search

jaywalnut310 / vits

VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
https://jaywalnut310.github.io/vits-demo/index.html
MIT License
6.72k stars 1.23k forks source link

How can I know the number of steps? #172

Open vidigal opened 1 year ago

vidigal commented 1 year ago

[INFO] [1.463881015777588, 3.3058362007141113, 14.746193885803223, 13.179031372070312, 0.3828892707824707, 1.021393895149231, 277000, 1.1124354334266811e-05] [INFO] Saving model and optimizer state at iteration 23084 to ./logs/vcg_model/G_277000.pth [INFO] Saving model and optimizer state at iteration 23084 to ./logs/vcg_model/D_277000.pth [INFO] ====> Epoch: 23084

Looking at the log above, the number of steps I ran was 277k?

Thanks!

heesuju commented 1 year ago

Yes, I believe that is correct. Additionally, the number of steps per each epoch depends on the size of your dataset and the batch size.