Skip to navigation

End-to-End Demo Chart

View as MarkdownOpen in Claude

The nvidia-bnr-h4m-sample Helm chart deploys a complete BNR demo pipeline on Holoscan for Media, including the following:

  • Sender pipeline.
  • BNR NIM service (nvidia-bnr-h4m-service).
  • Receiver pipeline (SMPTE ST 2110 or NMOS).
  • SRT output for preview.

Installation

Prerequisites

Complete all prerequisite steps (Rivermax license, image pull and model pull secrets, high-speed network attachment) before running helm install. For details, refer to Getting Started.

Pull the Chart

helm pull nim-repo/nvidia-bnr-h4m-sample --version 2.0.0

For the full repository setup, refer to Pull Helm Charts.

Helm Installation

The default values.yaml ships with example values for cluster-specific fields such as node selector (example-gpu-node), image pull secret, network name, and scheduler. Before deploying, update these fields to match your cluster.

Minimal deployment using global overrides (NMOS mode):

helm upgrade --install bnr-h4m-sample \
nvidia-bnr-h4m-sample-2.0.0.tgz \
--set global.nodeSelector.hostname=<gpu-node-name> \
--set global.image.secret=<image-pull-secret> \
--set global.network.name=<multus-net-attach-def> \
--set global.schedulerName=<scheduler-name> \
--set nvidia-bnr-h4m-service.ngc.secretName=<model-pull-secret>

For all available Helm values, refer to Configuration.

First, deploy the receiver and NIM service. When the pipeline is ready, enable the sender. This procedure prevents audio from accumulating in receiver queues before the NIM is ready.

# Phase 1: receiver + NIM service only
helm upgrade --install bnr-h4m-sample \
nvidia-bnr-h4m-sample-2.0.0.tgz \
--set sender.enabled=false
kubectl rollout status deployment/<receiver-appName> --timeout=180s
kubectl rollout status deployment/<nim-appName> --timeout=300s
# Phase 2: enable sender
helm upgrade --install bnr-h4m-sample \
nvidia-bnr-h4m-sample-2.0.0.tgz
kubectl rollout status deployment/<sender-appName> --timeout=180s

On Red Hat OpenShift, replace kubectl with oc.

After installation, verify all pods are running:

kubectl get pods

Sender Sample Media

The sender expects an MPEG Transport Stream (.ts) file containing an audio stream for BNR processing.

The sender container includes a sample file:

/workspace/assets/bnr_audio_48k_looped.ts

To test with your own audio, upload a .ts file to a PersistentVolumeClaim (PVC) and enable the built-in PVC mount on the sender:

sender:
inputAssets:
audioFile: /workspace/assets/my-custom-audio.ts
inputData:
pvc:
enabled: true
claimName: bnr-sender-input-data

Starter Configuration Files

SMPTE ST 2110 Configuration - Static (values-st2110.yaml)

sender:
enabled: true
appName: nvidia-bnr-sender-st2110
nodeSelector:
hostname: example-gpu-node
image:
repository: nvcr.io/nim/nvidia/bnr-h4m-sample-client
tag: "2.0.0"
secret: ngc-image-secret
network:
name: media-a-tx-net
inputAssets:
audioFile: /workspace/assets/bnr_audio_48k_looped.ts
nmos:
enabled: false
service:
enabled: true
type: NodePort
port: 9010
nodePort: 32513
receiver:
enabled: true
appName: nvidia-bnr-receiver-st2110
nodeSelector:
hostname: example-gpu-node
image:
repository: nvcr.io/nim/nvidia/bnr-h4m-sample-client
tag: "2.0.0"
secret: ngc-image-secret
network:
name: media-a-tx-net
receiverMode: processed
nmos:
enabled: false
service:
enabled: true
type: NodePort
port: 9010
nodePort: 32514
srtPort:
internal: 9090
external: 32090
nvidia-bnr-h4m-service:
enabled: true
appName: nvidia-bnr-nim-st2110
nodeSelector:
hostname: example-gpu-node
image:
repository: nvcr.io/nim/nvidia/bnr-h4m
tag: "2.0.0"
pullPolicy: IfNotPresent
secret: ngc-image-secret
network:
name: media-a-tx-net
nmos:
enabled: false
service:
enabled: true
type: NodePort
nimHttpPort: 8000
nimHttpNodePort: 32516
model:
type: v2-48k
intensityRatio: 1.0
bnr:
nmosEnabled: false
nimEnabled: true

NMOS Configuration (values-nmos.yaml)

sender:
enabled: true
appName: nvidia-bnr-sender-nmos
nodeSelector:
hostname: example-gpu-node
image:
repository: nvcr.io/nim/nvidia/bnr-h4m-sample-client
tag: "2.0.0"
secret: ngc-image-secret
network:
name: media-a-tx-net
inputAssets:
audioFile: /workspace/assets/bnr_audio_48k_looped.ts
nmos:
enabled: true
hostname: bnr-sender.local
description: BNR Audio Sender
label: BNR Audio Sender
service:
enabled: true
type: NodePort
port: 9010
nodePort: 32513
receiver:
enabled: true
appName: nvidia-bnr-receiver-nmos
nodeSelector:
hostname: example-gpu-node
image:
repository: nvcr.io/nim/nvidia/bnr-h4m-sample-client
tag: "2.0.0"
secret: ngc-image-secret
network:
name: media-a-tx-net
receiverMode: processed
nmos:
enabled: true
hostname: bnr-receiver.local
description: BNR Audio Receiver
label: BNR Audio Receiver
service:
enabled: true
type: NodePort
port: 9010
nodePort: 32514
srtPort:
internal: 9090
external: 32090
nvidia-bnr-h4m-service:
enabled: true
appName: nvidia-bnr-nim-nmos
nodeSelector:
hostname: example-gpu-node
image:
repository: nvcr.io/nim/nvidia/bnr-h4m
tag: "2.0.0"
pullPolicy: IfNotPresent
secret: ngc-image-secret
network:
name: media-a-tx-net
nmos:
enabled: true
httpPort: 9010
seed: nvidia-bnr-nim-nmos
hostname: bnr-nim.local
description: BNR-NIM
label: BNR-NIM
service:
enabled: true
type: NodePort
port: 9010
nodePort: 32515
nimHttpPort: 8000
nimHttpNodePort: 32516
model:
type: v2-48k
intensityRatio: 1.0
input:
audio:
sessionName: audio_in
output:
audio:
sessionName: audio_out
bnr:
nmosEnabled: true
nimEnabled: true

View Output via SRT

Get the internal IP address of the node:

kubectl get nodes -o wide

The SRT output is on port 32090 by default:

ffplay "srt://<internal-ip>:32090"

Verify

helm status bnr-h4m-sample
kubectl get pods -o wide

On Red Hat OpenShift, replace kubectl with oc.


Uninstall

helm uninstall bnr-h4m-sample