mirror of
https://github.com/OpenBMB/VoxCPM
synced 2025-12-12 11:58:11 +00:00
Modify lora inference api
This commit is contained in:
@@ -354,7 +354,6 @@ model = VoxCPM.from_pretrained(
|
|||||||
|
|
||||||
- Increase `r` (LoRA rank)
|
- Increase `r` (LoRA rank)
|
||||||
- Adjust `alpha` (try `alpha = r/2` or `alpha = r`)
|
- Adjust `alpha` (try `alpha = r/2` or `alpha = r`)
|
||||||
- Ensure `enable_dit: true` (required for voice cloning)
|
|
||||||
- Increase training steps
|
- Increase training steps
|
||||||
- Add more target modules
|
- Add more target modules
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user