babysor / babysor/MockingBird

一些关于生成语音时一直会有电流音的猜想

Open
#473 10 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

现在大家不管怎么优化提纯原始的人物语音,就算训练出来后loss<2.0,生成的语音也带有电流音。
会不会还是训练器本身的问题:

首先就是,当你用MockingBird GUI打开本地音频,它播放时就有几率是带有电流音;

另一个就是,在你生成的saved_models的wavs文件夹里,存放的都是训练时生成的音频,他们全都带有严重电流音,而且声音质量并没有随着step的增加而有任何改善。

希望大神能够指导一下我等小白,怎么能生成无电流音的声音

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by reproducing the electrical noise in MockingBird GUI when playing local audio, then compare it with the generated files under saved_models/wavs at different training steps. Determine whether the noise is present in the source playback, the training outputs, or both; done means identifying a reproducible cause and a focused fix or confirmed preprocessing issue.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
audio-video-rtc, machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.