search

chrisdonahue / wavegan

WaveGAN: Learn to synthesize raw audio with generative adversarial networks
MIT License
1.33k stars 281 forks source link

Samplerate questions #53

Closed SilvanMertes closed 5 years ago

SilvanMertes commented 5 years ago

Hi! I have a little question concerning the train-data that can be used. As I see, the default sample rate that is used by WaveGan is 16k. Does this imply that I also have to convert the training data to 16k sample rate? The BachPiano pieces for example have a sample rate of 44.1k Thank you for your reply!

go-dustin commented 5 years ago

I don't know for sure but I don't think you do. I believe you use this to set the sample rate of the source --data_sample_rate 44100

chrisdonahue commented 5 years ago

The script will automatically convert the sample rates of the source audio files into whatever sample rate you specify for the training script. The only exception is if you user --data_fast_wav to load files faster, in which case the file sample rate needs to match the specified sample rate to the training script.