babysor / babysor/MockingBird

【长期】训练克隆特定人声音&finetune

Open
#437 18 comments 0 reactions 0 assignees View on GitHub
discussion
Dominant language
Python
Stars
36.9k
Forks
5.2k
PR merge metrics
No merged PRs in 30d

Description

[AyahaShirane](https://github.com/AyahaShirane)
专项训练参照这个视频MockingBird数据集制作教程-手把手教你克隆海子姐的声线_哔哩哔哩_bilibili
实测在已有模型基础上训练20K左右就能改变成想要的语音语调了。你如果是想要泛用型台湾口音的话,就尽可能收集更多人的数据集,否则会偏向特定某一个人的口音,而且断句和停顿似乎也会受到新数据集的影响
Reference: #380

> 作者却苦于近期精力限制只能势单力薄处理一些小的bug,也看到issue区有不少爱好与开发者想要学习或二次改造更好满足自己需求,不过比较零碎难以展开。为了让项目和AI持续可以给大家提供更多价值,共同学习,我在issue区根据不同主题创建长期交流频道,若留言人数超过20也将建立对应交流群。
> - 如何改参数,搞出更逼真的克隆效果 435
> - 如何改模型,搞出更好效果 436
> - 训练克隆特定人声音&finetune 437
> - 学术/论文讨论/训练分析 438
> - 跨语言支持 440
> - 工程化/新场景讨论(绝不做恶 & 合法合规) 439

Contributor guide

No contributing guide indexed for this repository

Research direction

No files, tests, or entry points are named. Start by reading referenced issue #380 and the linked Bilibili tutorial, then clarify the target voice, dataset, model, and fine-tuning workflow; done would require an agreed, reproducible approach documented in the issue or project materials.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.