babysor / babysor/MockingBird

请问让程序能正常跑起来的步骤是怎样的?

Open
#122 20 comments 0 reactions 0 assignees View on GitHub
documentation
Dominant language
Python
Stars
36.9k
Forks
5.2k
PR merge metrics
No merged PRs in 30d

Description

2.1 使用数据集自己训练合成器模型(与2.2二选一)

·下载 数据集并解压:确保您可以访问 train 文件夹中的所有音频文件(如.wav)

·进行音频和梅尔频谱图预处理: python pre.py 可以传入参数 --dataset {dataset} 支持 aidatatang_200zh, magicdata, aishell3
假如你下载的 aidatatang_200zh文件放在D盘,train文件路径为 D:\data\aidatatang_200zh\corpus\train , 你的datasets_root就是 D:\data\

·训练合成器: python synthesizer_train.py mandarin /SV2TTS/synthesizer
当您在训练文件夹 synthesizer/saved_models/ 中看到注意线显示和损失满足您的需要时,请转到启动程序一步。

**是必须要完成上面所有的步骤才能跑起来么?才能到QT5的界面么?
感谢您的回复,谢谢!**

Contributor guide

No contributing guide indexed for this repository

Research direction

Start with the setup steps and commands named in the issue: pre.py, synthesizer_train.py, and the QT5 interface startup path. Verify whether the training workflow is required for launching the interface, then document the minimum steps and the purpose of each optional path. Done means a newcomer can follow the instructions and know whether training is necessary.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
documentation
Issue type
Documentation
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.