Update XTTS cloning #3207
Merged
Update XTTS cloning #3207
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Edresson
approved these changes
Nov 13, 2023
| @@ -255,39 +255,57 @@ def device(self): | |||
| return next(self.parameters()).device | |||
|
|
|||
| @torch.inference_mode() | |||
| def get_gpt_cond_latents(self, audio, sr, length: int = 3): | |||
| def get_gpt_cond_latents(self, audio, sr, length: int = 30, chunk_length: int = 6): | |||
There was a problem hiding this comment.
I think the default value here and in the config should be the same.
There was a problem hiding this comment.
I think it will be better, users can try to call this function individually and then get very different results. I think the better is both be equal to avoid issues like it.
There was a problem hiding this comment.
config as in the code or the release model's config
|
All looks good to me. |
|
@erogol With this PR we will be able to use upto 30s of speaker_wav for voice cloning? Instead of 6s (before)? |
|
You can use any length and any number of samples. Just don't go wild. Samples should be consistent in style, pitch, etc. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Optionally chunk input audio and average the computed latents. It prevents long silences, especially against references with many silent segments.