andreasjansson / music-inpainting-bert

Music inpainting of melody and chords

Cold

Public
8.5K runs
T4
GitHub
License

Run with an API

Playground API Examples README Versions

Prediction

andreasjansson/music-inpainting-bert:58bdc207

Model

andreasjansson/music-inpainting-bert:58bdc207

oz3dif2lijfa3ac2bkzidysbxa

Status

Succeeded

Source

Web

Hardware

–

Total duration

9.0s

Created

almost 3 years ago

Input

seed: -1
notes: c8 g4 f g.4 | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ?
tempo: "120"
chords: Cmaj7 | Cmaj7 | E-maj7 | E-maj7 | Cmaj7 | Cmaj7 | E-maj7 | E-maj7 | Gmaj7 | Gmaj7 | Fm7 | Fm7 | D-maj7 | E-maj7 | Cmaj7 | Cmaj7
sample_width: "10"
time_signature: "4"

{
  "seed": -1,
  "notes": "c8 g4 f g.4 | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ?",
  "tempo": "120",
  "chords": "Cmaj7 | Cmaj7 | E-maj7 | E-maj7 | Cmaj7 | Cmaj7 | E-maj7 | E-maj7 | Gmaj7 | Gmaj7 | Fm7 | Fm7 | D-maj7 | E-maj7 | Cmaj7 | Cmaj7",
  "sample_width": "10",
  "time_signature": "4"
}

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 andreasjansson/music-inpainting-bert using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "andreasjansson/music-inpainting-bert:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1",
  {
    input: {
      seed: -1,
      notes: "c8 g4 f g.4 | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ?",
      tempo: "120",
      chords: "Cmaj7 | Cmaj7 | E-maj7 | E-maj7 | Cmaj7 | Cmaj7 | E-maj7 | E-maj7 | Gmaj7 | Gmaj7 | Fm7 | Fm7 | D-maj7 | E-maj7 | Cmaj7 | Cmaj7",
      sample_width: "10",
      time_signature: "4"
    }
  }
);
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 andreasjansson/music-inpainting-bert using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "andreasjansson/music-inpainting-bert:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1",
    input={
        "seed": -1,
        "notes": "c8 g4 f g.4 | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ?",
        "tempo": "120",
        "chords": "Cmaj7 | Cmaj7 | E-maj7 | E-maj7 | Cmaj7 | Cmaj7 | E-maj7 | E-maj7 | Gmaj7 | Gmaj7 | Fm7 | Fm7 | D-maj7 | E-maj7 | Cmaj7 | Cmaj7",
        "sample_width": "10",
        "time_signature": "4"
    }
)
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 andreasjansson/music-inpainting-bert 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": "58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1",
    "input": {
      "seed": -1,
      "notes": "c8 g4 f g.4 | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ?",
      "tempo": "120",
      "chords": "Cmaj7 | Cmaj7 | E-maj7 | E-maj7 | Cmaj7 | Cmaj7 | E-maj7 | E-maj7 | Gmaj7 | Gmaj7 | Fm7 | Fm7 | D-maj7 | E-maj7 | Cmaj7 | Cmaj7",
      "sample_width": "10",
      "time_signature": "4"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Install Cog

brew install cog

If you don’t have Homebrew, there are other installation options available.

Pull and run andreasjansson/music-inpainting-bert using Cog (this will download the full model and run it in your local environment):

cog predict r8.im/andreasjansson/music-inpainting-bert@sha256:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1 \
  -i 'seed=-1' \
  -i 'notes="c8 g4 f g.4 | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ?"' \
  -i 'tempo="120"' \
  -i 'chords="Cmaj7 | Cmaj7 | E-maj7 | E-maj7 | Cmaj7 | Cmaj7 | E-maj7 | E-maj7 | Gmaj7 | Gmaj7 | Fm7 | Fm7 | D-maj7 | E-maj7 | Cmaj7 | Cmaj7"' \
  -i 'sample_width="10"' \
  -i 'time_signature="4"'

To learn more, take a look at the Cog documentation.

Pull and run andreasjansson/music-inpainting-bert using Docker (this will download the full model and run it in your local environment):

docker run -d -p 5000:5000 --gpus=all r8.im/andreasjansson/music-inpainting-bert@sha256:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "seed": -1,
      "notes": "c8 g4 f g.4 | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ?",
      "tempo": "120",
      "chords": "Cmaj7 | Cmaj7 | E-maj7 | E-maj7 | Cmaj7 | Cmaj7 | E-maj7 | E-maj7 | Gmaj7 | Gmaj7 | Fm7 | Fm7 | D-maj7 | E-maj7 | Cmaj7 | Cmaj7",
      "sample_width": "10",
      "time_signature": "4"
    }
  }' \
  http://localhost:5000/predictions

Output

mp3

Video Player is loading.

Current Time 00:00:000

Duration 00:00:000

Loaded: 0%

Stream Type LIVE

Remaining Time 00:00:000

midi

out.midi

score

{
  "completed_at": "2022-05-03T19:32:26.717006Z",
  "created_at": "2022-05-03T19:32:17.700984Z",
  "data_removed": false,
  "error": null,
  "id": "oz3dif2lijfa3ac2bkzidysbxa",
  "input": {
    "seed": -1,
    "notes": "c8 g4 f g.4 | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ?",
    "tempo": "120",
    "chords": "Cmaj7 | Cmaj7 | E-maj7 | E-maj7 | Cmaj7 | Cmaj7 | E-maj7 | E-maj7 | Gmaj7 | Gmaj7 | Fm7 | Fm7 | D-maj7 | E-maj7 | Cmaj7 | Cmaj7",
    "sample_width": "10",
    "time_signature": "4"
  },
  "logs": "Using seed: 41511\n0.0 10\n0.1 8\n0.2 6\n0.3 6\n0.4 5\n0.5 4\n0.6 4\n0.7 3\n0.8 2\n0.9 2\n0:0 (0/1 C4), (1/2 G4) Cmaj7 0\n0:1 (1/2 F4) Cmaj7 0\n0:2 (1/2 G4) Cmaj7 0\n3: Invalid pattern: 0\n1:0 (0/1 G4) Cmaj7 1\n1:1 (1/2 G4) Cmaj7 5\n1:2  Cmaj7 9\n2:3  Cmaj7 8\n2:0 (0/1 G4), (1/2 G4) Ebmaj7 10\n2:1 (1/2 B-4) Ebmaj7 9\n2:2 (1/2 G4) Ebmaj7 5\n3:3  Ebmaj7 5\n3:0  Ebmaj7 8\n3:1  Ebmaj7 1\n3:2  Ebmaj7 9\n4:3  Ebmaj7 10\n4:0 (0/1 C4), (1/2 G4) Cmaj7 3\n4:1 (1/2 F4) Cmaj7 6\n4:2 (1/2 G4) Cmaj7 1\n5:3 (0/1 F4) Cmaj7 2\n5:0 (0/1 G4) Cmaj7 5\n5:1 (1/2 G4) Cmaj7 8\n5:2  Cmaj7 1\n6:3 (0/1 G4) Cmaj7 6\n6:0 (0/1 G4), (1/2 G4) Ebmaj7 2\n6:1 (1/2 B-4) Ebmaj7 6\n6:2 (1/2 G4) Ebmaj7 8\n7:3  Ebmaj7 2\n7:0 (1/2 G4) Ebmaj7 4\n7:1 (1/2 B-4) Ebmaj7 4\n7:2 (1/2 G4) Ebmaj7 3\n8:3  Ebmaj7 8\n8:0 (0/1 G4) Gmaj7 9\n8:1 (1/2 G4) Gmaj7 6\n8:2 (1/2 G4) Gmaj7 2\n9:3 (0/1 G4) Gmaj7 9\n9:0 (0/1 G4) Gmaj7 4\n9:1 (1/2 G4) Gmaj7 4\n9:2 (1/2 G4) Gmaj7 10\n10:3 (0/1 G4) Gmaj7 10\n10:0 (0/1 G#4) Fm7 5\n10:1  Fm7 3\n10:2  Fm7 8\n11:3  Fm7 9\n11:0  Fm7 5\n11:1  Fm7 4\n11:2  Fm7 2\n12:3  Fm7 7\n12:0 (0/1 C4), (1/2 G4) Dbmaj7 3\n12:1 (1/2 F4) Dbmaj7 7\n12:2 (1/2 G4) Dbmaj7 6\n13:3 (0/1 G#4) Dbmaj7 10\n13:0 (0/1 B-4) Ebmaj7 7\n13:1 (1/2 G#4) Ebmaj7 3\n13:2 (1/2 G4) Ebmaj7 1\n14:3  Ebmaj7 10\n14:0 (0/1 A4) Cmaj7 4\n14:1  Cmaj7 7\n14:2  Cmaj7 6\n15:3  Cmaj7 7\n15:0 (0/1 C4) Cmaj7 1\n15:1  Cmaj7 7\n15:2 (1/2 G4) Cmaj7 2\n0 pattern\nffmpeg version 3.4.8-0ubuntu0.2 Copyright (c) 2000-2020 the FFmpeg developers\n  built with gcc 7 (Ubuntu 7.5.0-3ubuntu1~18.04)\n  configuration: --prefix=/usr --extra-version=0ubuntu0.2 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --enable-gpl --disable-stripping --enable-avresample --enable-avisynth --enable-gnutls --enable-ladspa --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librubberband --enable-librsvg --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvorbis --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzmq --enable-libzvbi --enable-omx --enable-openal --enable-opengl --enable-sdl2 --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libopencv --enable-libx264 --enable-shared\n  libavutil      55. 78.100 / 55. 78.100\n  libavcodec     57.107.100 / 57.107.100\n  libavformat    57. 83.100 / 57. 83.100\n  libavdevice    57. 10.100 / 57. 10.100\n  libavfilter     6.107.100 /  6.107.100\n  libavresample   3.  7.  0 /  3.  7.  0\n  libswscale      4.  8.100 /  4.  8.100\n  libswresample   2.  9.100 /  2.  9.100\n  libpostproc    54.  7.100 / 54.  7.100\nGuessed Channel Layout for Input Stream #0.0 : mono\nInput #0, wav, from '/tmp/tmpnuth5955/out.wav':\n  Duration: 00:00:32.50, bitrate: 2822 kb/s\n    Stream #0:0: Audio: pcm_f64le ([3][0][0][0] / 0x0003), 44100 Hz, mono, dbl, 2822 kb/s\nStream mapping:\n  Stream #0:0 -> #0:0 (pcm_f64le (native) -> mp3 (libmp3lame))\nPress [q] to stop, [?] for help\nOutput #0, mp3, to '/tmp/tmpnuth5955/out.mp3':\n  Metadata:\n    TSSE            : Lavf57.83.100\n    Stream #0:0: Audio: mp3 (libmp3lame), 44100 Hz, mono, fltp\n    Metadata:\n      encoder         : Lavc57.107.100 libmp3lame\nsize=     252kB time=00:00:32.15 bitrate=  64.1kbits/s speed=72.2x\nvideo:0kB audio:251kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.088168%\nLY output to `/tmp/tmpnuth5955/score.ly'...\nChanging working directory to: `/tmp/tmpnuth5955'\nProcessing `/tmp/tmpnuth5955/score.ly'\nParsing...\nInterpreting music...[8][16][16]\nPreprocessing graphical objects...\nInterpreting music...\nMIDI output to `score.midi'...\nFinding the ideal number of pages...\nFitting music on 1 page...\nDrawing systems...\nLayout output to `score.ps'...\nConverting to PNG...\nSuccess: compilation successfully completed",
  "metrics": {
    "predict_time": 8.793683,
    "total_time": 9.016022
  },
  "output": {
    "mp3": "https://replicate.delivery/mgxm/f1a45940-4144-47ce-9695-e994c47ad143/out.mp3",
    "midi": "https://replicate.delivery/mgxm/f9130a4a-ed2a-4a6a-91d0-bc9cba1df39f/out.midi",
    "score": "https://replicate.delivery/mgxm/08c47365-c531-403b-8a27-633229bd5932/score.png"
  },
  "started_at": "2022-05-03T19:32:17.923323Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/oz3dif2lijfa3ac2bkzidysbxa",
    "cancel": "https://api.replicate.com/v1/predictions/oz3dif2lijfa3ac2bkzidysbxa/cancel"
  },
  "version": "58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1"
}

