Skip to navigation

This page covers Helm values for the nvidia-active-speaker-detection-h4m-operator chart (controller pod) and fields for the NvidiaActiveSpeakerDetectionMediaFunction custom resource (NIM workload).

Pipeline tuning semantics on the custom resource match the Pipeline Configuration Helm keys.


Operator Helm Chart (nvidia-active-speaker-detection-h4m-operator)

Values for the operator controller pod (not the NIM deployment):

ConfigurationHelm KeyComment
Operator imageimage.repository, image.tag, image.pullPolicyDefaults: nvcr.io/nim/nvidia/active-speaker-detection-h4m-operator, tag 1.0.0, pull Always.
Inline registry credentials (operator pod)imageCredentials.*Defaults: registry nvcr.io, username $oauthtoken, password "", email ""; empty password skips chart-created pull secret.
Inline registry credentials (NIM operands)mediaFunction.imageCredentials.*Same shape as imageCredentials; empty password skips the media-function registry secret.
Pull secretsimagePullSecretsDefault: [{name: ngc-api-key}] (operator pod image pull).
Default NIM image for operandsmediaFunction.image, mediaFunction.imagePullSecretsDefaults: image nvcr.io/nim/nvidia/active-speaker-detection-h4m-nim:1.0.0, pull secrets [{name: ngc-api-key}].
Default NIM schedulermediaFunction.schedulerNameDefault: topo-aware-scheduler.
Operator replicasreplicasDefault: 1.
Leader electionleaderElectionDefault: true.
Operator pod resourcesresources.*Defaults: limits 500m CPU / 128Mi memory; requests 10m CPU / 64Mi memory.
Metricsmetrics.enabled, metrics.portDefault: true, port 8443.
ServiceAccountserviceAccount.create, serviceAccount.nameDefault: create true, name "".

The media function image is configured when the operator is installed, so NvidiaActiveSpeakerDetectionMediaFunction instances managed by an operator use the same validated operator and media-function image combination. This approach ensures the operator and workload are always supported together and avoids compatibility issues.

As a result, CRs managed by an operator share the chart-level mediaFunction.image and mediaFunction.imagePullSecrets configured at install time. To run multiple custom resources with different NIM image tags, deploy multiple operators, each configured with its own mediaFunction.image.


(operator-media-function-cr)=

Custom Resource (NvidiaActiveSpeakerDetectionMediaFunction)

Full YAML example: Example Manifest.

Scheduling and Cluster

ConfigurationCR PathComment
Node selectorspec.nodeSelectorKubernetes node labels (for example, kubernetes.io/hostname).

Parameters: Network, Resources, Secrets, Security

ConfigurationCR PathComment
High-speed networksspec.parameters.highSpeedNetworkDefault name: media-a-tx-net; for Multus, list of {name, ip?}.
Pod resourcesspec.parameters.resourcesKubernetes requests and limits for the operand NIM workload.
NGC model downloadspec.parameters.ngcModelDownloadsecretName, secretKey; default key: NGC_API_KEY.
Model cache / logsspec.parameters.nimModelCache / spec.parameters.nimLogsOptional PVC-backed model cache and NIM logs. Subkeys include path, pvc.enabled, and pvc.claimName; refer to Advanced Usage.
Security contextspec.parameters.securityContextExample: runAsUser: 1000, capabilities for Rivermax and RTP; refer to Getting Started
Pod security contextspec.parameters.podSecurityContextExample: fsGroup: 1000, seccompProfileType: RuntimeDefault; applies at the pod level.
NMOS metadataspec.parameters.label, spec.parameters.descriptionNMOS IS-04 registration strings.

Pod Resources (spec.parameters.resources)

