MockingBird的PT模型应该如何放置?
- Dominant language
- Python
- Stars
- 36.9k
- Forks
- 5.2k
- PR merge metrics
- No merged PRs in 30d
Description
经过好几天的研究,这里必须要补充一下:即便是按照上面保姆级的教程做完后,还差了许多PYTHON插件的,但每次运行界面不成功,缺了什么都有英文提示(最后一句),本人在win7和win10都能把软件界面跑起来了,其中win7必须要下载安装魔改过3.10版python,win7下安装 requirements.txt 也会在安装到wheel时出错,这时候不要理会,直接运行toolbox软件,然后就是提示缺了什么就安装什么,最后软件提示没有在目录下找到模型,于是我又去百度网盘中下载了模型放了进去,然后终于可以把软件界面运行起来了,但是软件的三个大项,可选的东西非常之少,以下我列一下吧:
Encoder:
pretrained
Synthesizer:
ceshi
mandarin
Vocoder:
g_hifigan
pretrained
wavernn_pretrained
Griffin-Lim
但是在那个保姆级的视频教程中,至少Synthesizer: 有一大堆可选,什么 什么 rty4_56k,可选的,
在此可否麻烦大佬,把这个软件的目录树清晰列一下,那些个模型是怎么放,因为根据保姆级视频教程,放拷到哪里都根本不起作用,软件界面仍然只有上面这几项少得可怜选项呢。
Contributor guide
No contributing guide indexed for this repository
Research direction
The issue names , , and the Encoder, Synthesizer, and Vocoder model choices, but no source files or tests. Start by checking how these directories and model lists are currently discovered, then document the directory tree and placement rules. Done means users can place the models correctly and see the expected available choices.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, documentation
- Issue type
- Documentation
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100