Use model to enhance audios with sample rate 16Khz or 8 Khz

[HiAlexa]

Can you suggest how can we use or change the model for audios with sample rate 16Khz or 8Khz ? i dont want to upsample the input to 48Khz. any help in this direction is much appreciated

[StuartIanNaylor]

Usually most soundcards will support 48Khz so you can just downsample auto with the plug devices

pcm.ladspa {
    type ladspa
    slave.pcm "plughw:3,0";
    path "/usr/lib/ladspa";
    plugins [{
        label deep_filter_mono
        input {
            control [ 100 ]
        }
    }]
}

pcm.deepfilter {
    type=plug
    slave = {
    pcm "ladspa"
    channels 1
    rate 48000}
}

If you put the ladspa in /usr/lib/ladspa then the plug device will auto resample even though the input is 48Khz

arecord -Ddeepfilter -r16000 -fS16_LE

[rodrigoGA]

I'm also keenly interested in this. It's important for many streaming services and phone calls that typically use 16KHz or 8KHz. Direct enhancement at these rates would be incredibly useful.

[github-actions[bot]]

This issue is stale because it has been open 90 days with no activity. Remove stale label or comment or this will be closed in 7 days.