babysor / babysor/MockingBird

求助一下 用特定的人物训练synthesizer 越训练越糟糕

Open
#591 3 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
36.9k
Forks
5.2k
PR merge metrics
No merged PRs in 30d

Description

想训练一个特定人物的synthesizer, 严格根据 **MockingBird数据集制作教程-手把手教你克隆海子姐的声线** 教程做的 数据集大概90句,社区模型换了N个,这些社区模型直接用没有问题,但是synthesizer_train了以后越来越模糊 ,训练1K左右有PLOTS图,看上去收敛很正常,但使用只有纯电音,完全不会说话了,数据集、代码仔细检查了应该没问题的 不知道什么原因 求助各位大佬

Contributor guide

No contributing guide indexed for this repository

Research direction

No source file or test is named. Start by retracing the MockingBird dataset tutorial and comparing the dataset, training configuration, plots, and checkpoints around 1K steps; done means identifying why training produces unintelligible electronic audio instead of usable speech.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
ai, 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.