Extremely large output file size using tortoise #366

Closed
opened 2023-09-03 03:20:22 +00:00 by halcyon · 2 comments

I've trained multiple models on different voices and Tortoise usually outputs files that are in the 1-5 mb range for a ~10 second clip.

However one of my models generates audio files that are over 100 mb in size for the same prompts. This is consistent across all checkpoints of the model and different prompts. Inference quality and speed are similar to other models. Are there any factors that might cause this to happen?

I've trained multiple models on different voices and Tortoise usually outputs files that are in the 1-5 mb range for a ~10 second clip. However one of my models generates audio files that are over 100 mb in size for the same prompts. This is consistent across all checkpoints of the model and different prompts. Inference quality and speed are similar to other models. Are there any factors that might cause this to happen?
Owner

Verify that you have Embed Output Metadata disabled in the settings.

Verify that you have `Embed Output Metadata` disabled in the settings.
Author
No description provided.
Sign in to join this conversation.
No Milestone
No project
No Assignees
2 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#366
No description provided.