valenti/spark-vibevoice
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update FINETUNING.md

Browse Source
This commit is contained in:
mrfakename
2025-09-23 08:59:46 -07:00
committed by GitHub
parent a84b1003d6
commit 74d57a72a9
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
FINETUNING.md
+1 -1
View File
@@ -8,7 +8,7 @@ Join the [Discord](https://discord.gg/ZDEYTTRxWG) for support. Also take a look
## Notes ## Notes
* Members of the community have observed that for fine-tuning VibeVoice on a single voice, it is often beneficial to set `voice_prompt_drop_rate` to `1.0` and avoid use of voice cloning/reference audio all together during inference. This can lead to more natural speech generation. **If you are training on a single speaker I highly recommend you try this.** * Members of the community have observed that for fine-tuning VibeVoice on a SINGLE voice, it is often beneficial to set `voice_prompt_drop_rate` to `1.0` and avoid use of voice cloning/reference audio all together during inference. This can lead to more natural speech generation. **If you are training on a single speaker I highly recommend you try this. NOTE: This will REMOVE voice cloning capabilities. Your fine-tuned model will NOT support voice-cloning**
## Example Script ## Example Script