Skip to content

Issues: auspicious3000/autovc

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Clear current search query, filters, and sorts
46 Open 65 Closed
46 Open 65 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

How you generate speaker embedding?
#34 opened Dec 13, 2019 by hsiehjackson
3
What are the full preprocessing steps?
#14 opened Aug 8, 2019 by MostafaOmar98
1
What is the format of the metadata?
#17 opened Aug 14, 2019 by 1015720437
21
Re-training steps?
#18 opened Aug 16, 2019 by Husnain08
1
re-training result, it is not good enough, can you share some advice about Hyperparameter？
#19 opened Aug 16, 2019 by ZHANG-SHI-CHANG
3
Does anyone reproduce the sound quality in the demo page?
#20 opened Aug 19, 2019 by WeiLi233
15
Is voice activity detection necessary for wav preprocessing？
#21 opened Aug 20, 2019 by WeiLi233
1
Downsampling process is different from that described in the paper
#22 opened Aug 22, 2019 by light1726
3
Hyperparameters for generating mel spectrogram from training .wav files
#25 opened Aug 27, 2019 by sroutray
3
AutoVC on a large scale data?
#26 opened Sep 1, 2019 by iyah4888
2
How to use this project on another dataset?
#28 opened Sep 20, 2019 by smalissa
4
confusion with speaker encoder and loss func
#29 opened Oct 2, 2019 by andylida
10
How to generate mel spectrogram
#4 opened Jun 20, 2019 by nkcdy
33
Why need original speaker embeddings concatenated with original speaker spectrogram?
#30 opened Oct 7, 2019 by nkcdy
10
Follow-up work available for viewing
#44 opened Apr 24, 2020 by auspicious3000
7
Whether the speech on each batch will be crop to a fixed length of time during training?
#48 opened May 29, 2020 by qq547276542
4
Issues with conversion of VCTK speakers using pre-trained model
#49 opened Jul 10, 2020 by gustxsr
9
F0-consistent many-to-many non-parallel voice conversion via conditional autoencoder
#50 opened Jul 14, 2020 by tebin
9
If speaker embedding is not added to the encoder input, will it affect the model effect?
#52 opened Jul 31, 2020 by qq547276542
1
Making zero-shot model
#53 opened Sep 10, 2020 by sbkim052
1
reconstruction loss won't decrease
#54 opened Sep 15, 2020 by billy800413
1
confusion about model update
#55 opened Sep 16, 2020 by jayzhu02
8
unable to apply voice conversion to long files using my trained speaker embedding
#57 opened Sep 22, 2020 by xanguera
4
question about training loss and inference performance
#61 opened Oct 23, 2020 by zzw922cn
6
Unintelligible Results on Custom Data and on the sample /Wavs from this Repo
#124 opened May 7, 2024 by jvel07
ProTip! Adding no:label will show everything without a label.