yl4579/StarGANv2-VC

Support needed for Multiple Discriminators Implementation

Open

#68 opened on Dec 7, 2022

View on GitHub
 (2 comments) (0 reactions) (0 assignees)Python (111 forks)github user discovery
help wanted

Repository metrics

Stars
 (522 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

    Using multiple discriminators is effective, and when the model converges, the sound quality on the unseen speaker is better, and the similarity to the target speaker is better than the original one.

Originally posted by @980202006 in https://github.com/yl4579/StarGANv2-VC/issues/6#issuecomment-945602695

Contributor guide

Research direction
Explore the existing discriminator architecture in StarGANv2 VC and design a method to incorporate multiple discriminators, potentially using an ensemble or multi scale approach. Investigate how the training loss and updates would be affected.
Tech stack
pythonpytorch
Domain
ai
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
4
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Mostly clear
Prerequisites
PythonPyTorchDeep LearningGANs
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
20