You're looking at a specific version of this model. Jump to the model overview.
erickluis00 /all-in-one-audio:91323769
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 |
|---|---|---|---|
| music_input |
string
|
An audio file input to analyze.
|
|
| visualize |
boolean
|
False
|
Save visualizations
|
| sonify |
boolean
|
False
|
Save sonifications
|
| activ |
boolean
|
False
|
Save frame-level raw activations from sigmoid and softmax
|
| embed |
boolean
|
False
|
Save frame-level embeddings
|
| model |
string
(enum)
|
harmonix-all
Options: harmonix-all, harmonix-fold0, harmonix-fold1, harmonix-fold2, harmonix-fold3, harmonix-fold4, harmonix-fold5, harmonix-fold6, harmonix-fold7 |
Name of the pretrained model to use
|
| include_activations |
boolean
|
False
|
Whether to include activations in the analysis results or not.
|
| include_embeddings |
boolean
|
False
|
Whether to include embeddings in the analysis results or not.
|
| audioSeparator |
boolean
|
False
|
TEST AUDIO SEPARATOR MDX NET
|
| audioSeparatorModel |
string
|
Kim_Vocal_2.onnx
|
Name of the pretrained model to use: https://raw.githubusercontent.com/TRvlvr/application_data/main/filelists/download_checks.json | Default: Kim_Vocal_2.onnx
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'items': {'format': 'uri', 'type': 'string'},
'title': 'Output',
'type': 'array'}