Open Madhavan0123 opened 8 months ago
Hi, temporarily turn off duration discriminator and tell me if it works.
Yes it seems to be working for now. Any reason with the duration discriminator is causing the issue ?
I feel my implementation was too naive. Might need to correct it with some testing. Busy on other models now, will do it when I have some time on me. Let me know about the audio quality after you train. Thanks.
Hello,thank you for your great effort ! I meet the same problem and I want to know will you correct it recently or still busy on other models?
I have moved to improving pflowtts
.
I have moved to improving
pflowtts
.
Hi, p0p4k, How is the pflowtts growing now? is it a better choice then vits2? can it support both normal tts and zero-shot tts?
I think better than vits/vits2. Only downside it not being e2e.
I think better than vits/vits2. Only downside it not being e2e.
ok, thank you.
@p0p4k do you know the bug here?
@codeghees which part ? training stuck part?
yep
In the same boat.
@codeghees did not look into this personally cause of no gpu yet. Maybe you can try to debug and send a PR. I can assist you. Thanks a lot!
Yep, will do! Trying to debug this.
@p0p4k bug is on line
scaler.scale(loss_gen_all).backward()
Seems like GradScalar has issues with multi-gpu. I removed it and replaced it with standard backprop. The issue persists. Looks like a multi GPU issue.
Works on single gpu?
Haven't tested yet. Trying a run with fp16 enabled.
@p0p4k I have no issues for single GPU training. But it will stuck if I do multiple GPU training. Any success for resolving the issue?
Hello ,
Thanks for all the effort to create this repo. When I launch training it runs for a few steps and then I see no progress at all. Its just stuck without any progress for a long time. It still hasnt progressed. INFO:ljs_base:Saving model and optimizer state at iteration 1 to ./logs/ljs_base/G_0.pth INFO:ljs_base:Saving model and optimizer state at iteration 1 to ./logs/ljs_base/D_0.pth INFO:ljs_base:Saving model and optimizer state at iteration 1 to ./logs/ljs_base/DUR_0.pth Loading train data: 4%|████████████▍
have you encountered this before ? Any help would be extremely helpful