skol101
skol101
Still not working on m1 as per https://github.com/osrf/homebrew-simulation/issues/1628#issuecomment-2167803844 But this works : curl -ssL http://get.gazebosim.org | sh
Have you tried using data_augmentation flag?
I've followed your training instructions to the T, with one slight difference: I haven't created test.txt in prepare_flist, though this shouldn't have any effect on training results.
Also, is 64 batch size could be the issue. I understand that's to utilise as much memory of the rtx 3090 as possible.
I see, so it's not as simple as renaming data_utils_old.py to data_utils.py ?
Oh yes, "splitting voice" is something I'm hearing , too, in the generated audio.
Can this model be fine-tuned to a custom dataset by continuning from a pre-trained checkpoint?
Ok, I'll first try finetuning
I have continued from the pretrained model, but the logs are saying that current step is only 130400, not 900k. I've downloaded generator and discriminator from here https://onedrive.live.com/?authkey=%21AOOs5nZpsLC4ECE&id=537643E55991EE7B%219178&cid=537643E55991EE7B But generator...
I've started fine tuning with 2 gpus, but the same batch size . Good to know. I'll observe tuning results.