How to get the predicted K_steps? Question about Boundary predict

Open
#112 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
5/5
Estimated time
Over a week
Newbie friendliness
20/100
Issue type
Documentation
Clarity
Needs clarification
Activity status
Stale
Tech stack
python
Domain
machine-learning

Research direction

Start with the linked docs/README-SVS-opencpop-cascade.md pipeline and trace how the trained fs model relates to the ds model. Investigate how Boundary predict obtains K_steps instead of using the fixed value 60. Done means documenting a supported way to obtain the predicted K_steps, if one exists.

Written by the indexing model from the issue text.

Description

Hi,
I am training a singing model following this pipeline with a different dataset.
I wonder how to get the predicted K_steps from trained fs model for ds model, rather than just use K_steps = 60 .
I have tried to find it out but failed. Could anyone give me a hand? Much thanks!

Dominant language
Python
Stars
4.9k
Forks
826
No merged PRs in 30d

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from MoonInTheRiver/DiffSinger

All issues in MoonInTheRiver/DiffSinger

Similar issues

More Python issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.