ResourceRequestsLimits
cpu1212
hugepages-2Mi8Gi8Gi
memory8Gi8Gi
nvidia.com/gpu11

Parameters: Pipeline Tuning

(parameters-pipeline-asd-tuning-cr)=

ConfigurationCR Path (spec.parameters.*)Environment Variable (on NIM Pod)Comment
Sync tolerancesyncToleranceAI4M_ACTIVESPEAKERDETECTION_SYNC_TOLERANCEDefault: 0.5986; valid range: (0, 1). Invalid values fall back to default.
Bounding box overlaytestFrameOverlayModeAI4M_ACTIVESPEAKERDETECTION_TEST_FRAME_OVERLAY_MODEtrue or false
Output frame buffer sizeoutputFrameBufferSizeAI4M_ACTIVESPEAKERDETECTION_OUTPUT_FRAME_BUFFER_SIZEDefault: 30 frames.
Audio silence detectionuseAudioThresholdToDetectActiveAudioStreamAI4M_ACTIVESPEAKERDETECTION_USE_AUDIO_THRESHOLD_TO_DETECT_ACTIVE_AUDIO_STREAMDefault: false.
Audio silence thresholdaudioThresholdDbAI4M_ACTIVESPEAKERDETECTION_AUDIO_THRESHOLD_DBDefault: -40.0 dB.
Log levelloggingLevel(mapped by operator to NIM env)0 FATAL, 1 ERROR, 2 WARN, 3 INFO (default), 4 DEBUG, 5 VERBOSE.

Inputs and Outputs

AreaCR PathComment
Video inspec.inputs.video_inputcontrol, transport, format.video; see subfields in next table.
Audio inspec.inputs.audio_inputs (audio_input_0 … audio_input_<n-1>)One block per stream; count must match pipeline.
Video outspec.outputs.video_outputOptional; resolution must match input when present.
Ancillary outspec.outputs.ancillary_data_outputRequired for SMPTE ST 2110-40; format.data.media_type default: video/smpte291; payload layout: Ancillary Data Payload.

Video Format Subfields

These subfields apply to video input and video output.

FieldExample ValueComment
media_typevideo/rawFixed for uncompressed ST 2110-20.
frame_width1920Must match NIM video.width.
frame_height1080Must match NIM video.height.
frame_rate"30"Frames per second as a string.
interlace_modeprogressive
color_samplingYCbCr-4:2:2
component_depth10Bits per component.
colorspaceBT709
transfer_characteristicSDR

frame_rate must be identical for spec.inputs.video_input.format.video and spec.outputs.video_output.format.video. Invalid values are rejected when the CR is applied. The following values are supported:

ValueRate
"24"24 fps
"25"25 fps
"30"30 fps
"30000/1001"29.97 fps (fractional)
"50"50 fps
"60"60 fps
"60000/1001"59.94 fps (fractional)

Use a plain integer string for whole rates and a numerator/denominator string for fractional rates. Always quote the value in YAML so fractions are not interpreted as numbers.

Audio Format Subfields

These subfields apply to each audio_input_n stream.

FieldExample ValueComment
sample_rate48000Must match NIM audio.samplingRate.
channel_count1Mono per stream; must match NIM audio.numChannels.
sample_depth24Bits; corresponds to PCM L24.
media_typeaudio/L24Fixed for ST 2110-30 mono L24.

CR Schema Reference

With the nvidiaactivespeakerdetectionmediafunctions.nvidia.com CRD installed, inspect field types and OpenAPI details from the cluster:

kubectl explain nvidiaactivespeakerdetectionmediafunctions.nvidia.com --recursive
kubectl explain nvidiaactivespeakerdetectionmediafunctions.nvidia.com.spec
kubectl explain nvidiaactivespeakerdetectionmediafunctions.nvidia.com.spec.inputs.video_input.format.video
kubectl explain nvidiaactivespeakerdetectionmediafunctions.nvidia.com.spec.outputs.ancillary_data_output

Some validation rules might not appear in kubectl explain output but are still enforced when the CR is applied.

Status Conditions (status.conditions)

Status Overview

The operator reports health using Kubernetes conditions in status.conditions (type, status, reason, message).

A media function is considered healthy and ready when the following are all True:

  • Provisioned: Deployment and pod are running.
  • Registered: Successfully registered with NMOS / SDP.
  • Configured: Required configuration has been applied.

Important Statuses

StatusWhat It Means
ProvisionedApp deployment is running.
RegisteredRegistration succeeded.
ConfiguredConfiguration applied successfully.
ConnectedConnections are established.
ActiveReserved for future media-flow status.
DegradedReserved for future health reporting.

When to Alert

Alert if any of these stay False:

  • Provisioned
  • Registered
  • Configured

Most important failure reason values:

  • DeploymentNotAvailable
  • NmosQueryFailed

Connected False is usually informational or transient and can occur when connections are still being established.

Ignore Active and Degraded for now.

Check Status

Use the custom resource metadata.name (not a Pod name).

kubectl get nvidiaactivespeakerdetectionmediafunction <cr-name> \
-o jsonpath='{range .status.conditions[*]}{.type}{"\t"}{.status}{"\t"}{.reason}{"\n"}{end}'

See Also