Status
Time
39s
Submitted
4 mo ago
Privacy
Outputs
Logs
' stroke-width='2'%3e%3ccircle stroke-opacity='.5' cx='18' cy='18' r='18'/%3e%3cpath d='M36 18c0-9.94-8.06-18-18-18'%3e%3canimateTransform attributeName='transform' type='rotate' from='0 18 18' to='360 18 18' dur='1s' repeatCount='indefinite'/%3e%3c/path%3e%3c/g%3e%3c/g%3e%3c/svg%3e){kind=small}
listening for logs...Job Inputs
model
The model to be used for audio separation. Default is "htdemucs_ft". Check the README for more information on the available models.
two_stems
Only seperate audio into stem and no_stem. the stem which is specified will be seperated from the rest of the stems.
overlap
option controls the amount of overlap between prediction windows. Default is 0.25 (i.e. 25%) which is probably fine. It can probably be reduced to 0.1 to improve a bit speed.
shifts
The number of shifts to be used. performs multiple predictions with random shifts (a.k.a the shift trick) of the input and average them. This makes prediction SHIFTS times slower. Default is 0
audio_format
The format of the audio file to be returned. Default is "wav". You can choose from "mp3", "flac" or "wav".