Hi, I need to train a 16 kHz model for noise removal in the meeting scenario, and there are two questions:
If I train based on 16K audio data, what modifications need to be made in the config.ini, for example, is it okay for me like this?
[df]
sr = 16000
fft_size = 480
hop_size = 240
nb_erb = 16
nb_df = 48
Is that so? Are there any other places that need to be modified to make the model effect optimal?
Are there any 16k pre-trained models? Thank you very much.
Hi, I need to train a 16 kHz model for noise removal in the meeting scenario, and there are two questions:
Is that so? Are there any other places that need to be modified to make the model effect optimal?