Generated in

8.8 seconds

Tweak it ShareReport

Using seed: 41511
0.0 10
0.1 8
0.2 6
0.3 6
0.4 5
0.5 4
0.6 4
0.7 3
0.8 2
0.9 2
0:0 (0/1 C4), (1/2 G4) Cmaj7 0
0:1 (1/2 F4) Cmaj7 0
0:2 (1/2 G4) Cmaj7 0
3: Invalid pattern: 0
1:0 (0/1 G4) Cmaj7 1
1:1 (1/2 G4) Cmaj7 5
1:2  Cmaj7 9
2:3  Cmaj7 8
2:0 (0/1 G4), (1/2 G4) Ebmaj7 10
2:1 (1/2 B-4) Ebmaj7 9
2:2 (1/2 G4) Ebmaj7 5
3:3  Ebmaj7 5
3:0  Ebmaj7 8
3:1  Ebmaj7 1
3:2  Ebmaj7 9
4:3  Ebmaj7 10
4:0 (0/1 C4), (1/2 G4) Cmaj7 3
4:1 (1/2 F4) Cmaj7 6
4:2 (1/2 G4) Cmaj7 1
5:3 (0/1 F4) Cmaj7 2
5:0 (0/1 G4) Cmaj7 5
5:1 (1/2 G4) Cmaj7 8
5:2  Cmaj7 1
6:3 (0/1 G4) Cmaj7 6
6:0 (0/1 G4), (1/2 G4) Ebmaj7 2
6:1 (1/2 B-4) Ebmaj7 6
6:2 (1/2 G4) Ebmaj7 8
7:3  Ebmaj7 2
7:0 (1/2 G4) Ebmaj7 4
7:1 (1/2 B-4) Ebmaj7 4
7:2 (1/2 G4) Ebmaj7 3
8:3  Ebmaj7 8
8:0 (0/1 G4) Gmaj7 9
8:1 (1/2 G4) Gmaj7 6
8:2 (1/2 G4) Gmaj7 2
9:3 (0/1 G4) Gmaj7 9
9:0 (0/1 G4) Gmaj7 4
9:1 (1/2 G4) Gmaj7 4
9:2 (1/2 G4) Gmaj7 10
10:3 (0/1 G4) Gmaj7 10
10:0 (0/1 G#4) Fm7 5
10:1  Fm7 3
10:2  Fm7 8
11:3  Fm7 9
11:0  Fm7 5
11:1  Fm7 4
11:2  Fm7 2
12:3  Fm7 7
12:0 (0/1 C4), (1/2 G4) Dbmaj7 3
12:1 (1/2 F4) Dbmaj7 7
12:2 (1/2 G4) Dbmaj7 6
13:3 (0/1 G#4) Dbmaj7 10
13:0 (0/1 B-4) Ebmaj7 7
13:1 (1/2 G#4) Ebmaj7 3
13:2 (1/2 G4) Ebmaj7 1
14:3  Ebmaj7 10
14:0 (0/1 A4) Cmaj7 4
14:1  Cmaj7 7
14:2  Cmaj7 6
15:3  Cmaj7 7
15:0 (0/1 C4) Cmaj7 1
15:1  Cmaj7 7
15:2 (1/2 G4) Cmaj7 2
0 pattern
ffmpeg version 3.4.8-0ubuntu0.2 Copyright (c) 2000-2020 the FFmpeg developers
  built with gcc 7 (Ubuntu 7.5.0-3ubuntu1~18.04)
  configuration: --prefix=/usr --extra-version=0ubuntu0.2 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --enable-gpl --disable-stripping --enable-avresample --enable-avisynth --enable-gnutls --enable-ladspa --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librubberband --enable-librsvg --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvorbis --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzmq --enable-libzvbi --enable-omx --enable-openal --enable-opengl --enable-sdl2 --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libopencv --enable-libx264 --enable-shared
  libavutil      55. 78.100 / 55. 78.100
  libavcodec     57.107.100 / 57.107.100
  libavformat    57. 83.100 / 57. 83.100
  libavdevice    57. 10.100 / 57. 10.100
  libavfilter     6.107.100 /  6.107.100
  libavresample   3.  7.  0 /  3.  7.  0
  libswscale      4.  8.100 /  4.  8.100
  libswresample   2.  9.100 /  2.  9.100
  libpostproc    54.  7.100 / 54.  7.100
Guessed Channel Layout for Input Stream #0.0 : mono
Input #0, wav, from '/tmp/tmpnuth5955/out.wav':
  Duration: 00:00:32.50, bitrate: 2822 kb/s
    Stream #0:0: Audio: pcm_f64le ([3][0][0][0] / 0x0003), 44100 Hz, mono, dbl, 2822 kb/s
Stream mapping:
  Stream #0:0 -> #0:0 (pcm_f64le (native) -> mp3 (libmp3lame))
Press [q] to stop, [?] for help
Output #0, mp3, to '/tmp/tmpnuth5955/out.mp3':
  Metadata:
    TSSE            : Lavf57.83.100
    Stream #0:0: Audio: mp3 (libmp3lame), 44100 Hz, mono, fltp
    Metadata:
      encoder         : Lavc57.107.100 libmp3lame
size=     252kB time=00:00:32.15 bitrate=  64.1kbits/s speed=72.2x
video:0kB audio:251kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.088168%
LY output to `/tmp/tmpnuth5955/score.ly'...
Changing working directory to: `/tmp/tmpnuth5955'
Processing `/tmp/tmpnuth5955/score.ly'
Parsing...
Interpreting music...[8][16][16]
Preprocessing graphical objects...
Interpreting music...
MIDI output to `score.midi'...
Finding the ideal number of pages...
Fitting music on 1 page...
Drawing systems...
Layout output to `score.ps'...
Converting to PNG...
Success: compilation successfully completed

Prediction

andreasjansson/music-inpainting-bert:58bdc207

Model

andreasjansson/music-inpainting-bert:58bdc207

24zmd4jb5rbv7c3y4vckxrkmv4

Status

Succeeded

Source

Web

Hardware

–

Total duration

5.6s

Created

almost 3 years ago

Input

seed: -1
notes: c.8 c16 c4 G | e.8 e16 e4 c | c.8 e16 g.4 g8 | f.8 e16 d2 | d.8 e16 f4 f | e.8 d16 e4 c | c.8 e16 d4 G | B.8 d16 c2 |
tempo: "90"
chords: C | ? | ? | ? | ? | ? | ? | C
sample_width: "100"
time_signature: "3"

{
  "seed": -1,
  "notes": "c.8 c16 c4 G | e.8 e16 e4 c | c.8 e16 g.4 g8 | f.8 e16 d2 | d.8 e16 f4 f | e.8 d16 e4 c | c.8 e16 d4 G | B.8 d16 c2 |",
  "tempo": "90",
  "chords": "C | ? | ? | ? | ? | ? | ? | C",
  "sample_width": "100",
  "time_signature": "3"
}

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 andreasjansson/music-inpainting-bert using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "andreasjansson/music-inpainting-bert:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1",
  {
    input: {
      seed: -1,
      notes: "c.8 c16 c4 G | e.8 e16 e4 c | c.8 e16 g.4 g8 | f.8 e16 d2 | d.8 e16 f4 f | e.8 d16 e4 c | c.8 e16 d4 G | B.8 d16 c2 |",
      tempo: "90",
      chords: "C | ? | ? | ? | ? | ? | ? | C",
      sample_width: "100",
      time_signature: "3"
    }
  }
);
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 andreasjansson/music-inpainting-bert using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "andreasjansson/music-inpainting-bert:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1",
    input={
        "seed": -1,
        "notes": "c.8 c16 c4 G | e.8 e16 e4 c | c.8 e16 g.4 g8 | f.8 e16 d2 | d.8 e16 f4 f | e.8 d16 e4 c | c.8 e16 d4 G | B.8 d16 c2 |",
        "tempo": "90",
        "chords": "C | ? | ? | ? | ? | ? | ? | C",
        "sample_width": "100",
        "time_signature": "3"
    }
)
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 andreasjansson/music-inpainting-bert 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": "58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1",
    "input": {
      "seed": -1,
      "notes": "c.8 c16 c4 G | e.8 e16 e4 c | c.8 e16 g.4 g8 | f.8 e16 d2 | d.8 e16 f4 f | e.8 d16 e4 c | c.8 e16 d4 G | B.8 d16 c2 |",
      "tempo": "90",
      "chords": "C | ? | ? | ? | ? | ? | ? | C",
      "sample_width": "100",
      "time_signature": "3"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Install Cog

brew install cog

If you don’t have Homebrew, there are other installation options available.

Pull and run andreasjansson/music-inpainting-bert using Cog (this will download the full model and run it in your local environment):

cog predict r8.im/andreasjansson/music-inpainting-bert@sha256:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1 \
  -i 'seed=-1' \
  -i 'notes="c.8 c16 c4 G | e.8 e16 e4 c | c.8 e16 g.4 g8 | f.8 e16 d2 | d.8 e16 f4 f | e.8 d16 e4 c | c.8 e16 d4 G | B.8 d16 c2 |"' \
  -i 'tempo="90"' \
  -i 'chords="C | ? | ? | ? | ? | ? | ? | C"' \
  -i 'sample_width="100"' \
  -i 'time_signature="3"'

To learn more, take a look at the Cog documentation.

Pull and run andreasjansson/music-inpainting-bert using Docker (this will download the full model and run it in your local environment):

docker run -d -p 5000:5000 --gpus=all r8.im/andreasjansson/music-inpainting-bert@sha256:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "seed": -1,
      "notes": "c.8 c16 c4 G | e.8 e16 e4 c | c.8 e16 g.4 g8 | f.8 e16 d2 | d.8 e16 f4 f | e.8 d16 e4 c | c.8 e16 d4 G | B.8 d16 c2 |",
      "tempo": "90",
      "chords": "C | ? | ? | ? | ? | ? | ? | C",
      "sample_width": "100",
      "time_signature": "3"
    }
  }' \
  http://localhost:5000/predictions

Output

mp3

Video Player is loading.

