babysor / babysor/MockingBird

用自己的数据集重跑了一个PPG模型 但是vc模式转换出来的效果为什么还是和readme中提供的PPG模型一样?

Open
#750 0 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

![715885fa4af2f137501057d55935628](https://user-images.githubusercontent.com/24547717/192208754-62520b53-e443-4c21-85ca-df6eb634c9ea.jpg)
![6af2d68f89b9e2becffdee98232dfb4](https://user-images.githubusercontent.com/24547717/192208766-7d427d99-4270-479d-bc4a-146782b1ec30.jpg)

我用自己的数据集跑的PPG模型 放到 ppg2mel/saved_model 目录下, demo_toolbox中 convertor 选择该模型 转换出来的结果 还是 和 readme中提供的PPG模型效果一样 没有变化

是需要 extractor 下的模型也需要重跑吗?

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by inspecting how demo_toolbox's converter selects and loads the model from ppg2mel/saved_model, then compare that path with the README model setup. Check the extractor model usage and run a conversion with the custom checkpoint; done means identifying whether the custom model is loaded and explaining the unchanged output or documenting the required model files.

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
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.