Unable to run example pipeline with nvaudioinfer component

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU)
GPU
• DeepStream Version
7.0
• JetPack Version (valid for Jetson only)
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs)
Unable to run example
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)

I’m looking at the reference section DeepStream Reference Application - deepstream-audio app — DeepStream documentation

There is a diagram of a pipeline graph with nvstreammux, nvinferaudio, and nvstreamdemux

1716×967 81.2 KB

Following this, there is an example gst-launch-1.0 command “demonstrating the above sample graph without nvinferaudio component:”

USE_NEW_NVSTREAMMUX=yes gst-launch-1.0 \
uridecodebin uri=file:///opt/nvidia/deepstream/deepstream/samples/streams/sonyc_mixed_audio.wav name=source_0 ! queue ! audioconvert ! audioresample ! mux.sink_0 \
uridecodebin uri=file:///opt/nvidia/deepstream/deepstream/samples/streams/sonyc_mixed_audio.wav name=source_1 ! queue ! audioconvert ! audioresample ! mux.sink_1 \
nvstreammux name=mux batch-size=2 ! \
nvstreamdemux name=demux \
demux.src_0 ! audioconvert ! audioresample ! alsasink async=false \
demux.src_1 ! audioconvert ! audioresample ! alsasink async=false

The above example seems to run correctly.

Now, I’m trying to extend the example to include nvinferaudio as follows.

USE_NEW_NVSTREAMMUX=yes gst-launch-1.0 \
uridecodebin uri=file:///opt/nvidia/deepstream/deepstream/samples/streams/sonyc_mixed_audio.wav name=source_0 ! queue ! audioconvert ! audioresample ! mux.sink_0 \
uridecodebin uri=file:///opt/nvidia/deepstream/deepstream/samples/streams/sonyc_mixed_audio.wav name=source_1 ! queue ! audioconvert ! audioresample ! mux.sink_1 \
nvstreammux name=mux batch-size=2 ! \
queue ! nvinferaudio config-file-path=/opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream-audio/configs/config_infer_audio_sonyc.txt ! \
nvstreamdemux name=demux \
demux.src_0 ! audioconvert ! audioresample ! alsasink async=false \
demux.src_1 ! audioconvert ! audioresample ! alsasink async=false

However, I’m unable to get this to run.

I see the follow messages

ERROR: from element /GstPipeline:pipeline0/GstNvInferAudio:nvinferaudio0: Failed to create audio transform
Additional debug info:
gstnvinferaudio.cpp(284): gst_nvinferaudio_start (): /GstPipeline:pipeline0/GstNvInferAudio:nvinferaudio0

Any help is appreciated.
Robert.

3

nvstreamdemux does not support nvinferaudio output.

4

Is this a bug? Are there plans to fix or support this?

5

No. It is not necessary to get audio from the batch. In the samples, the audio data can be sent to sink by tee after decoder.

E.G.

USE_NEW_NVSTREAMMUX=yes gst-launch-1.0 \
uridecodebin uri=file:///opt/nvidia/deepstream/deepstream/samples/streams/sonyc_mixed_audio.wav name=source_0 ! queue ! audioconvert ! audioresample ! tee name=t1 t1. ! mux.sink_0 \
uridecodebin uri=file:///opt/nvidia/deepstream/deepstream/samples/streams/sonyc_mixed_audio.wav name=source_1 ! queue ! audioconvert ! audioresample ! tee name=t2 t2. ! mux.sink_1 \
nvstreammux name=mux batch-size=2 ! \
queue ! nvinferaudio config-file-path=/opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream-audio/configs/config_infer_audio_sonyc.txt ! fakesink \
t1. ! audioconvert ! audioresample ! alsasink async=false \
t2. ! audioconvert ! audioresample ! alsasink async=false
6

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.