Current Time 00:00:000

Duration 00:00:000

Loaded: 0%

Stream Type LIVE

Remaining Time 00:00:000

midi

out.midi

score

{
  "completed_at": "2022-05-03T19:34:10.862035Z",
  "created_at": "2022-05-03T19:34:05.259038Z",
  "data_removed": false,
  "error": null,
  "id": "24zmd4jb5rbv7c3y4vckxrkmv4",
  "input": {
    "seed": -1,
    "notes": "c.8 c16 c4 G | e.8 e16 e4 c | c.8 e16 g.4 g8 | f.8 e16 d2 | d.8 e16 f4 f | e.8 d16 e4 c | c.8 e16 d4 G | B.8 d16 c2 |",
    "tempo": "90",
    "chords": "C | ? | ? | ? | ? | ? | ? | C",
    "sample_width": "100",
    "time_signature": "3"
  },
  "logs": "Using seed: 9849\n0.0 10\n0.1 8\n0.2 6\n0.3 6\n0.4 5\n0.5 4\n0.6 4\n0.7 3\n0.8 2\n0.9 2\n0:0 (0/1 C4), (3/4 C4) C/C 0\n0:1 (0/1 C4) C/C 0\n1:2 (0/1 G3) C/C 0\n1:0 (0/1 E4), (3/4 E4) F/F 0\n1:1 (0/1 E4) C/C 0\n2:2 (0/1 C4) F/F 0\n2:0 (0/1 C4), (3/4 E4) F/F 0\n2:1 (0/1 G4) Bb/Bb 0\n3:2 (1/2 G4) Bb/Bb 0\n3:0 (0/1 F4), (3/4 E4) Bb/Bb 0\n3:1 (0/1 D4) Bb/Bb 0\n4:2  Bb/Bb 0\n4:0 (0/1 D4), (3/4 E4) Bb/Bb 0\n4:1 (0/1 F4) Bb/Bb 0\n5:2 (0/1 F4) Bb/Bb 0\n5:0 (0/1 E4), (3/4 D4) F/F 0\n5:1 (0/1 E4) F/F 0\n6:2 (0/1 C4) F/F 0\n6:0 (0/1 C4), (3/4 E4) F/F 0\n6:1 (0/1 D4) Bb/Bb 0\n7:2 (0/1 G3) Bb/Bb 0\n7:0 (0/1 B3), (3/4 D4) C/C 0\n7:1 (0/1 C4) C/C 0\nffmpeg version 3.4.8-0ubuntu0.2 Copyright (c) 2000-2020 the FFmpeg developers\n  built with gcc 7 (Ubuntu 7.5.0-3ubuntu1~18.04)\n  configuration: --prefix=/usr --extra-version=0ubuntu0.2 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --enable-gpl --disable-stripping --enable-avresample --enable-avisynth --enable-gnutls --enable-ladspa --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librubberband --enable-librsvg --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvorbis --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzmq --enable-libzvbi --enable-omx --enable-openal --enable-opengl --enable-sdl2 --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libopencv --enable-libx264 --enable-shared\n  libavutil      55. 78.100 / 55. 78.100\n  libavcodec     57.107.100 / 57.107.100\n  libavformat    57. 83.100 / 57. 83.100\n  libavdevice    57. 10.100 / 57. 10.100\n  libavfilter     6.107.100 /  6.107.100\n  libavresample   3.  7.  0 /  3.  7.  0\n  libswscale      4.  8.100 /  4.  8.100\n  libswresample   2.  9.100 /  2.  9.100\n  libpostproc    54.  7.100 / 54.  7.100\nGuessed Channel Layout for Input Stream #0.0 : mono\nInput #0, wav, from '/tmp/tmpm02acne5/out.wav':\n  Duration: 00:00:16.33, bitrate: 2822 kb/s\n    Stream #0:0: Audio: pcm_f64le ([3][0][0][0] / 0x0003), 44100 Hz, mono, dbl, 2822 kb/s\nStream mapping:\n  Stream #0:0 -> #0:0 (pcm_f64le (native) -> mp3 (libmp3lame))\nPress [q] to stop, [?] for help\nOutput #0, mp3, to '/tmp/tmpm02acne5/out.mp3':\n  Metadata:\n    TSSE            : Lavf57.83.100\n    Stream #0:0: Audio: mp3 (libmp3lame), 44100 Hz, mono, fltp\n    Metadata:\n      encoder         : Lavc57.107.100 libmp3lame\nsize=     126kB time=00:00:16.00 bitrate=  64.3kbits/s speed=75.6x\nvideo:0kB audio:125kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.176911%\nLY output to `/tmp/tmpm02acne5/score.ly'...\nChanging working directory to: `/tmp/tmpm02acne5'\nProcessing `/tmp/tmpm02acne5/score.ly'\nParsing...\nInterpreting music...[8][8]\nPreprocessing graphical objects...\nInterpreting music...\nMIDI output to `score.midi'...\nFinding the ideal number of pages...\nFitting music on 1 page...\nDrawing systems...\nLayout output to `score.ps'...\nConverting to PNG...\nSuccess: compilation successfully completed",
  "metrics": {
    "predict_time": 5.421096,
    "total_time": 5.602997
  },
  "output": {
    "mp3": "https://replicate.delivery/mgxm/3b97edde-20c5-4133-bcc0-2bf1f32fe4bc/out.mp3",
    "midi": "https://replicate.delivery/mgxm/617b85ed-8055-4c6d-a051-798234d42dc7/out.midi",
    "score": "https://replicate.delivery/mgxm/be244d4a-31f0-4eea-b028-3a23158b4c11/score.png"
  },
  "started_at": "2022-05-03T19:34:05.440939Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/24zmd4jb5rbv7c3y4vckxrkmv4",
    "cancel": "https://api.replicate.com/v1/predictions/24zmd4jb5rbv7c3y4vckxrkmv4/cancel"
  },
  "version": "58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1"
}

Generated in

5.4 seconds

Tweak it ShareReport

Using seed: 9849
0.0 10
0.1 8
0.2 6
0.3 6
0.4 5
0.5 4
0.6 4
0.7 3
0.8 2
0.9 2
0:0 (0/1 C4), (3/4 C4) C/C 0
0:1 (0/1 C4) C/C 0
1:2 (0/1 G3) C/C 0
1:0 (0/1 E4), (3/4 E4) F/F 0
1:1 (0/1 E4) C/C 0
2:2 (0/1 C4) F/F 0
2:0 (0/1 C4), (3/4 E4) F/F 0
2:1 (0/1 G4) Bb/Bb 0
3:2 (1/2 G4) Bb/Bb 0
3:0 (0/1 F4), (3/4 E4) Bb/Bb 0
3:1 (0/1 D4) Bb/Bb 0
4:2  Bb/Bb 0
4:0 (0/1 D4), (3/4 E4) Bb/Bb 0
4:1 (0/1 F4) Bb/Bb 0
5:2 (0/1 F4) Bb/Bb 0
5:0 (0/1 E4), (3/4 D4) F/F 0
5:1 (0/1 E4) F/F 0
6:2 (0/1 C4) F/F 0
6:0 (0/1 C4), (3/4 E4) F/F 0
6:1 (0/1 D4) Bb/Bb 0
7:2 (0/1 G3) Bb/Bb 0
7:0 (0/1 B3), (3/4 D4) C/C 0
7:1 (0/1 C4) C/C 0
ffmpeg version 3.4.8-0ubuntu0.2 Copyright (c) 2000-2020 the FFmpeg developers
  built with gcc 7 (Ubuntu 7.5.0-3ubuntu1~18.04)
  configuration: --prefix=/usr --extra-version=0ubuntu0.2 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --enable-gpl --disable-stripping --enable-avresample --enable-avisynth --enable-gnutls --enable-ladspa --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librubberband --enable-librsvg --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvorbis --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzmq --enable-libzvbi --enable-omx --enable-openal --enable-opengl --enable-sdl2 --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libopencv --enable-libx264 --enable-shared
  libavutil      55. 78.100 / 55. 78.100
  libavcodec     57.107.100 / 57.107.100
  libavformat    57. 83.100 / 57. 83.100
  libavdevice    57. 10.100 / 57. 10.100
  libavfilter     6.107.100 /  6.107.100
  libavresample   3.  7.  0 /  3.  7.  0
  libswscale      4.  8.100 /  4.  8.100
  libswresample   2.  9.100 /  2.  9.100
  libpostproc    54.  7.100 / 54.  7.100
Guessed Channel Layout for Input Stream #0.0 : mono
Input #0, wav, from '/tmp/tmpm02acne5/out.wav':
  Duration: 00:00:16.33, bitrate: 2822 kb/s
    Stream #0:0: Audio: pcm_f64le ([3][0][0][0] / 0x0003), 44100 Hz, mono, dbl, 2822 kb/s
Stream mapping:
  Stream #0:0 -> #0:0 (pcm_f64le (native) -> mp3 (libmp3lame))
Press [q] to stop, [?] for help
Output #0, mp3, to '/tmp/tmpm02acne5/out.mp3':
  Metadata:
    TSSE            : Lavf57.83.100
    Stream #0:0: Audio: mp3 (libmp3lame), 44100 Hz, mono, fltp
    Metadata:
      encoder         : Lavc57.107.100 libmp3lame
size=     126kB time=00:00:16.00 bitrate=  64.3kbits/s speed=75.6x
video:0kB audio:125kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.176911%
LY output to `/tmp/tmpm02acne5/score.ly'...
Changing working directory to: `/tmp/tmpm02acne5'
Processing `/tmp/tmpm02acne5/score.ly'
Parsing...
Interpreting music...[8][8]
Preprocessing graphical objects...
Interpreting music...
MIDI output to `score.midi'...
Finding the ideal number of pages...
Fitting music on 1 page...
Drawing systems...
Layout output to `score.ps'...
Converting to PNG...
Success: compilation successfully completed

Prediction

andreasjansson/music-inpainting-bert:58bdc207

Model

andreasjansson/music-inpainting-bert:58bdc207

zujeyvjiqzgwldwk4nkflb2jzq

Status

Succeeded

Source

Web

Hardware

–

Total duration

6.3s

Created

almost 3 years ago

Input

seed: -1
notes: c.4 c8 c4 G | A A G2 | e.4 e8 d4 d | ? | ? | ? | ? | ?
tempo: "120"
chords: C | ? | ? | ? | ? | ? | ? | ?
sample_width: "10"
time_signature: "4"

{
  "seed": -1,
  "notes": "c.4 c8 c4 G | A A G2 | e.4 e8 d4 d | ? | ? | ? | ? | ?",
  "tempo": "120",
  "chords": "C | ? | ? | ? | ? | ? | ? | ?",
  "sample_width": "10",
  "time_signature": "4"
}

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 andreasjansson/music-inpainting-bert using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "andreasjansson/music-inpainting-bert:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1",
  {
    input: {
      seed: -1,
      notes: "c.4 c8 c4 G | A A G2 | e.4 e8 d4 d | ? | ? | ? | ? | ?",
      tempo: "120",
      chords: "C | ? | ? | ? | ? | ? | ? | ?",
      sample_width: "10",
      time_signature: "4"
    }
  }
);
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 andreasjansson/music-inpainting-bert using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "andreasjansson/music-inpainting-bert:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1",
    input={
        "seed": -1,
        "notes": "c.4 c8 c4 G | A A G2 | e.4 e8 d4 d | ? | ? | ? | ? | ?",
        "tempo": "120",
        "chords": "C | ? | ? | ? | ? | ? | ? | ?",
        "sample_width": "10",
        "time_signature": "4"
    }
)
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 andreasjansson/music-inpainting-bert 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": "58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1",
    "input": {
      "seed": -1,
      "notes": "c.4 c8 c4 G | A A G2 | e.4 e8 d4 d | ? | ? | ? | ? | ?",
      "tempo": "120",
      "chords": "C | ? | ? | ? | ? | ? | ? | ?",
      "sample_width": "10",
      "time_signature": "4"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Install Cog

brew install cog

If you don’t have Homebrew, there are other installation options available.

Pull and run andreasjansson/music-inpainting-bert using Cog (this will download the full model and run it in your local environment):

cog predict r8.im/andreasjansson/music-inpainting-bert@sha256:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1 \
  -i 'seed=-1' \
  -i 'notes="c.4 c8 c4 G | A A G2 | e.4 e8 d4 d | ? | ? | ? | ? | ?"' \
  -i 'tempo="120"' \
  -i 'chords="C | ? | ? | ? | ? | ? | ? | ?"' \
  -i 'sample_width="10"' \
  -i 'time_signature="4"'

To learn more, take a look at the Cog documentation.

Pull and run andreasjansson/music-inpainting-bert using Docker (this will download the full model and run it in your local environment):

docker run -d -p 5000:5000 --gpus=all r8.im/andreasjansson/music-inpainting-bert@sha256:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "seed": -1,
      "notes": "c.4 c8 c4 G | A A G2 | e.4 e8 d4 d | ? | ? | ? | ? | ?",
      "tempo": "120",
      "chords": "C | ? | ? | ? | ? | ? | ? | ?",
      "sample_width": "10",
      "time_signature": "4"
    }
  }' \
  http://localhost:5000/predictions

Output

mp3

Video Player is loading.

