jagilley/demucs – Run with an API on Replicate

jagilley / demucs

Get individual instruments/vocals from any music file

Cold

Public
316 runs
T4
GitHub
License

Run with an API

Playground API Examples README Versions

Input

audio

*file

The audio file to separate

two_stems

string

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

int24

boolean

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

Default: false

float32

boolean

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

Default: false

clip_mode

string

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

Default: "rescale"

mp3

boolean

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

Default: false

mp3_bitrate

integer

The bitrate of the converted mp3.

Default: 320

shifts

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

workers

integer

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

Default: 0

split

boolean

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

Default: false

overlap

number

Overlap between the splits.

Default: 0.25

Run this model in Node.js with one line of code:

npx create-replicate --model=jagilley/demucs

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run jagilley/demucs using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "jagilley/demucs:d80c2162c80d6bd9ccb015cd49ff1ffcc0e80e8b86cae520b8157c7604378c33",
  {
    input: {
      mp3: false,
      int24: false,
      split: false,
      shifts: 1,
      float32: false,
      overlap: 0.25,
      workers: 0,
      clip_mode: "rescale",
      two_stems: "drums",
      mp3_bitrate: 320
    }
  }
);
console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run jagilley/demucs using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "jagilley/demucs:d80c2162c80d6bd9ccb015cd49ff1ffcc0e80e8b86cae520b8157c7604378c33",
    input={
        "mp3": False,
        "int24": False,
        "split": False,
        "shifts": 1,
        "float32": False,
        "overlap": 0.25,
        "workers": 0,
        "clip_mode": "rescale",
        "two_stems": "drums",
        "mp3_bitrate": 320
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run jagilley/demucs using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "d80c2162c80d6bd9ccb015cd49ff1ffcc0e80e8b86cae520b8157c7604378c33",
    "input": {
      "mp3": false,
      "int24": false,
      "split": false,
      "shifts": 1,
      "float32": false,
      "overlap": 0.25,
      "workers": 0,
      "clip_mode": "rescale",
      "two_stems": "drums",
      "mp3_bitrate": 320
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

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

Run time and cost

This model costs approximately $0.019 to run on Replicate, or 52 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 T4 GPU hardware. Predictions typically complete within 84 seconds. The predict time for this model varies significantly based on the inputs.

Readme

…

Model description

…

Intended use

…

Ethical considerations

…

Caveats and recommendations

…