FullSubNet-plus

FullSubNet-plus copied to clipboard

small code fix needed in clipping detection

3

Hey, first of all I'd like to thank you for this great model and for sharing it on github! a small bug i found: as we know, cIRM isn't bounded...

ariel-c-verbit

Problem in loading your pre-trained checkpoint

2

I tried to use your pre-trained checkpoints, data.pkl, to inference noisy signals, but found out that there is problem in torch.load() function, indicating failure to load the .pkl file. I...

hou821

How do I create my own dataset?

3

If I want to train my own dataset, what should the structure of the dataset be, and should the names of the files in the clean and noise folders be...

QHCV

soundfile.LibsndfileError: Error opening 'xx/xx/xx.wav': File contains data in an unknown format.

8

I find a problem when training my model: soundfile.LibsndfileError: Error opening 'xx/xx/xx.wav': File contains data in an unknown format. I run this in Ubuntu I have tried many methods. What...

QHCV

Question about the output of Quick Start.

5

I follot the steps of the part Quick Start, the commands as follows:  and the program runs with no bug, but the output is weird, there is only a...

Plutoisme

About the efficiency of the MulCA module

5

I am trying to reproduce the FullSubNet+ on some speech enhancement datasets. The results are amazing, the noise suppression ability of this method is so good, and **very impressive**! :star_struck::star_struck::star_struck:...

747929791

Control the strength of Enhancement

3

Can we control the strength of enhancement of Fullsubnet by config this? 

v-nhandt21

train.toml出错

6

你好呀，我在复现你的工作的时候发现，train.toml出错了，我发现是因为snr_range = [-5,20]和metrics = ["WB_PESQ", "NB_PESQ", "STOI", "SI_SDR"]这里有问题，把这两行注释掉就没问题。我在网上没找到解决方法，请问您遇到过这样的问题吗？期待您的回复

Cagemoney

Error occurred while training the FullSubNet-Plus model

4

Hi, I encountered an error like that when training FullSubNet-Plus about 100 epoch on DNS dataset. What is the reason and how to solve it. error: File "/venv/py365/lib/python3.6/site-packages/librosa/util/utils.py", line 310,...

Yaho-b

num_groups_in_drop_band的问题

1

学长，我有个问题，num_groups_in_drop_band要是不为1，输出的掩膜维度的F不就变了嘛，后续还原语音的时候，就和原来的幅度谱大小对不上了

Morning4Star