Current Time 00:00:000

Duration 00:00:000

Loaded: 0%

Stream Type LIVE

Remaining Time 00:00:000

midi

out.midi

score

{
  "completed_at": "2022-05-03T19:35:31.260007Z",
  "created_at": "2022-05-03T19:35:24.996347Z",
  "data_removed": false,
  "error": null,
  "id": "zujeyvjiqzgwldwk4nkflb2jzq",
  "input": {
    "seed": -1,
    "notes": "c.4 c8 c4 G | A A G2 | e.4 e8 d4 d | ? | ? | ? | ? | ?",
    "tempo": "120",
    "chords": "C | ? | ? | ? | ? | ? | ? | ?",
    "sample_width": "10",
    "time_signature": "4"
  },
  "logs": "Using seed: 9630\n0.0 10\n0.0 10\n0.1 8\n0.1 8\n0.2 6\n0.2 6\n0.3 6\n0.3 6\n0.4 5\n0.4 5\n0.5 4\n0.5 4\n0.6 4\n0.6 4\n0.7 3\n0.7 3\n0.8 2\n0.8 2\n0.9 2\n0.9 2\n0:0 (0/1 C4) C/C 0\n0:1 (1/2 C4) C/C 0\n0:2 (0/1 C4) C/C 0\n1:3 (0/1 G3) C/C 0\n1:0 (0/1 A3) G7 0\n1:1 (0/1 A3) G7 0\n1:2 (0/1 G3) G7 0\n2:3  G7 0\n2:0 (0/1 E4) C/C 0\n2:1 (1/2 E4) C/C 0\n2:2 (0/1 D4) G7 0\n3:3 (0/1 D4) G7 0\n3:0 (0/1 G3) G7 2\n3:1 (0/1 G3) Dm7 6\n3:2 (0/1 G3) G7 7\n4:3  G7 4\n4:0 (0/1 G4) Dm7 1\n4:1 (1/2 A4) Dm7 10\n4:2 (0/1 G4) Dm7 5\n5:3 (0/1 F4) Dm7 8\n5:0 (0/1 A3) G7 8\n5:1 (0/1 A3) G7 2\n5:2 (0/1 G3) G7 1\n6:3  G7 3\n6:0 (0/1 E4) Dm7 9\n6:1 (1/2 E4) Dm7 6\n6:2 (0/1 D4) Dm7 4\n7:3 (0/1 D4) G7 5\n7:0 (0/1 A3) Dm7 7\n7:1 (0/1 C4) F/F 10\n7:2 (0/1 G3) G7 9\nffmpeg version 3.4.8-0ubuntu0.2 Copyright (c) 2000-2020 the FFmpeg developers\n  built with gcc 7 (Ubuntu 7.5.0-3ubuntu1~18.04)\n  configuration: --prefix=/usr --extra-version=0ubuntu0.2 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --enable-gpl --disable-stripping --enable-avresample --enable-avisynth --enable-gnutls --enable-ladspa --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librubberband --enable-librsvg --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvorbis --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzmq --enable-libzvbi --enable-omx --enable-openal --enable-opengl --enable-sdl2 --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libopencv --enable-libx264 --enable-shared\n  libavutil      55. 78.100 / 55. 78.100\n  libavcodec     57.107.100 / 57.107.100\n  libavformat    57. 83.100 / 57. 83.100\n  libavdevice    57. 10.100 / 57. 10.100\n  libavfilter     6.107.100 /  6.107.100\n  libavresample   3.  7.  0 /  3.  7.  0\n  libswscale      4.  8.100 /  4.  8.100\n  libswresample   2.  9.100 /  2.  9.100\n  libpostproc    54.  7.100 / 54.  7.100\nGuessed Channel Layout for Input Stream #0.0 : mono\nInput #0, wav, from '/tmp/tmpk1yxuube/out.wav':\n  Duration: 00:00:16.50, bitrate: 2822 kb/s\n    Stream #0:0: Audio: pcm_f64le ([3][0][0][0] / 0x0003), 44100 Hz, mono, dbl, 2822 kb/s\nStream mapping:\n  Stream #0:0 -> #0:0 (pcm_f64le (native) -> mp3 (libmp3lame))\nPress [q] to stop, [?] for help\nOutput #0, mp3, to '/tmp/tmpk1yxuube/out.mp3':\n  Metadata:\n    TSSE            : Lavf57.83.100\n    Stream #0:0: Audio: mp3 (libmp3lame), 44100 Hz, mono, fltp\n    Metadata:\n      encoder         : Lavc57.107.100 libmp3lame\nsize=     127kB time=00:00:16.13 bitrate=  64.2kbits/s speed=66.9x\nvideo:0kB audio:126kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.175482%\nLY output to `/tmp/tmpk1yxuube/score.ly'...\nChanging working directory to: `/tmp/tmpk1yxuube'\nProcessing `/tmp/tmpk1yxuube/score.ly'\nParsing...\nInterpreting music...[8][8]\nPreprocessing graphical objects...\nInterpreting music...\nMIDI output to `score.midi'...\nFinding the ideal number of pages...\nFitting music on 1 page...\nDrawing systems...\nLayout output to `score.ps'...\nConverting to PNG...\nSuccess: compilation successfully completed",
  "metrics": {
    "predict_time": 6.05063,
    "total_time": 6.26366
  },
  "output": {
    "mp3": "https://replicate.delivery/mgxm/b21c3fb5-0a4e-4187-99a7-7b1432de40f5/out.mp3",
    "midi": "https://replicate.delivery/mgxm/895421f0-8471-4560-8dd1-a8a05f868948/out.midi",
    "score": "https://replicate.delivery/mgxm/f8c4fd60-d95b-4ad1-b432-09e0b53494ca/score.png"
  },
  "started_at": "2022-05-03T19:35:25.209377Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/zujeyvjiqzgwldwk4nkflb2jzq",
    "cancel": "https://api.replicate.com/v1/predictions/zujeyvjiqzgwldwk4nkflb2jzq/cancel"
  },
  "version": "58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1"
}

Generated in

6.1 seconds

Tweak it ShareReport

Using seed: 9630
0.0 10
0.0 10
0.1 8
0.1 8
0.2 6
0.2 6
0.3 6
0.3 6
0.4 5
0.4 5
0.5 4
0.5 4
0.6 4
0.6 4
0.7 3
0.7 3
0.8 2
0.8 2
0.9 2
0.9 2
0:0 (0/1 C4) C/C 0
0:1 (1/2 C4) C/C 0
0:2 (0/1 C4) C/C 0
1:3 (0/1 G3) C/C 0
1:0 (0/1 A3) G7 0
1:1 (0/1 A3) G7 0
1:2 (0/1 G3) G7 0
2:3  G7 0
2:0 (0/1 E4) C/C 0
2:1 (1/2 E4) C/C 0
2:2 (0/1 D4) G7 0
3:3 (0/1 D4) G7 0
3:0 (0/1 G3) G7 2
3:1 (0/1 G3) Dm7 6
3:2 (0/1 G3) G7 7
4:3  G7 4
4:0 (0/1 G4) Dm7 1
4:1 (1/2 A4) Dm7 10
4:2 (0/1 G4) Dm7 5
5:3 (0/1 F4) Dm7 8
5:0 (0/1 A3) G7 8
5:1 (0/1 A3) G7 2
5:2 (0/1 G3) G7 1
6:3  G7 3
6:0 (0/1 E4) Dm7 9
6:1 (1/2 E4) Dm7 6
6:2 (0/1 D4) Dm7 4
7:3 (0/1 D4) G7 5
7:0 (0/1 A3) Dm7 7
7:1 (0/1 C4) F/F 10
7:2 (0/1 G3) G7 9
ffmpeg version 3.4.8-0ubuntu0.2 Copyright (c) 2000-2020 the FFmpeg developers
  built with gcc 7 (Ubuntu 7.5.0-3ubuntu1~18.04)
  configuration: --prefix=/usr --extra-version=0ubuntu0.2 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --enable-gpl --disable-stripping --enable-avresample --enable-avisynth --enable-gnutls --enable-ladspa --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librubberband --enable-librsvg --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvorbis --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzmq --enable-libzvbi --enable-omx --enable-openal --enable-opengl --enable-sdl2 --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libopencv --enable-libx264 --enable-shared
  libavutil      55. 78.100 / 55. 78.100
  libavcodec     57.107.100 / 57.107.100
  libavformat    57. 83.100 / 57. 83.100
  libavdevice    57. 10.100 / 57. 10.100
  libavfilter     6.107.100 /  6.107.100
  libavresample   3.  7.  0 /  3.  7.  0
  libswscale      4.  8.100 /  4.  8.100
  libswresample   2.  9.100 /  2.  9.100
  libpostproc    54.  7.100 / 54.  7.100
Guessed Channel Layout for Input Stream #0.0 : mono
Input #0, wav, from '/tmp/tmpk1yxuube/out.wav':
  Duration: 00:00:16.50, bitrate: 2822 kb/s
    Stream #0:0: Audio: pcm_f64le ([3][0][0][0] / 0x0003), 44100 Hz, mono, dbl, 2822 kb/s
Stream mapping:
  Stream #0:0 -> #0:0 (pcm_f64le (native) -> mp3 (libmp3lame))
Press [q] to stop, [?] for help
Output #0, mp3, to '/tmp/tmpk1yxuube/out.mp3':
  Metadata:
    TSSE            : Lavf57.83.100
    Stream #0:0: Audio: mp3 (libmp3lame), 44100 Hz, mono, fltp
    Metadata:
      encoder         : Lavc57.107.100 libmp3lame
size=     127kB time=00:00:16.13 bitrate=  64.2kbits/s speed=66.9x
video:0kB audio:126kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.175482%
LY output to `/tmp/tmpk1yxuube/score.ly'...
Changing working directory to: `/tmp/tmpk1yxuube'
Processing `/tmp/tmpk1yxuube/score.ly'
Parsing...
Interpreting music...[8][8]
Preprocessing graphical objects...
Interpreting music...
MIDI output to `score.midi'...
Finding the ideal number of pages...
Fitting music on 1 page...
Drawing systems...
Layout output to `score.ps'...
Converting to PNG...
Success: compilation successfully completed

Prediction

andreasjansson/music-inpainting-bert:58bdc207

Model

andreasjansson/music-inpainting-bert:58bdc207

zm25glfcfbgfndfbwlulmzsh6m

Status

Succeeded

Source

Web

Hardware

–

Total duration

41.0s

Created

almost 3 years ago

Input

seed: -1
notes: e2 f#4 | g.4 f#8 e4 | b2 b4 | b.2 | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | e.2
tempo: "100"
chords: Em | Em | Em | Em | Fm | Fm | Em | Em | Fm | Fm | Em | Em | B7 | B7 | Em | Em
sample_width: "80"
time_signature: "3"

{
  "seed": -1,
  "notes": "e2 f#4 | g.4 f#8 e4 | b2 b4 | b.2 | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | e.2",
  "tempo": "100",
  "chords": "Em | Em | Em | Em | Fm | Fm | Em | Em | Fm | Fm | Em | Em | B7 | B7 | Em | Em",
  "sample_width": "80",
  "time_signature": "3"
}

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 andreasjansson/music-inpainting-bert using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "andreasjansson/music-inpainting-bert:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1",
  {
    input: {
      seed: -1,
      notes: "e2 f#4 | g.4 f#8 e4 | b2 b4 | b.2 | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | e.2",
      tempo: "100",
      chords: "Em | Em | Em | Em | Fm | Fm | Em | Em | Fm | Fm | Em | Em | B7 | B7 | Em | Em",
      sample_width: "80",
      time_signature: "3"
    }
  }
);
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 andreasjansson/music-inpainting-bert using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "andreasjansson/music-inpainting-bert:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1",
    input={
        "seed": -1,
        "notes": "e2 f#4 | g.4 f#8 e4 | b2 b4 | b.2 | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | e.2",
        "tempo": "100",
        "chords": "Em | Em | Em | Em | Fm | Fm | Em | Em | Fm | Fm | Em | Em | B7 | B7 | Em | Em",
        "sample_width": "80",
        "time_signature": "3"
    }
)
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 andreasjansson/music-inpainting-bert 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": "58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1",
    "input": {
      "seed": -1,
      "notes": "e2 f#4 | g.4 f#8 e4 | b2 b4 | b.2 | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | e.2",
      "tempo": "100",
      "chords": "Em | Em | Em | Em | Fm | Fm | Em | Em | Fm | Fm | Em | Em | B7 | B7 | Em | Em",
      "sample_width": "80",
      "time_signature": "3"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Install Cog

brew install cog

If you don’t have Homebrew, there are other installation options available.

Pull and run andreasjansson/music-inpainting-bert using Cog (this will download the full model and run it in your local environment):

cog predict r8.im/andreasjansson/music-inpainting-bert@sha256:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1 \
  -i 'seed=-1' \
  -i 'notes="e2 f#4 | g.4 f#8 e4 | b2 b4 | b.2 | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | e.2"' \
  -i 'tempo="100"' \
  -i 'chords="Em | Em | Em | Em | Fm | Fm | Em | Em | Fm | Fm | Em | Em | B7 | B7 | Em | Em"' \
  -i 'sample_width="80"' \
  -i 'time_signature="3"'

To learn more, take a look at the Cog documentation.

