110 review and test voice cloning task #132
Conversation
fabiocat93
added
documentation
|
hi @900miles, can you please review this?
|
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #132 +/- ##
==========================================
+ Coverage 59.33% 59.43% +0.10%
==========================================
Files 83 84 +1
Lines 2850 2845 -5
==========================================
Hits 1691 1691
+ Misses 1159 1154 -5 ☔ View full report in Codecov by Sentry. |
| source_audios (List[Audio]): A list of source audio samples. | ||
| target_audios (List[Audio]): A list of target audio samples. | ||
| model (SenselabModel, optional): The model to use for voice cloning. | ||
| Defaults to TorchModel(path_or_uri="bshall/knn-vc", revision="master"). |
There was a problem hiding this comment.
We should specify in the documentation itself that as of now, only KNNVC is supported.
|
@900miles thank you. i think i have fixed the last comments. feel free to approve the code if you think it's ready to be merged. |
tutorials/voice_cloning.ipynb
Outdated
There was a problem hiding this comment.
The colab link in this file points to the speech-to-text tutorial
| This function performs a pairwise voice cloning operation, where each audio in the | ||
| `source_audios` list is converted and mapped onto the corresponding audio in the | ||
| `target_audios` list. The resulting list contains target audio samples with their | ||
| voices replaced by the voices from the corresponding source samples. |
There was a problem hiding this comment.
I'm pretty sure this is backwards. The resulting list contains the content of the source audio file with the voice changed to sound like the voice in the corresponding target audio file, right?
It should be ready for another review @900miles |
PR to address the questions in #110