Multichannel Wiener filtering is not working with the librosa backend
- 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
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