Jetson-voice on nx whats the trick

Robotics & Edge Computing Jetson & Embedded Systems Jetson Xavier NX
1

I wanted to try jetson voice on my nx but the docker want’s r32.4.2 which is not avalable on the NX. is there another image that I am not finding? if so where do i get it?

2

Hi @Nick_H, here’s the link to the JetPack 4.4 Developer Preview SD card image: https://developer.nvidia.com/jetson-nx-developer-kit-sd-card-image-44-dp

Also there is newer version of jetson-voice project that has containers for JetPack 4.4.1 / 4.5 / 4.5.1:
https://github.com/dusty-nv/jetson-voice

1 Like
3

I got things going using your git on 4.5.1 all except for a mic.

My Tascam DR-05X
Input Device ID 25 - ‘TASCAM DR Series: USB Audio (hw:3,0)’ (inputs=2) (sample_rate=44100
Output Device ID 25 - ‘TASCAM DR Series: USB Audio (hw:3,0)’ (outputs=2) (sample_rate=44100

gives me the invalid sample rate

Audio Input Device:
{'defaultHighInputLatency': 0.034829931972789115,
 'defaultHighOutputLatency': 0.034829931972789115,
 'defaultLowInputLatency': 0.008684807256235827,
 'defaultLowOutputLatency': 0.008684807256235827,
 'defaultSampleRate': 44100.0,
 'hostApi': 0,
 'index': 25,
 'maxInputChannels': 2,
 'maxOutputChannels': 2,
 'name': 'TASCAM DR Series: USB Audio (hw:3,0)',
 'structVersion': 2}
Expression 'paInvalidSampleRate' failed in 'src/hostapi/alsa/pa_linux_alsa.c', line: 2048
Expression 'PaAlsaStreamComponent_InitialConfigure( &self->capture, inParams, self->primeBuffers, hwParamsCapture, &realSr )' failed in 'src/hostapi/alsa/pa_linux_alsa.c', line: 2719
Expression 'PaAlsaStream_Configure( stream, inputParameters, outputParameters, sampleRate, framesPerBuffer, &inputLatency, &outputLatency, &hostBufferSizeMode )' failed in 'src/hostapi/alsa/pa_linux_alsa.c', line: 2843
Traceback (most recent call last):
  File "examples/asr.py", line 33, in <module>
    for samples in stream:
  File "/jetson-voice/jetson_voice/utils/audio.py", line 174, in __iter__
    self.open()
  File "/jetson-voice/jetson_voice/utils/audio.py", line 146, in open
    frames_per_buffer=self.chunk_size)
  File "/usr/local/lib/python3.6/dist-packages/pyaudio.py", line 750, in open
    stream = Stream(self, *args, **kwargs)
  File "/usr/local/lib/python3.6/dist-packages/pyaudio.py", line 441, in __init__
    self._stream = pa.open(**arguments)
OSError: [Errno -9997] Invalid sample rate
5

Hi @Nick_H, please see my reply in your other thread here:

7

This topic was automatically closed 60 days after the last reply. New replies are no longer allowed.