Pull and run andreasjansson/music-inpainting-bert using Docker (this will download the full model and run it in your local environment):

docker run -d -p 5000:5000 --gpus=all r8.im/andreasjansson/music-inpainting-bert@sha256:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "seed": -1,
      "notes": "e2 f#4 | g.4 f#8 e4 | b2 b4 | b.2 | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | e.2",
      "tempo": "100",
      "chords": "Em | Em | Em | Em | Fm | Fm | Em | Em | Fm | Fm | Em | Em | B7 | B7 | Em | Em",
      "sample_width": "80",
      "time_signature": "3"
    }
  }' \
  http://localhost:5000/predictions

Output

mp3

Video Player is loading.

Current Time 00:00:000

Duration 00:00:000

Loaded: 0%

Stream Type LIVE

Remaining Time 00:00:000

midi

out.midi

score

{
  "completed_at": "2022-05-03T19:30:00.838490Z",
  "created_at": "2022-05-03T19:29:19.882955Z",
  "data_removed": false,
  "error": null,
  "id": "zm25glfcfbgfndfbwlulmzsh6m",
  "input": {
    "seed": -1,
    "notes": "e2 f#4 | g.4 f#8 e4 | b2 b4 | b.2 | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | e.2",
    "tempo": "100",
    "chords": "Em | Em | Em | Em | Fm | Fm | Em | Em | Fm | Fm | Em | Em | B7 | B7 | Em | Em",
    "sample_width": "80",
    "time_signature": "3"
  },
  "logs": "Using seed: 15241\n0.0 80\n0.1 12\n0.2 9\n0.3 7\n0.4 6\n0.5 5\n0.6 4\n0.7 3\n0.8 3\n0.9 2\n0:0 (0/1 E4) Em/E 0\n0:1  Em/E 0\n1:2 (0/1 F#4) Em/E 0\n1:0 (0/1 G4) Em/E 0\n1:1 (1/2 F#4) Em/E 0\n2:2 (0/1 E4) Em/E 0\n2:0 (0/1 B4) Em/E 0\n2:1  Em/E 0\n3:2 (0/1 B4) Em/E 0\n3:0 (0/1 B4) Em/E 0\n3:1  Em/E 0\n4:2  Em/E 0\n4:0  Fm/F 5\n4:1 (0/1 F4) Fm/F 1\n5:2 (0/1 G#4) Fm/F 8\n5:0 (0/1 G#4) Fm/F 6\n5:1  Fm/F 4\n6:2  Fm/F 4\n6:0 (0/1 E5) Em/E 5\n6:1  Em/E 3\n7:2 (0/1 B4) Em/E 5\n7:0 (0/1 E4) Em/E 6\n7:1  Em/E 7\n8:2 (0/1 B4) Em/E 1\n8:0 (0/1 C5) Fm/F 3\n8:1  Fm/F 8\n9:2 (0/1 E-5) Fm/F 2\n9:0 (0/1 F5) Fm/F 3\n9:1  Fm/F 6\n10:2 (0/1 E-5) Fm/F 1\n10:0 (0/1 E5) Em/E 7\n10:1  Em/E 5\n11:2 (0/1 B4) Em/E 3\n11:0 (0/1 B4) Em/E 8\n11:1  Em/E 7\n12:2  Em/E 2\n12:0 (0/1 B4) B7 2\n12:1  B7 1\n13:2 (0/1 E-5) B7 4\n13:0 (0/1 F#5) B7 7\n13:1  B7 4\n14:2  B7 9\n14:0 (0/1 E5) Em/E 6\n14:1  Em/E 8\n15:2 (0/1 B4) Em/E 2\n15:0 (0/1 E4) Em/E 0\n46: Invalid pattern: 0\n0 pattern\nffmpeg version 3.4.8-0ubuntu0.2 Copyright (c) 2000-2020 the FFmpeg developers\n  built with gcc 7 (Ubuntu 7.5.0-3ubuntu1~18.04)\n  configuration: --prefix=/usr --extra-version=0ubuntu0.2 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --enable-gpl --disable-stripping --enable-avresample --enable-avisynth --enable-gnutls --enable-ladspa --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librubberband --enable-librsvg --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvorbis --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzmq --enable-libzvbi --enable-omx --enable-openal --enable-opengl --enable-sdl2 --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libopencv --enable-libx264 --enable-shared\n  libavutil      55. 78.100 / 55. 78.100\n  libavcodec     57.107.100 / 57.107.100\n  libavformat    57. 83.100 / 57. 83.100\n  libavdevice    57. 10.100 / 57. 10.100\n  libavfilter     6.107.100 /  6.107.100\n  libavresample   3.  7.  0 /  3.  7.  0\n  libswscale      4.  8.100 /  4.  8.100\n  libswresample   2.  9.100 /  2.  9.100\n  libpostproc    54.  7.100 / 54.  7.100\nGuessed Channel Layout for Input Stream #0.0 : mono\nInput #0, wav, from '/tmp/tmpollascuu/out.wav':\n  Duration: 00:00:29.20, bitrate: 2822 kb/s\n    Stream #0:0: Audio: pcm_f64le ([3][0][0][0] / 0x0003), 44100 Hz, mono, dbl, 2822 kb/s\nStream mapping:\n  Stream #0:0 -> #0:0 (pcm_f64le (native) -> mp3 (libmp3lame))\nPress [q] to stop, [?] for help\nOutput #0, mp3, to '/tmp/tmpollascuu/out.mp3':\n  Metadata:\n    TSSE            : Lavf57.83.100\n    Stream #0:0: Audio: mp3 (libmp3lame), 44100 Hz, mono, fltp\n    Metadata:\n      encoder         : Lavc57.107.100 libmp3lame\nsize=     226kB time=00:00:28.83 bitrate=  64.1kbits/s speed=69.5x\nvideo:0kB audio:226kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.098302%\nLY output to `/tmp/tmpollascuu/score.ly'...\nChanging working directory to: `/tmp/tmpollascuu'\nProcessing `/tmp/tmpollascuu/score.ly'\nParsing...\nInterpreting music...[8][16][16]\nPreprocessing graphical objects...\nInterpreting music...\nMIDI output to `score.midi'...\nFinding the ideal number of pages...\nFitting music on 1 page...\nDrawing systems...\nLayout output to `score.ps'...\nConverting to PNG...\nSuccess: compilation successfully completed",
  "metrics": {
    "predict_time": 6.815062,
    "total_time": 40.955535
  },
  "output": {
    "mp3": "https://replicate.delivery/mgxm/331241fb-1824-4c82-8b81-4d8b3e803d62/out.mp3",
    "midi": "https://replicate.delivery/mgxm/9faf7f5c-494a-47eb-b094-8aa66042ece3/out.midi",
    "score": "https://replicate.delivery/mgxm/ae55a649-7479-4310-821e-bb74e12dd937/score.png"
  },
  "started_at": "2022-05-03T19:29:54.023428Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/zm25glfcfbgfndfbwlulmzsh6m",
    "cancel": "https://api.replicate.com/v1/predictions/zm25glfcfbgfndfbwlulmzsh6m/cancel"
  },
  "version": "58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1"
}

Generated in

6.8 seconds

Tweak it ShareReport

Using seed: 15241
0.0 80
0.1 12
0.2 9
0.3 7
0.4 6
0.5 5
0.6 4
0.7 3
0.8 3
0.9 2
0:0 (0/1 E4) Em/E 0
0:1  Em/E 0
1:2 (0/1 F#4) Em/E 0
1:0 (0/1 G4) Em/E 0
1:1 (1/2 F#4) Em/E 0
2:2 (0/1 E4) Em/E 0
2:0 (0/1 B4) Em/E 0
2:1  Em/E 0
3:2 (0/1 B4) Em/E 0
3:0 (0/1 B4) Em/E 0
3:1  Em/E 0
4:2  Em/E 0
4:0  Fm/F 5
4:1 (0/1 F4) Fm/F 1
5:2 (0/1 G#4) Fm/F 8
5:0 (0/1 G#4) Fm/F 6
5:1  Fm/F 4
6:2  Fm/F 4
6:0 (0/1 E5) Em/E 5
6:1  Em/E 3
7:2 (0/1 B4) Em/E 5
7:0 (0/1 E4) Em/E 6
7:1  Em/E 7
8:2 (0/1 B4) Em/E 1
8:0 (0/1 C5) Fm/F 3
8:1  Fm/F 8
9:2 (0/1 E-5) Fm/F 2
9:0 (0/1 F5) Fm/F 3
9:1  Fm/F 6
10:2 (0/1 E-5) Fm/F 1
10:0 (0/1 E5) Em/E 7
10:1  Em/E 5
11:2 (0/1 B4) Em/E 3
11:0 (0/1 B4) Em/E 8
11:1  Em/E 7
12:2  Em/E 2
12:0 (0/1 B4) B7 2
12:1  B7 1
13:2 (0/1 E-5) B7 4
13:0 (0/1 F#5) B7 7
13:1  B7 4
14:2  B7 9
14:0 (0/1 E5) Em/E 6
14:1  Em/E 8
15:2 (0/1 B4) Em/E 2
15:0 (0/1 E4) Em/E 0
46: Invalid pattern: 0
0 pattern
ffmpeg version 3.4.8-0ubuntu0.2 Copyright (c) 2000-2020 the FFmpeg developers
  built with gcc 7 (Ubuntu 7.5.0-3ubuntu1~18.04)
  configuration: --prefix=/usr --extra-version=0ubuntu0.2 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --enable-gpl --disable-stripping --enable-avresample --enable-avisynth --enable-gnutls --enable-ladspa --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librubberband --enable-librsvg --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvorbis --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzmq --enable-libzvbi --enable-omx --enable-openal --enable-opengl --enable-sdl2 --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libopencv --enable-libx264 --enable-shared
  libavutil      55. 78.100 / 55. 78.100
  libavcodec     57.107.100 / 57.107.100
  libavformat    57. 83.100 / 57. 83.100
  libavdevice    57. 10.100 / 57. 10.100
  libavfilter     6.107.100 /  6.107.100
  libavresample   3.  7.  0 /  3.  7.  0
  libswscale      4.  8.100 /  4.  8.100
  libswresample   2.  9.100 /  2.  9.100
  libpostproc    54.  7.100 / 54.  7.100
Guessed Channel Layout for Input Stream #0.0 : mono
Input #0, wav, from '/tmp/tmpollascuu/out.wav':
  Duration: 00:00:29.20, bitrate: 2822 kb/s
    Stream #0:0: Audio: pcm_f64le ([3][0][0][0] / 0x0003), 44100 Hz, mono, dbl, 2822 kb/s
Stream mapping:
  Stream #0:0 -> #0:0 (pcm_f64le (native) -> mp3 (libmp3lame))
Press [q] to stop, [?] for help
Output #0, mp3, to '/tmp/tmpollascuu/out.mp3':
  Metadata:
    TSSE            : Lavf57.83.100
    Stream #0:0: Audio: mp3 (libmp3lame), 44100 Hz, mono, fltp
    Metadata:
      encoder         : Lavc57.107.100 libmp3lame
size=     226kB time=00:00:28.83 bitrate=  64.1kbits/s speed=69.5x
video:0kB audio:226kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.098302%
LY output to `/tmp/tmpollascuu/score.ly'...
Changing working directory to: `/tmp/tmpollascuu'
Processing `/tmp/tmpollascuu/score.ly'
Parsing...
Interpreting music...[8][16][16]
Preprocessing graphical objects...
Interpreting music...
MIDI output to `score.midi'...
Finding the ideal number of pages...
Fitting music on 1 page...
Drawing systems...
Layout output to `score.ps'...
Converting to PNG...
Success: compilation successfully completed

Prediction

andreasjansson/music-inpainting-bert:58bdc207

Model

andreasjansson/music-inpainting-bert:58bdc207

kxipvevgkzgmdeuwighovnegw4

Status

Succeeded

Source

Web

Hardware

–

Total duration

5.6s

Created

almost 3 years ago

Input

seed: -1
notes: e.4 f#8 g a | ? | ? | ? | ? | ? | b.4 a8 g f# | e.2
tempo: "80"
chords: Em | Em | Am | Am | G | F#7 | B7 | Em
sample_width: "40"
time_signature: "3"

{
  "seed": -1,
  "notes": "e.4 f#8 g a | ? | ? | ? | ? | ? | b.4 a8 g f# | e.2",
  "tempo": "80",
  "chords": "Em | Em | Am | Am | G | F#7 | B7 | Em",
  "sample_width": "40",
  "time_signature": "3"
}

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 andreasjansson/music-inpainting-bert using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "andreasjansson/music-inpainting-bert:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1",
  {
    input: {
      seed: -1,
      notes: "e.4 f#8 g a | ? | ? | ? | ? | ? | b.4 a8 g f# | e.2",
      tempo: "80",
      chords: "Em | Em | Am | Am | G | F#7 | B7 | Em",
      sample_width: "40",
      time_signature: "3"
    }
  }
);
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 andreasjansson/music-inpainting-bert using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "andreasjansson/music-inpainting-bert:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1",
    input={
        "seed": -1,
        "notes": "e.4 f#8 g a | ? | ? | ? | ? | ? | b.4 a8 g f# | e.2",
        "tempo": "80",
        "chords": "Em | Em | Am | Am | G | F#7 | B7 | Em",
        "sample_width": "40",
        "time_signature": "3"
    }
)
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 andreasjansson/music-inpainting-bert 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": "58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1",
    "input": {
      "seed": -1,
      "notes": "e.4 f#8 g a | ? | ? | ? | ? | ? | b.4 a8 g f# | e.2",
      "tempo": "80",
      "chords": "Em | Em | Am | Am | G | F#7 | B7 | Em",
      "sample_width": "40",
      "time_signature": "3"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Install Cog

brew install cog

If you don’t have Homebrew, there are other installation options available.

