RVC-Project / RVC-Project/Retrieval-based-Voice-Conversion-WebUI

New f0/pitch tracker

Open
#2,373 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
38.4k
Forks
5.3k
PR merge metrics
No merged PRs in 30d

Description

Consider using the pitch trackers from penn which might be higher quality.

NOTES:

  • Use the dev branch of that repo, according to their README.
  • The paper shows that FCNF0++ and DeepF0++ are almost equally good, without must statistical difference detected in their experiments.

[edit: I seem to recall that DeepF0++ uses less memory than FCNF0++, but it's worth checking this again]

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

Read the penn dev branch README and the linked paper first, comparing FCNF0++ and DeepF0++ for quality and memory use. Then locate the repository's existing pitch-tracker integration point and determine how the selected tracker would be evaluated; done means a chosen penn tracker is integrated and its quality and resource tradeoffs are verified.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
audio-video-rtc, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.