Remember settings for dataset creation and training
Closed this issue · 2 comments
RenNagasaki commented
erew123 commented
Ill see what I can do on the next version.
If for now you want to fix the values in finetune.py:
Learning rate is line 1447 value=5e-6,
and the others are lines 1142 to 1165:
parser.add_argument(
"--num_epochs",
type=int,
help="Number of epochs to train. Default: 10",
default=10,
)
parser.add_argument(
"--batch_size",
type=int,
help="Batch size. Default: 4",
default=4,
)
parser.add_argument(
"--grad_acumm",
type=int,
help="Grad accumulation steps. Default: 1",
default=1,
)
parser.add_argument(
"--max_audio_length",
type=int,
help="Max permitted audio size in seconds. Default: 11",
default=11,
)
Thanks
RenNagasaki commented
Love that! Thanks! ❤️