Pull and run andreasjansson/music-inpainting-bert using Cog (this will download the full model and run it in your local environment):

cog predict r8.im/andreasjansson/music-inpainting-bert@sha256:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1 \
  -i 'seed=-1' \
  -i 'notes="e.4 f#8 g a | ? | ? | ? | ? | ? | b.4 a8 g f# | e.2"' \
  -i 'tempo="80"' \
  -i 'chords="Em | Em | Am | Am | G | F#7 | B7 | Em"' \
  -i 'sample_width="40"' \
  -i 'time_signature="3"'

To learn more, take a look at the Cog documentation.

Pull and run andreasjansson/music-inpainting-bert using Docker (this will download the full model and run it in your local environment):

docker run -d -p 5000:5000 --gpus=all r8.im/andreasjansson/music-inpainting-bert@sha256:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "seed": -1,
      "notes": "e.4 f#8 g a | ? | ? | ? | ? | ? | b.4 a8 g f# | e.2",
      "tempo": "80",
      "chords": "Em | Em | Am | Am | G | F#7 | B7 | Em",
      "sample_width": "40",
      "time_signature": "3"
    }
  }' \
  http://localhost:5000/predictions

Output

mp3

Video Player is loading.

Current Time 00:00:000

Duration 00:00:000

Loaded: 0%

Stream Type LIVE

Remaining Time 00:00:000

midi

out.midi

score

{
  "completed_at": "2022-05-03T19:38:40.143558Z",
  "created_at": "2022-05-03T19:38:34.533299Z",
  "data_removed": false,
  "error": null,
  "id": "kxipvevgkzgmdeuwighovnegw4",
  "input": {
    "seed": -1,
    "notes": "e.4 f#8 g a | ? | ? | ? | ? | ? | b.4 a8 g f# | e.2",
    "tempo": "80",
    "chords": "Em | Em | Am | Am | G | F#7 | B7 | Em",
    "sample_width": "40",
    "time_signature": "3"
  },
  "logs": "Using seed: 11712\n0.0 40\n0.1 11\n0.2 9\n0.3 7\n0.4 6\n0.5 5\n0.6 4\n0.7 3\n0.8 3\n0.9 2\n0:0 (0/1 E4) Em/E 0\n0:1 (1/2 F#4) Em/E 0\n1:2 (0/1 G4), (1/2 A4) Em/E 0\n1:0 (0/1 B4) Em/E 6\n1:1  Em/E 6\n2:2 (0/1 G4), (1/2 A4) Em/E 3\n2:0 (0/1 E4) Am/A 8\n2:1  Am/A 3\n3:2 (0/1 E4) Am/A 4\n3:0 (0/1 A4) Am/A 2\n3:1  Am/A 5\n4:2 (0/1 E4) Am/A 7\n4:0 (0/1 D4) G/G 4\n4:1  G/G 7\n5:2 (0/1 G4) G/G 5\n5:0 (0/1 F#4) Gb7 2\n5:1  Gb7 1\n6:2 (0/1 G4), (1/2 A4) Gb7 1\n6:0 (0/1 B4) B7 0\n6:1 (1/2 A4) B7 0\n7:2 (0/1 G4), (1/2 F#4) B7 0\n7:0 (0/1 E4) Em/E 0\n22: Invalid pattern: 0\n0 pattern\nffmpeg version 3.4.8-0ubuntu0.2 Copyright (c) 2000-2020 the FFmpeg developers\n  built with gcc 7 (Ubuntu 7.5.0-3ubuntu1~18.04)\n  configuration: --prefix=/usr --extra-version=0ubuntu0.2 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --enable-gpl --disable-stripping --enable-avresample --enable-avisynth --enable-gnutls --enable-ladspa --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librubberband --enable-librsvg --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvorbis --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzmq --enable-libzvbi --enable-omx --enable-openal --enable-opengl --enable-sdl2 --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libopencv --enable-libx264 --enable-shared\n  libavutil      55. 78.100 / 55. 78.100\n  libavcodec     57.107.100 / 57.107.100\n  libavformat    57. 83.100 / 57. 83.100\n  libavdevice    57. 10.100 / 57. 10.100\n  libavfilter     6.107.100 /  6.107.100\n  libavresample   3.  7.  0 /  3.  7.  0\n  libswscale      4.  8.100 /  4.  8.100\n  libswresample   2.  9.100 /  2.  9.100\n  libpostproc    54.  7.100 / 54.  7.100\nGuessed Channel Layout for Input Stream #0.0 : mono\nInput #0, wav, from '/tmp/tmpwjjxutc0/out.wav':\n  Duration: 00:00:18.25, bitrate: 2822 kb/s\n    Stream #0:0: Audio: pcm_f64le ([3][0][0][0] / 0x0003), 44100 Hz, mono, dbl, 2822 kb/s\nStream mapping:\n  Stream #0:0 -> #0:0 (pcm_f64le (native) -> mp3 (libmp3lame))\nPress [q] to stop, [?] for help\nOutput #0, mp3, to '/tmp/tmpwjjxutc0/out.mp3':\n  Metadata:\n    TSSE            : Lavf57.83.100\n    Stream #0:0: Audio: mp3 (libmp3lame), 44100 Hz, mono, fltp\n    Metadata:\n      encoder         : Lavc57.107.100 libmp3lame\nsize=     140kB time=00:00:17.91 bitrate=  64.2kbits/s speed=71.9x\nvideo:0kB audio:140kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.158113%\nLY output to `/tmp/tmpwjjxutc0/score.ly'...\nChanging working directory to: `/tmp/tmpwjjxutc0'\nProcessing `/tmp/tmpwjjxutc0/score.ly'\nParsing...\nInterpreting music...[8][8]\nPreprocessing graphical objects...\nInterpreting music...\nMIDI output to `score.midi'...\nFinding the ideal number of pages...\nFitting music on 1 page...\nDrawing systems...\nLayout output to `score.ps'...\nConverting to PNG...\nSuccess: compilation successfully completed",
  "metrics": {
    "predict_time": 5.294946,
    "total_time": 5.610259
  },
  "output": {
    "mp3": "https://replicate.delivery/mgxm/7b6ca49d-2941-4077-a588-d188feab16ab/out.mp3",
    "midi": "https://replicate.delivery/mgxm/fc8c5ed7-0134-44f5-8e8e-8757b2dc8ebb/out.midi",
    "score": "https://replicate.delivery/mgxm/e5854084-04ef-4001-ba75-7d0cf9f14246/score.png"
  },
  "started_at": "2022-05-03T19:38:34.848612Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/kxipvevgkzgmdeuwighovnegw4",
    "cancel": "https://api.replicate.com/v1/predictions/kxipvevgkzgmdeuwighovnegw4/cancel"
  },
  "version": "58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1"
}

Generated in

5.3 seconds

Tweak it ShareReport

Using seed: 11712
0.0 40
0.1 11
0.2 9
0.3 7
0.4 6
0.5 5
0.6 4
0.7 3
0.8 3
0.9 2
0:0 (0/1 E4) Em/E 0
0:1 (1/2 F#4) Em/E 0
1:2 (0/1 G4), (1/2 A4) Em/E 0
1:0 (0/1 B4) Em/E 6
1:1  Em/E 6
2:2 (0/1 G4), (1/2 A4) Em/E 3
2:0 (0/1 E4) Am/A 8
2:1  Am/A 3
3:2 (0/1 E4) Am/A 4
3:0 (0/1 A4) Am/A 2
3:1  Am/A 5
4:2 (0/1 E4) Am/A 7
4:0 (0/1 D4) G/G 4
4:1  G/G 7
5:2 (0/1 G4) G/G 5
5:0 (0/1 F#4) Gb7 2
5:1  Gb7 1
6:2 (0/1 G4), (1/2 A4) Gb7 1
6:0 (0/1 B4) B7 0
6:1 (1/2 A4) B7 0
7:2 (0/1 G4), (1/2 F#4) B7 0
7:0 (0/1 E4) Em/E 0
22: Invalid pattern: 0
0 pattern
ffmpeg version 3.4.8-0ubuntu0.2 Copyright (c) 2000-2020 the FFmpeg developers
  built with gcc 7 (Ubuntu 7.5.0-3ubuntu1~18.04)
  configuration: --prefix=/usr --extra-version=0ubuntu0.2 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --enable-gpl --disable-stripping --enable-avresample --enable-avisynth --enable-gnutls --enable-ladspa --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librubberband --enable-librsvg --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvorbis --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzmq --enable-libzvbi --enable-omx --enable-openal --enable-opengl --enable-sdl2 --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libopencv --enable-libx264 --enable-shared
  libavutil      55. 78.100 / 55. 78.100
  libavcodec     57.107.100 / 57.107.100
  libavformat    57. 83.100 / 57. 83.100
  libavdevice    57. 10.100 / 57. 10.100
  libavfilter     6.107.100 /  6.107.100
  libavresample   3.  7.  0 /  3.  7.  0
  libswscale      4.  8.100 /  4.  8.100
  libswresample   2.  9.100 /  2.  9.100
  libpostproc    54.  7.100 / 54.  7.100
Guessed Channel Layout for Input Stream #0.0 : mono
Input #0, wav, from '/tmp/tmpwjjxutc0/out.wav':
  Duration: 00:00:18.25, bitrate: 2822 kb/s
    Stream #0:0: Audio: pcm_f64le ([3][0][0][0] / 0x0003), 44100 Hz, mono, dbl, 2822 kb/s
Stream mapping:
  Stream #0:0 -> #0:0 (pcm_f64le (native) -> mp3 (libmp3lame))
Press [q] to stop, [?] for help
Output #0, mp3, to '/tmp/tmpwjjxutc0/out.mp3':
  Metadata:
    TSSE            : Lavf57.83.100
    Stream #0:0: Audio: mp3 (libmp3lame), 44100 Hz, mono, fltp
    Metadata:
      encoder         : Lavc57.107.100 libmp3lame
size=     140kB time=00:00:17.91 bitrate=  64.2kbits/s speed=71.9x
video:0kB audio:140kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.158113%
LY output to `/tmp/tmpwjjxutc0/score.ly'...
Changing working directory to: `/tmp/tmpwjjxutc0'
Processing `/tmp/tmpwjjxutc0/score.ly'
Parsing...
Interpreting music...[8][8]
Preprocessing graphical objects...
Interpreting music...
MIDI output to `score.midi'...
Finding the ideal number of pages...
Fitting music on 1 page...
Drawing systems...
Layout output to `score.ps'...
Converting to PNG...
Success: compilation successfully completed

Prediction

andreasjansson/music-inpainting-bert:58bdc207

Model

andreasjansson/music-inpainting-bert:58bdc207

iswjari2ujbqdosk65rrv7qogy

Status

Succeeded

Source

Web

Hardware

–

Total duration

5.5s

Created

almost 3 years ago

Input

seed: -1
notes: e.4 f#8 g a | ? | ? | ? | ? | ? | b.4 a8 g f# | e.2
tempo: "100"
chords: Em | Em | Am | Am | G | F#7 | B7 | Em
sample_width: "71"
time_signature: "3"

{
  "seed": -1,
  "notes": "e.4 f#8 g a | ? | ? | ? | ? | ? | b.4 a8 g f# | e.2",
  "tempo": "100",
  "chords": "Em | Em | Am | Am | G | F#7 | B7 | Em",
  "sample_width": "71",
  "time_signature": "3"
}

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 andreasjansson/music-inpainting-bert using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "andreasjansson/music-inpainting-bert:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1",
  {
    input: {
      seed: -1,
      notes: "e.4 f#8 g a | ? | ? | ? | ? | ? | b.4 a8 g f# | e.2",
      tempo: "100",
      chords: "Em | Em | Am | Am | G | F#7 | B7 | Em",
      sample_width: "71",
      time_signature: "3"
    }
  }
);
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 andreasjansson/music-inpainting-bert using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "andreasjansson/music-inpainting-bert:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1",
    input={
        "seed": -1,
        "notes": "e.4 f#8 g a | ? | ? | ? | ? | ? | b.4 a8 g f# | e.2",
        "tempo": "100",
        "chords": "Em | Em | Am | Am | G | F#7 | B7 | Em",
        "sample_width": "71",
        "time_signature": "3"
    }
)
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 andreasjansson/music-inpainting-bert 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": "58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1",
    "input": {
      "seed": -1,
      "notes": "e.4 f#8 g a | ? | ? | ? | ? | ? | b.4 a8 g f# | e.2",
      "tempo": "100",
      "chords": "Em | Em | Am | Am | G | F#7 | B7 | Em",
      "sample_width": "71",
      "time_signature": "3"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Install Cog

brew install cog

If you don’t have Homebrew, there are other installation options available.

