deezer / deezer/spleeter

Multichannel Wiener filtering is not working with the librosa backend

Open
#580 0 comments 0 reactions 0 assignees View on GitHub
bug invalid
Dominant language
Python
Stars
28.4k
Forks
3.1k
PR merge metrics
No merged PRs in 30d

Description

## Description

With the librosa backend, the Multichannel Wiener filtering option is not taken into account.

## Step to reproduce

Both the following commands will output the exact same audio files, mwf being on or off:
```bash
spleeter separate audio_example.mp3 -B librosa
spleeter separate audio_example.mp3 -B librosa --mwf
```

Contributor guide

Open the contributing guide

Research direction

Start by tracing the `spleeter separate` command and the librosa backend handling of `--mwf`. Run the two commands from the issue to confirm that their output files are identical, then follow the option through the backend until the flag affects processing. Done means multichannel Wiener filtering changes the librosa-backend output when `--mwf` is supplied.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
audio-video-rtc
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.