You're looking at a specific version of this model. Jump to the model overview.

jagilley /demucs:2996cc66

Input

*file

The audio file to separate

string

If you want to separate into two stems, enter the name of the stem here.

boolean

If you want to output 24 bit wav files, set this to true.

Default: false

boolean

If you want to output 32 bit wav files, set this to true. Keep in mind this is 2x bigger.

Default: false

string

trategy for avoiding clipping: rescaling entire signal if necessary (rescale) or hard clipping (clamp)

Default: "rescale"

boolean

If you want to convert the output wavs to mp3, set this to true.

Default: false

integer

The bitrate of the converted mp3.

Default: 320

integer

Number of random shifts for equivariant stabilization. Increase separation time but improves quality for Demucs. 10 was used in the original paper.

Default: 1

integer

Number of jobs. This can increase memory usage but will be much faster when multiple cores are available.

Default: 0

boolean

If you want to split audio in chunks, set this to true. This can use large amounts of memory.

Default: false

number

Overlap between the splits.

Default: 0.25

Output

No output yet! Press "Submit" to start a prediction.