Is this page helpful?

End-to-End Demo Chart Configuration#

This page covers Helm values for the sender and receiver components of the nvidia-active-speaker-detection-h4m-sample chart. NIM service keys within the demo chart live under nvidia-active-speaker-detection-h4m-service.<key>. For more information, refere to Common Helm Configuration and Pipeline Configuration.

Sender#

Configuration

Helm Key (sender.*)

Comment

Enable sender

sender.enabled

Allowed: Boolean; default: true. Two-phase bring-up (receiver + NIM service first, then sender) recommended.

Naming / scale

sender.appName, sender.replicas

Defaults: nvidia-active-speaker-detection-sender-nmos, 1.

Node

sender.nodeSelector.hostname

Default: example-gpu-node; set to a node name that exists in your cluster (such as from kubectl get nodes).

Image

sender.image.repository, sender.image.tag, sender.image.secret

Defaults: nvcr.io/nim/nvidia/active-speaker-detection-h4m-sample-sender, 1.0.0, ngc-api-key.

Input asset

sender.inputAssets.*

Keys: videoFile, numOfAudioTrack, videoFramerateNum, videoFramerateDen, videoWidth, videoHeight; defaults: /workspace/assets/sample_asset.ts, 2, 30, 1, 1920, 1080.

SMPTE ST 2110 ports

sender.st2110Ports.*

Keys: senderRemoteIp, video, audio; defaults: 234.5.8.26, 7005, 7006.

NMOS

sender.nmos.*

Keys: enabled, hostname, description, label; defaults: true, asd-sender.local, NVIDIA Active Speaker Detection Sender, Nvidia-ASD-Sender. Same semantics as NIM service nmos.*; refer to Common Helm Configuration.

Multus / secondary network

sender.network.name

Default: media-a-tx-net; pod secondary network attachment (such as high-speed media fabric).

Input Asset Requirements#

The sender expects an MPEG Transport Stream (.ts) file with the following specifications:

  • Video stream: H.264, with one or more visible speakers.

  • Audio streams: Opus, 48 kHz, mono; one track per speaker.

The sender container includes a bundled sample file at /workspace/assets/sample_asset.ts (1080p, 30 fps, 2 audio tracks).

Note

An audio stream must contain only a single speaker’s audio. During silence, samples must be zero. If background noise is present, enable audio thresholding via useAudioThresholdToDetectActiveAudioStream and audioThresholdDb on the NIM service. For details, refer to Pipeline Configuration.

Receiver#

Configuration

Helm Key (receiver.*)

Comment

Enable receiver

receiver.enabled

default: true.

Naming / scale

receiver.appName, receiver.replicas

Defaults: nvidia-active-speaker-detection-receiver-nmos, 1.

Node

receiver.nodeSelector.hostname

Default example-gpu-node; set to a node name that exists in your cluster (for example, from kubectl get nodes).

Image

receiver.image.*

Defaults: repository nvcr.io/nim/nvidia/active-speaker-detection-h4m-sample-receiver, tag 1.0.0, secret ngc-api-key.

Receive mode

receiver.receiverType

Allowed: ancillary or video; default: ancillary (see next row).

Ancillary params

receiver.ancillaryInputParams.*

Keys: hostIp, hostPort, framerateNum, framerateDen; defaults: 234.5.8.27, 7006, 30, 1. Used in ancillary mode.

Video params

receiver.videoInputParams.*

Keys: videoReceiverRemoteIp, videoReceiverPort, videoWidth, videoHeight, videoFramerateNum, videoFramerateDen; defaults: 234.5.8.26, 7005, 1920, 1080, 30, 1. Used in video mode.

NMOS

receiver.nmos.*

Keys: enabled, hostname, description, label; defaults: true, sd-receiver.local, NVIDIA Active Speaker Detection Receiver, Nvidia-ASD-ANC-Receiver.

SRT output

receiver.srtPort.internal, receiver.srtPort.external

SRT preview stream mapping; defaults: internal 8888, external 30889.

Multus / secondary network

receiver.network.name

Default: media-a-tx-net; pod secondary network attachment (such as high-speed media fabric).

Receiver Modes#

Mode

Value

Description

Ancillary

ancillary

Receives bounding box metadata via SMPTE ST 2110-40. Use to consume detection results programmatically.

Video

video

Receives output video with bounding box overlays, re-streamed via SRT. Requires testFrameOverlayMode: true on the NIM service.

See Also#