[Dataset] Where should I put the dataset and what should it look like? #345
Labels
No Label
bug
duplicate
enhancement
help wanted
insufficient info
invalid
news
not a bug
question
wontfix
No Milestone
No project
No Assignees
2 Participants
Notifications
Due Date
No due date set.
Dependencies
No dependencies set.
Reference: mrq/ai-voice-cloning#345
Loading…
Reference in New Issue
Block a user
No description provided.
Delete Branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
This work is very nice, but regarding the training details in the wiki I didn't get it, I have a dataset folder that includes a wav subfolder that consisis of roughly 3000 2-4s wav clip, and a metadata.txt(fig below), each line of this file is wav_name(in wav subfolder) | text of this wav clip. Is my dataset formatted correctly? And where should i put it.

If this is for TorToiSe, then everything under the web UI puts the data in the right place. You're free to make any adjustments to the
train.txt
before finetuning.