speech-enhancement icon indicating copy to clipboard operation
speech-enhancement copied to clipboard

Published 20 hours ago • verified publisher icon nmd2k
→

Metadata

An attempt to Vietnamese speech enhencement with U-net and Unet based ResNet

Results 2 speech-enhancement issues
Sort by recently updated
recently updated
newest added

If I don't have training data that uses the default parameters, how can I enhance my speech with a custom model?

1 comment

Dear,Friends. this is your original config.py. ![image](https://user-images.githubusercontent.com/43106285/160350715-b7a4c783-18f4-4f92-877b-0024f154f6d4.png) And this is mine ![image](https://user-images.githubusercontent.com/43106285/160351007-209fa3fb-b6a2-43b1-8a0b-0598702467de.png) And I use my final .pth and the result is awful. I don't know which files need to...

WHUynl avatar WHUynl

Why should we predicting the noise instead of the clean voice?

1 comment

kimwai99 avatar kimwai99

← Metadata

19
Stars
1
Forks
Watchers

Owner

verified publisher icon nmd2k

Metadata

An attempt to Vietnamese speech enhencement with U-net and Unet based ResNet

Back