erickluis00 / all-in-one-audio

AI Music Structure Analyzer + Stem Splitter using Demucs & Mdx-Net with Python-Audio-Separator

  • Public
  • 17.5K runs
  • L40S
  • GitHub
  • License

Input

Video Player is loading.
Current Time 00:00:000
Duration 00:00:000
Loaded: 0%
Stream Type LIVE
Remaining Time 00:00:000
 
1x
file

An audio file input to analyze.

boolean

Save visualizations

Default: false

boolean

Save sonifications

Default: false

string

Name of the pretrained model to use

Default: "harmonix-all"

boolean

Whether to include activations in the analysis results or not.

Default: false

boolean

Whether to include embeddings in the analysis results or not.

Default: false

boolean

Separate the audio into vocals and instrumental with MDX-net (best for music)

Default: false

string
Shift + Return to add a new line

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

mdx_vocals

Video Player is loading.
Current Time 00:00:000
Duration 00:00:000
Loaded: 0%
Stream Type LIVE
Remaining Time 00:00:000
 
1x

demucs_bass

Video Player is loading.
Current Time 00:00:000
Duration 00:00:000
Loaded: 0%
Stream Type LIVE
Remaining Time 00:00:000
 
1x

demucs_drums

Video Player is loading.
Current Time 00:00:000
Duration 00:00:000
Loaded: 0%
Stream Type LIVE
Remaining Time 00:00:000
 
1x

demucs_other

Video Player is loading.
Current Time 00:00:000
Duration 00:00:000
Loaded: 0%
Stream Type LIVE
Remaining Time 00:00:000
 
1x

sonification

Video Player is loading.
Current Time 00:00:000
Duration 00:00:000
Loaded: 0%
Stream Type LIVE
Remaining Time 00:00:000
 
1x

demucs_vocals

Video Player is loading.
Current Time 00:00:000
Duration 00:00:000
Loaded: 0%
Stream Type LIVE
Remaining Time 00:00:000
 
1x

visualization

visualization

mdx_instrumental

Video Player is loading.
Current Time 00:00:000
Duration 00:00:000
Loaded: 0%
Stream Type LIVE
Remaining Time 00:00:000
 
1x
Generated in

This example was created by a different version, erickluis00/all-in-one-audio:d77f3985.

Run time and cost

This model costs approximately $0.060 to run on Replicate, or 16 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 62 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.