festinuz/denoising-historical-data
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
eloimoliner 2021-08-31 18:23:56 +03:00 committed by GitHub
parent 6c886c2b53
commit 160a291bff
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -21,13 +21,13 @@ To install the environment through anaconda, follow the instructions:
conda activate historical_denoiser conda activate historical_denoiser
## Denosing Recordings ## Denosing Recordings
Run the following commands to install the pretrained weights of the neural network model: Run the following commands to install the pretrained weights of the two-stage U-Net model:
wget ckptzipurl wget ckptzipurl
unzip name.zip /experiments/trained_model unzip name.zip /experiments/trained_model
If the environment is installed correctly, you can denoise an audio file by running: If the environment is installed correctly, you can denoise an audio file by running:
bash inference.sh $filename bash inference.sh $filename
A ".wav" file with the denoised version, as well as the residual noise and the original signal in "mono" will be stored in the same directory as the input file. A ".wav" file with the denoised version, as well as the residual noise and the original signal in "mono" will be stored in the same directory as the input file.