rnnoise_16k

rnnoise_16k copied to clipboard

我想直接读16bit 16k的pcm进行处理，但是显示"check gain"，处理后的音频爆音，查看了作者的读取wav方法，发现使用f32读取后，值应该是【-1,1】，为什么还要在乘36728。 想问一下怎么修改才可以直接处理pcm不出错呢，谢谢

lin-sh

got stuck during the training process

2

Epoch trained for about 20 times, but got stuck during the training process and didn't continue training. What is the likely reason

liangxt2012

can i use 128 as framesize when using model , if not, how can I do it ?

4

我可以在使用模型的时候使用帧长度为128吗，我看现有的模型是使用的帧长度是160。如果在使用模型的时候使用128帧长不合适，那么需要改网络训练的帧长，重新训练吗？

zhuhao528

src下面的makefile有什么用？

1

如果你训练的时候需要生成denoise_training的可执行文件，不是只要运行./compile.sh就行呀。。。

zxj329

about the matrix size and count

3

I use denoise.c to extract features. And I changed count to 100000, so it printed 100000*75 on the screen. However when I run bin2hdf5.py , an error occurs: "cannot reshape...

xiaoqi91

how this 300 should be in 16K model even in 8K (because I want to change it to 8k ) thanks

hhetui

hk0901