MoonInTheRiver / MoonInTheRiver/DiffSinger

I find that there are some bad cases in F0 prediction.

Open
#39 7 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

I find that there are some bad cases in F0 prediction. I recommend people to increase 'predictor_layers' or decrease 'predictor_dropout' to enhance the ability of pitch predictor for the part of MIDI version. Also, increasing 'max_tokens' could be helpful if more powerful GPUs are available.

Originally posted by @MoonInTheRiver in https://github.com/MoonInTheRiver/DiffSinger/issues/31#issuecomment-1046585739

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.

Research direction

The issue does not name files, tests, or an entry point. Start by locating the MIDI F0 prediction configuration and reproduce the reported bad cases, then inspect the effects of predictor_layers, predictor_dropout, and max_tokens. Done means identifying a concrete correction or confirming configuration guidance.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.