Closed RenNagasaki closed 2 months ago
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
Love that! Thanks! ❤️
Please, do me the favour of saving these settings. I'm having to train a shitload of voices, and having to refill all these fields each time, is killing me. 🤣