[GH-ISSUE #798] Higher learning rate - No sound after model inference #503

New issue

Closed

opened 2026-10-20 10:00:02 +00:00 by bsakaguchi · 2 comments

bsakaguchi commented

2026-10-20 10:00:02 +00:00

Owner

Originally created by @KatieBelli on GitHub (Jul 19, 2023).
Original GitHub issue: https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/issues/798

I changed the learning rate from 1e-4 to 5e-3 and trained for 350 epochs but no matter which audio file I infer with the model there is always no sound. How can I fix this?

Originally created by @KatieBelli on GitHub (Jul 19, 2023). Original GitHub issue: https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/issues/798 I changed the learning rate from 1e-4 to 5e-3 and trained for 350 epochs but no matter which audio file I infer with the model there is always no sound. How can I fix this?

bsakaguchi

2026-10-20 10:00:02 +00:00

closed this issue
added the
stale
label

bsakaguchi commented

2026-10-20 10:00:03 +00:00

Author

Owner

@github-actions[bot] commented on GitHub (Apr 28, 2024):

This issue was closed because it has been inactive for 15 days since being marked as stale.

@github-actions[bot] commented on GitHub (Apr 28, 2024): This issue was closed because it has been inactive for 15 days since being marked as stale.

bsakaguchi commented

2026-10-20 10:00:03 +00:00

Author

Owner

@aizawa-naoki commented on GitHub (May 20, 2025):

I think it is because 5e-3 = 1e-4 * 50 , so high for break the model

@aizawa-naoki commented on GitHub (May 20, 2025): I think it is because 5e-3 = 1e-4 * **50** , so high for break the model