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

cjwbw /demucs:abf8fe28

Input schema

The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.

Field Type Default value Description
audio
string
Input audio
model_name
string (enum)
htdemucs

Options:

htdemucs, htdemucs_ft, htdemucs_6s, hdemucs_mmi, mdx, mdx_q, mdx_extra, mdx_extra_q

Choose a model
stem
string (enum)

Options:

vocals, bass, drums, guitar, piano, other

Only separate audio into the chosen stem and others (no_stem).
clip_mode
string (enum)
rescale

Options:

rescale, clamp

Strategy for avoiding clipping: rescaling entire signal if necessary (rescale) or hard clipping (clamp).
shifts
integer
1
Number of random shifts for equivariant stabilization.Increase separation time but improves quality for Demucs. 10 was used in the original paper
overlap
number
0.25
Overlap between the splits.
mp3_bitrate
integer
320
Bitrate of converted mp3
float32
boolean
False
Save wav output as float32 (2x bigger).
output_format
string (enum)
mp3

Options:

mp3, wav, flac

Choose the output format

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema
{'properties': {'bass': {'format': 'uri', 'title': 'Bass', 'type': 'string'},
                'drums': {'format': 'uri', 'title': 'Drums', 'type': 'string'},
                'guitar': {'format': 'uri',
                           'title': 'Guitar',
                           'type': 'string'},
                'other': {'format': 'uri', 'title': 'Other', 'type': 'string'},
                'piano': {'format': 'uri', 'title': 'Piano', 'type': 'string'},
                'vocals': {'format': 'uri',
                           'title': 'Vocals',
                           'type': 'string'}},
 'title': 'ModelOutput',
 'type': 'object'}