Deep voices #286

Open
opened 2023-06-29 04:47:28 +00:00 by helloitsme · 2 comments

Has anyone had success with deep voices? I've found every model trained with a deep speaker so far to come out much higher than their normal voice.

Has anyone had success with deep voices? I've found every model trained with a deep speaker so far to come out much higher than their normal voice.

Both low and high-pitched voices come out closer to the median. Might improve with more training cycles but I usually just pitch-shift it with ffmpeg.

Both low and high-pitched voices come out closer to the median. Might improve with more training cycles but I usually just pitch-shift it with ffmpeg.

I have gotten pretty accurate (meaning low pitched) results on George Takei and James Earl Jones using ~250 epochs however the results have static-y artifacts. I'm trying to finetune BigVGAN to see if that helps

I have gotten pretty accurate (meaning low pitched) results on George Takei and James Earl Jones using ~250 epochs however the results have static-y artifacts. I'm trying to finetune BigVGAN to see if that helps
Sign in to join this conversation.
No Milestone
No project
No Assignees
3 Participants
Notifications
Due Date
The due date is invalid or out of range. Please use the format 'yyyy-mm-dd'.

No due date set.

Dependencies

No dependencies set.

Reference: mrq/ai-voice-cloning#286
No description provided.