Closed jhaco closed 7 months ago
I'll also add this functionality to SMDataTools. StepCOVNet shouldn't need to do any file conversion imo
https://www.tensorflow.org/io/tutorials/audio
Could make an uplift task that includes this new feature and do away with librosa altogether
Since we're already using the Librosa library for some of our audio processing, we could cut down on a lot of the wav_converter code by using librosa.load
By default, librosa.load will resample to 22,050 hz, reduce the number of channels to 1 (mono), and normalize the data so that values will range from -1 to 1.
Since we want to create 16,000 hz, mono wav files, we can adjust the conversion function to do this using
Thoughts?