[GH-ISSUE #2352] Can I create a small final Model from "model and optimizer state" (epoch-) saves? #1630

New issue

Open

opened 2026-10-20 10:10:44 +00:00 by bsakaguchi · 0 comments

bsakaguchi commented

2026-10-20 10:10:44 +00:00

Owner

Originally created by @bananenmann66 on GitHub (Oct 16, 2024).
Original GitHub issue: https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/issues/2352

Hi,
yesterday I trained a new Model with 1000 Epochs, but I forgot to check the "Save a small final model to the 'weights' folder at each save point" option. While training I let RVC save every 5th epoch the model and optimizer state. Tensorboard now shows me, that step 15.800 out of 19.800 could be the best. Is there a possibility to create a small final model from those big G_15800.pth and D_15800.pth files later (now) without needing to do the whole training again? ? Please, help :D

Originally created by @bananenmann66 on GitHub (Oct 16, 2024). Original GitHub issue: https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/issues/2352 Hi, yesterday I trained a new Model with 1000 Epochs, but I forgot to check the "**Save a small final model to the 'weights' folder at each save point**" option. While training I let RVC save every 5th epoch the model and optimizer state. Tensorboard now shows me, that step 15.800 out of 19.800 could be the best. Is there a possibility to create a small final model from those big G_15800.pth and D_15800.pth files later (now) without needing to do the whole training again? ? Please, help :D