Pull and run andreasjansson/music-inpainting-bert using Cog (this will download the full model and run it in your local environment):

cog predict r8.im/andreasjansson/music-inpainting-bert@sha256:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1 \
  -i 'seed=-1' \
  -i 'notes="e.4 f#8 g a | ? | ? | ? | ? | ? | b.4 a8 g f# | e.2"' \
  -i 'tempo="100"' \
  -i 'chords="Em | Em | Am | Am | G | F#7 | B7 | Em"' \
  -i 'sample_width="71"' \
  -i 'time_signature="3"'

To learn more, take a look at the Cog documentation.

Pull and run andreasjansson/music-inpainting-bert using Docker (this will download the full model and run it in your local environment):

docker run -d -p 5000:5000 --gpus=all r8.im/andreasjansson/music-inpainting-bert@sha256:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "seed": -1,
      "notes": "e.4 f#8 g a | ? | ? | ? | ? | ? | b.4 a8 g f# | e.2",
      "tempo": "100",
      "chords": "Em | Em | Am | Am | G | F#7 | B7 | Em",
      "sample_width": "71",
      "time_signature": "3"
    }
  }' \
  http://localhost:5000/predictions

Output

mp3

Video Player is loading.

Current Time 00:00:000

Duration 00:00:000

Loaded: 0%

Stream Type LIVE

Remaining Time 00:00:000

midi

out.midi

score

{
  "completed_at": "2022-05-03T19:38:55.711719Z",
  "created_at": "2022-05-03T19:38:50.253598Z",
  "data_removed": false,
  "error": null,
  "id": "iswjari2ujbqdosk65rrv7qogy",
  "input": {
    "seed": -1,
    "notes": "e.4 f#8 g a | ? | ? | ? | ? | ? | b.4 a8 g f# | e.2",
    "tempo": "100",
    "chords": "Em | Em | Am | Am | G | F#7 | B7 | Em",
    "sample_width": "71",
    "time_signature": "3"
  },
  "logs": "Using seed: 38187\n0.0 71\n0.1 12\n0.2 9\n0.3 7\n0.4 6\n0.5 5\n0.6 4\n0.7 3\n0.8 3\n0.9 2\n0:0 (0/1 E4) Em/E 0\n0:1 (1/2 F#4) Em/E 0\n1:2 (0/1 G4), (1/2 A4) Em/E 0\n1:0 (0/1 E5) Em/E 8\n1:1 (1/2 B4) Em/E 3\n2:2 (0/1 A4), (1/2 G4) Em/E 5\n2:0 (0/1 E5) Am/A 3\n2:1 (1/2 A4) Am/A 1\n3:2 (0/1 G4), (1/2 F#4) Am/A 6\n3:0 (0/1 E4) Am/A 6\n3:1  Am/A 4\n4:2 (0/1 E4) Am/A 7\n4:0 (0/1 G4) G/G 5\n4:1 (1/2 F#4) G/G 1\n5:2 (0/1 G4), (1/2 A4) G/G 2\n5:0 (0/1 B-4) Gb7 4\n5:1 (1/2 E4) Gb7 2\n6:2 (0/1 E-4), (1/2 E4) Gb7 7\n6:0 (0/1 B4) B7 0\n6:1 (1/2 A4) B7 0\n7:2 (0/1 G4), (1/2 F#4) B7 0\n7:0 (0/1 E4) Em/E 0\n22: Invalid pattern: 0\n0 pattern\nffmpeg version 3.4.8-0ubuntu0.2 Copyright (c) 2000-2020 the FFmpeg developers\n  built with gcc 7 (Ubuntu 7.5.0-3ubuntu1~18.04)\n  configuration: --prefix=/usr --extra-version=0ubuntu0.2 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --enable-gpl --disable-stripping --enable-avresample --enable-avisynth --enable-gnutls --enable-ladspa --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librubberband --enable-librsvg --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvorbis --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzmq --enable-libzvbi --enable-omx --enable-openal --enable-opengl --enable-sdl2 --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libopencv --enable-libx264 --enable-shared\n  libavutil      55. 78.100 / 55. 78.100\n  libavcodec     57.107.100 / 57.107.100\n  libavformat    57. 83.100 / 57. 83.100\n  libavdevice    57. 10.100 / 57. 10.100\n  libavfilter     6.107.100 /  6.107.100\n  libavresample   3.  7.  0 /  3.  7.  0\n  libswscale      4.  8.100 /  4.  8.100\n  libswresample   2.  9.100 /  2.  9.100\n  libpostproc    54.  7.100 / 54.  7.100\nGuessed Channel Layout for Input Stream #0.0 : mono\nInput #0, wav, from '/tmp/tmpmfne4bxm/out.wav':\n  Duration: 00:00:14.80, bitrate: 2822 kb/s\n    Stream #0:0: Audio: pcm_f64le ([3][0][0][0] / 0x0003), 44100 Hz, mono, dbl, 2822 kb/s\nStream mapping:\n  Stream #0:0 -> #0:0 (pcm_f64le (native) -> mp3 (libmp3lame))\nPress [q] to stop, [?] for help\nOutput #0, mp3, to '/tmp/tmpmfne4bxm/out.mp3':\n  Metadata:\n    TSSE            : Lavf57.83.100\n    Stream #0:0: Audio: mp3 (libmp3lame), 44100 Hz, mono, fltp\n    Metadata:\n      encoder         : Lavc57.107.100 libmp3lame\nsize=     114kB time=00:00:14.49 bitrate=  64.2kbits/s speed=69.1x\nvideo:0kB audio:113kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.195366%\nLY output to `/tmp/tmpmfne4bxm/score.ly'...\nChanging working directory to: `/tmp/tmpmfne4bxm'\nProcessing `/tmp/tmpmfne4bxm/score.ly'\nParsing...\nInterpreting music...[8][8]\nPreprocessing graphical objects...\nInterpreting music...\nMIDI output to `score.midi'...\nFinding the ideal number of pages...\nFitting music on 1 page...\nDrawing systems...\nLayout output to `score.ps'...\nConverting to PNG...\nSuccess: compilation successfully completed",
  "metrics": {
    "predict_time": 5.242744,
    "total_time": 5.458121
  },
  "output": {
    "mp3": "https://replicate.delivery/mgxm/43253dc0-8969-44ed-ac44-bf9d5d6c02d2/out.mp3",
    "midi": "https://replicate.delivery/mgxm/fd389619-4065-4c91-9080-d80fb0279c03/out.midi",
    "score": "https://replicate.delivery/mgxm/333d178b-6827-4fdc-a061-1e574fb6a84c/score.png"
  },
  "started_at": "2022-05-03T19:38:50.468975Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/iswjari2ujbqdosk65rrv7qogy",
    "cancel": "https://api.replicate.com/v1/predictions/iswjari2ujbqdosk65rrv7qogy/cancel"
  },
  "version": "58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1"
}

Generated in

5.3 seconds

Tweak it ShareReport

Using seed: 38187
0.0 71
0.1 12
0.2 9
0.3 7
0.4 6
0.5 5
0.6 4
0.7 3
0.8 3
0.9 2
0:0 (0/1 E4) Em/E 0
0:1 (1/2 F#4) Em/E 0
1:2 (0/1 G4), (1/2 A4) Em/E 0
1:0 (0/1 E5) Em/E 8
1:1 (1/2 B4) Em/E 3
2:2 (0/1 A4), (1/2 G4) Em/E 5
2:0 (0/1 E5) Am/A 3
2:1 (1/2 A4) Am/A 1
3:2 (0/1 G4), (1/2 F#4) Am/A 6
3:0 (0/1 E4) Am/A 6
3:1  Am/A 4
4:2 (0/1 E4) Am/A 7
4:0 (0/1 G4) G/G 5
4:1 (1/2 F#4) G/G 1
5:2 (0/1 G4), (1/2 A4) G/G 2
5:0 (0/1 B-4) Gb7 4
5:1 (1/2 E4) Gb7 2
6:2 (0/1 E-4), (1/2 E4) Gb7 7
6:0 (0/1 B4) B7 0
6:1 (1/2 A4) B7 0
7:2 (0/1 G4), (1/2 F#4) B7 0
7:0 (0/1 E4) Em/E 0
22: Invalid pattern: 0
0 pattern
ffmpeg version 3.4.8-0ubuntu0.2 Copyright (c) 2000-2020 the FFmpeg developers
  built with gcc 7 (Ubuntu 7.5.0-3ubuntu1~18.04)
  configuration: --prefix=/usr --extra-version=0ubuntu0.2 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --enable-gpl --disable-stripping --enable-avresample --enable-avisynth --enable-gnutls --enable-ladspa --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librubberband --enable-librsvg --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvorbis --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzmq --enable-libzvbi --enable-omx --enable-openal --enable-opengl --enable-sdl2 --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libopencv --enable-libx264 --enable-shared
  libavutil      55. 78.100 / 55. 78.100
  libavcodec     57.107.100 / 57.107.100
  libavformat    57. 83.100 / 57. 83.100
  libavdevice    57. 10.100 / 57. 10.100
  libavfilter     6.107.100 /  6.107.100
  libavresample   3.  7.  0 /  3.  7.  0
  libswscale      4.  8.100 /  4.  8.100
  libswresample   2.  9.100 /  2.  9.100
  libpostproc    54.  7.100 / 54.  7.100
Guessed Channel Layout for Input Stream #0.0 : mono
Input #0, wav, from '/tmp/tmpmfne4bxm/out.wav':
  Duration: 00:00:14.80, bitrate: 2822 kb/s
    Stream #0:0: Audio: pcm_f64le ([3][0][0][0] / 0x0003), 44100 Hz, mono, dbl, 2822 kb/s
Stream mapping:
  Stream #0:0 -> #0:0 (pcm_f64le (native) -> mp3 (libmp3lame))
Press [q] to stop, [?] for help
Output #0, mp3, to '/tmp/tmpmfne4bxm/out.mp3':
  Metadata:
    TSSE            : Lavf57.83.100
    Stream #0:0: Audio: mp3 (libmp3lame), 44100 Hz, mono, fltp
    Metadata:
      encoder         : Lavc57.107.100 libmp3lame
size=     114kB time=00:00:14.49 bitrate=  64.2kbits/s speed=69.1x
video:0kB audio:113kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.195366%
LY output to `/tmp/tmpmfne4bxm/score.ly'...
Changing working directory to: `/tmp/tmpmfne4bxm'
Processing `/tmp/tmpmfne4bxm/score.ly'
Parsing...
Interpreting music...[8][8]
Preprocessing graphical objects...
Interpreting music...
MIDI output to `score.midi'...
Finding the ideal number of pages...
Fitting music on 1 page...
Drawing systems...
Layout output to `score.ps'...
Converting to PNG...
Success: compilation successfully completed

