Iver Jordal
Iver Jordal
I haven't thought it through, but yeah, we should ideally have a pretrained model that is ready to be used. The model can be uploaded as a binary in a...
It would be awesome if you could make that happen 🤩 But I guess the pretrained model would depend on a specific sample rate, right? Ideally, torch-audiomentations should be compatible...
I think @nicofarr means time mask like in SpecAugment, but applied to waveforms. I.e. pick one or more time spans and silence the audio there
When I resample, I can get two outcomes: * The pitch goes up and the tempo goes up * The pitch goes down and the tempo goes down Here's a...
No, not at the moment. I recommend using the TimeStretch in audiomentations for the time being. There is an experimental time stretch PR in torch-audiomentations, but it is nowhere near...
https://github.com/vinusankars/ESOLA
This ideas is not implemented in audiomentations yet. The idea in this issue is to add "anchors" and allow the output to have the same length as the input. Different...
> * and another repo where they added anchors not randomly but at the start/end of phones or words. I don't remember the name of the repo right now, but...
What's better? * `target_rms` * `target_rms_db` (and give the RMS value in decibel)
Hi :) Thanks for the effort so far, and thanks for the patience. I've been in crunch mode at work for the past few days. I saw that there are...