIM using the optimized model.
docker run -it --rm --name=riva-speech \
   --runtime=nvidia \
   --gpus '"device=0"' \
   --shm-size=8GB \
   -e NGC_API_KEY \
   -e NIM_MANIFEST_PROFILE \
   -e NIM_HTTP_API_PORT=9000 \
   -e NIM_GRPC_API_PORT=50051 \
   -p 9000:9000 \
   -p 50051:50051 \
   -v $PWD/exported_model:/opt/nim/.cache \
   -e NIM_DISABLE_MODEL_DOWNLOAD=True \
   nvcr.io/nim/nvidia/riva-speech:1.2.0

Note

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

Supported Models#

Model

Language

Model format/GPU

GPU Memory (GB)

NIM_MANIFEST_PROFILE

fastpitch-hifigan

en-US

Pre-generated / H100

2

bbce2a3a-4337-11ef-84fe-e7f5af9cc9af

fastpitch-hifigan

en-US

RMIR / Generic

2

3b6cd99c-74c2-11ef-b646-b303b35236b9

Running Inference#

  1. Open a new terminal and run the following command to check if the service is ready to handle inference requests:

curl -X 'GET' 'http://localhost:9000/v1/health/ready'

If the service is ready, you get a response similar to the following.

{"status":"ready"}
  1. Install the Riva Python client

Riva uses gRPC APIs. You can download proto files from Riva gRPC Proto files and compile them to a target language using Protoc compiler. You can find Riva clients in C++ and Python languages at the following locations.

Install Riva Python client

sudo apt-get install python3-pip
pip install -r https://raw.githubusercontent.com/nvidia-riva/python-clients/main/requirements.txt
pip install --force-reinstall git+https://github.com/nvidia-riva/python-clients.git

Download Riva sample client

git clone https://github.com/nvidia-riva/python-clients.git
  1. Run Text-to-Speech (TTS) inference:

python3 python-clients/scripts/tts/talk.py --server 0.0.0.0:50051 \
  --voice "English-US.Female-1" --language-code en-US \
  --text "Hello, this is a speech synthesizer." \
  --output output.wav

On running the above command, the synthesized audio file named output.wav will be created. Available voices can be queried using --list-voices option.

python3 python-clients/scripts/tts/talk.py --server 0.0.0.0:50051 --list-voices

The sample client supports the following options to make a transcription request to the gRPC endpoint.

  • --text - Text input to synthesize, supports providing SSML tags with text. See customization for further information.

  • --language-code - A language of input text. Currently, only “en-US” is supported in Riva TTS NIM.

  • --list-voices - List available voices. This argument should be used exclusively just to query the available voices before running inference.

  • --voice - A voice name to use. You can determine the value from the output of --list-voices option.

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 for 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_MANIFEST_PROFILE=<profile>

Specify the model to load.

-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.

Stopping the Container#

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

docker stop riva-speech
docker rm riva-speech