MoonInTheRiver / MoonInTheRiver/DiffSinger
some questions about vocoder
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 4.9k
- Forks
- 826
- PR merge metrics
- No merged PRs in 30d
Description
Hi, @MoonInTheRiver, thank you for your great work. I have some questions about the training of vocoder as follows:
- In the training phase, did you use the same loss function as the HiFi-GAN vocoder model's loss function? That is, did you use other loss functions besides feature_loss, discriminator_loss and generator_loss?
- During the forward computation of the Discriminator, are there mel features input in addition to the real and predicted audio?
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
The issue names no files, tests, or entry points. It asks for clarification about vocoder training losses and discriminator inputs, so first inspect the vocoder training and discriminator implementation; done would require documented answers grounded in the existing code.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- audio-video-rtc, machine-learning
- Issue type
- Documentation
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 15/100