Prediction

andreasjansson/music-inpainting-bert:58bdc207

Model

andreasjansson/music-inpainting-bert:58bdc207

ogj47dc2vfcjdhzpyelk5xhqbm

Status

Succeeded

Source

Web

Hardware

–

Total duration

37.5s

Created

almost 3 years ago

Input

seed: -1
notes: e.4 f#8 g a | ? | ? | ? | ? | ? | b.4 a8 g f# | e.2
tempo: "120"
chords: Em | Em | Am | Am | G | F#7 | B7 | Em
sample_width: "141"
time_signature: "3"

{
  "seed": -1,
  "notes": "e.4 f#8 g a | ? | ? | ? | ? | ? | b.4 a8 g f# | e.2",
  "tempo": "120",
  "chords": "Em | Em | Am | Am | G | F#7 | B7 | Em",
  "sample_width": "141",
  "time_signature": "3"
}

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 andreasjansson/music-inpainting-bert using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "andreasjansson/music-inpainting-bert:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1",
  {
    input: {
      seed: -1,
      notes: "e.4 f#8 g a | ? | ? | ? | ? | ? | b.4 a8 g f# | e.2",
      tempo: "120",
      chords: "Em | Em | Am | Am | G | F#7 | B7 | Em",
      sample_width: "141",
      time_signature: "3"
    }
  }
);
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 andreasjansson/music-inpainting-bert using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "andreasjansson/music-inpainting-bert:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1",
    input={
        "seed": -1,
        "notes": "e.4 f#8 g a | ? | ? | ? | ? | ? | b.4 a8 g f# | e.2",
        "tempo": "120",
        "chords": "Em | Em | Am | Am | G | F#7 | B7 | Em",
        "sample_width": "141",
        "time_signature": "3"
    }
)
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 andreasjansson/music-inpainting-bert 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": "58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1",
    "input": {
      "seed": -1,
      "notes": "e.4 f#8 g a | ? | ? | ? | ? | ? | b.4 a8 g f# | e.2",
      "tempo": "120",
      "chords": "Em | Em | Am | Am | G | F#7 | B7 | Em",
      "sample_width": "141",
      "time_signature": "3"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Install Cog

brew install cog

If you don’t have Homebrew, there are other installation options available.

Pull and run andreasjansson/music-inpainting-bert using Cog (this will download the full model and run it in your local environment):

cog predict r8.im/andreasjansson/music-inpainting-bert@sha256:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1 \
  -i 'seed=-1' \
  -i 'notes="e.4 f#8 g a | ? | ? | ? | ? | ? | b.4 a8 g f# | e.2"' \
  -i 'tempo="120"' \
  -i 'chords="Em | Em | Am | Am | G | F#7 | B7 | Em"' \
  -i 'sample_width="141"' \
  -i 'time_signature="3"'

To learn more, take a look at the Cog documentation.

Pull and run andreasjansson/music-inpainting-bert using Docker (this will download the full model and run it in your local environment):

docker run -d -p 5000:5000 --gpus=all r8.im/andreasjansson/music-inpainting-bert@sha256:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "seed": -1,
      "notes": "e.4 f#8 g a | ? | ? | ? | ? | ? | b.4 a8 g f# | e.2",
      "tempo": "120",
      "chords": "Em | Em | Am | Am | G | F#7 | B7 | Em",
      "sample_width": "141",
      "time_signature": "3"
    }
  }' \
  http://localhost:5000/predictions

Output

mp3

Video Player is loading.

Current Time 00:00:000

Duration 00:00:000

Loaded: 0%

Stream Type LIVE

Remaining Time 00:00:000

midi

out.midi

score

{
  "completed_at": "2022-05-03T19:30:12.879646Z",
  "created_at": "2022-05-03T19:29:35.406661Z",
  "data_removed": false,
  "error": null,
  "id": "ogj47dc2vfcjdhzpyelk5xhqbm",
  "input": {
    "seed": -1,
    "notes": "e.4 f#8 g a | ? | ? | ? | ? | ? | b.4 a8 g f# | e.2",
    "tempo": "120",
    "chords": "Em | Em | Am | Am | G | F#7 | B7 | Em",
    "sample_width": "141",
    "time_signature": "3"
  },
  "logs": "Using seed: 15564\n0.0 141\n0.1 12\n0.2 9\n0.3 7\n0.4 6\n0.5 5\n0.6 4\n0.7 3\n0.8 3\n0.9 2\n0:0 (0/1 E4) Em/E 0\n0:1 (1/2 F#4) Em/E 0\n1:2 (0/1 G4), (1/2 A4) Em/E 0\n1:0 (0/1 G4) Em/E 2\n1:1  Em/E 6\n2:2 (0/1 E4) Em/E 3\n2:0 (0/1 A5) Am/A 1\n2:1 (1/2 B5) Am/A 8\n3:2 (0/1 A5), (1/2 G5) Am/A 6\n3:0 (0/1 A5) Am/A 4\n3:1  Am/A 2\n4:2 (0/1 E5) Am/A 5\n4:0 (0/1 D5) G/G 5\n4:1 (1/2 E5) G/G 3\n5:2 (0/1 D5), (1/2 B4) G/G 7\n5:0 (0/1 C#5) Gb7 4\n5:1 (1/2 C5) Gb7 7\n6:2 (0/1 C#5), (1/2 C5) Gb7 1\n6:0 (0/1 B4) B7 0\n6:1 (1/2 A4) B7 0\n7:2 (0/1 G4), (1/2 F#4) B7 0\n7:0 (0/1 E4) Em/E 0\n22: Invalid pattern: 0\n0 pattern\nffmpeg version 3.4.8-0ubuntu0.2 Copyright (c) 2000-2020 the FFmpeg developers\n  built with gcc 7 (Ubuntu 7.5.0-3ubuntu1~18.04)\n  configuration: --prefix=/usr --extra-version=0ubuntu0.2 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --enable-gpl --disable-stripping --enable-avresample --enable-avisynth --enable-gnutls --enable-ladspa --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librubberband --enable-librsvg --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvorbis --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzmq --enable-libzvbi --enable-omx --enable-openal --enable-opengl --enable-sdl2 --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libopencv --enable-libx264 --enable-shared\n  libavutil      55. 78.100 / 55. 78.100\n  libavcodec     57.107.100 / 57.107.100\n  libavformat    57. 83.100 / 57. 83.100\n  libavdevice    57. 10.100 / 57. 10.100\n  libavfilter     6.107.100 /  6.107.100\n  libavresample   3.  7.  0 /  3.  7.  0\n  libswscale      4.  8.100 /  4.  8.100\n  libswresample   2.  9.100 /  2.  9.100\n  libpostproc    54.  7.100 / 54.  7.100\nGuessed Channel Layout for Input Stream #0.0 : mono\nInput #0, wav, from '/tmp/tmprvn1r7he/out.wav':\n  Duration: 00:00:12.50, bitrate: 2822 kb/s\n    Stream #0:0: Audio: pcm_f64le ([3][0][0][0] / 0x0003), 44100 Hz, mono, dbl, 2822 kb/s\nStream mapping:\n  Stream #0:0 -> #0:0 (pcm_f64le (native) -> mp3 (libmp3lame))\nPress [q] to stop, [?] for help\nOutput #0, mp3, to '/tmp/tmprvn1r7he/out.mp3':\n  Metadata:\n    TSSE            : Lavf57.83.100\n    Stream #0:0: Audio: mp3 (libmp3lame), 44100 Hz, mono, fltp\n    Metadata:\n      encoder         : Lavc57.107.100 libmp3lame\nsize=      96kB time=00:00:12.17 bitrate=  64.3kbits/s speed=67.9x\nvideo:0kB audio:95kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.232599%\nLY output to `/tmp/tmprvn1r7he/score.ly'...\nChanging working directory to: `/tmp/tmprvn1r7he'\nProcessing `/tmp/tmprvn1r7he/score.ly'\nParsing...\nInterpreting music...[8][8]\nPreprocessing graphical objects...\nInterpreting music...\nMIDI output to `score.midi'...\nFinding the ideal number of pages...\nFitting music on 1 page...\nDrawing systems...\nLayout output to `score.ps'...\nConverting to PNG...\nSuccess: compilation successfully completed",
  "metrics": {
    "predict_time": 5.021412,
    "total_time": 37.472985
  },
  "output": {
    "mp3": "https://replicate.delivery/mgxm/6bdd94b2-624d-4940-b5c4-f69aad428ff0/out.mp3",
    "midi": "https://replicate.delivery/mgxm/93fcf4bc-29be-4869-8430-2fe18146f2b4/out.midi",
    "score": "https://replicate.delivery/mgxm/a9c24d17-7d7e-48f2-9c71-a8830b355ded/score.png"
  },
  "started_at": "2022-05-03T19:30:07.858234Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/ogj47dc2vfcjdhzpyelk5xhqbm",
    "cancel": "https://api.replicate.com/v1/predictions/ogj47dc2vfcjdhzpyelk5xhqbm/cancel"
  },
  "version": "58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1"
}

Generated in

5.0 seconds

Tweak it ShareReport

Using seed: 15564
0.0 141
0.1 12
0.2 9
0.3 7
0.4 6
0.5 5
0.6 4
0.7 3
0.8 3
0.9 2
0:0 (0/1 E4) Em/E 0
0:1 (1/2 F#4) Em/E 0
1:2 (0/1 G4), (1/2 A4) Em/E 0
1:0 (0/1 G4) Em/E 2
1:1  Em/E 6
2:2 (0/1 E4) Em/E 3
2:0 (0/1 A5) Am/A 1
2:1 (1/2 B5) Am/A 8
3:2 (0/1 A5), (1/2 G5) Am/A 6
3:0 (0/1 A5) Am/A 4
3:1  Am/A 2
4:2 (0/1 E5) Am/A 5
4:0 (0/1 D5) G/G 5
4:1 (1/2 E5) G/G 3
5:2 (0/1 D5), (1/2 B4) G/G 7
5:0 (0/1 C#5) Gb7 4
5:1 (1/2 C5) Gb7 7
6:2 (0/1 C#5), (1/2 C5) Gb7 1
6:0 (0/1 B4) B7 0
6:1 (1/2 A4) B7 0
7:2 (0/1 G4), (1/2 F#4) B7 0
7:0 (0/1 E4) Em/E 0
22: Invalid pattern: 0
0 pattern
ffmpeg version 3.4.8-0ubuntu0.2 Copyright (c) 2000-2020 the FFmpeg developers
  built with gcc 7 (Ubuntu 7.5.0-3ubuntu1~18.04)
  configuration: --prefix=/usr --extra-version=0ubuntu0.2 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --enable-gpl --disable-stripping --enable-avresample --enable-avisynth --enable-gnutls --enable-ladspa --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librubberband --enable-librsvg --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvorbis --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzmq --enable-libzvbi --enable-omx --enable-openal --enable-opengl --enable-sdl2 --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libopencv --enable-libx264 --enable-shared
  libavutil      55. 78.100 / 55. 78.100
  libavcodec     57.107.100 / 57.107.100
  libavformat    57. 83.100 / 57. 83.100
  libavdevice    57. 10.100 / 57. 10.100
  libavfilter     6.107.100 /  6.107.100
  libavresample   3.  7.  0 /  3.  7.  0
  libswscale      4.  8.100 /  4.  8.100
  libswresample   2.  9.100 /  2.  9.100
  libpostproc    54.  7.100 / 54.  7.100
Guessed Channel Layout for Input Stream #0.0 : mono
Input #0, wav, from '/tmp/tmprvn1r7he/out.wav':
  Duration: 00:00:12.50, bitrate: 2822 kb/s
    Stream #0:0: Audio: pcm_f64le ([3][0][0][0] / 0x0003), 44100 Hz, mono, dbl, 2822 kb/s
Stream mapping:
  Stream #0:0 -> #0:0 (pcm_f64le (native) -> mp3 (libmp3lame))
Press [q] to stop, [?] for help
Output #0, mp3, to '/tmp/tmprvn1r7he/out.mp3':
  Metadata:
    TSSE            : Lavf57.83.100
    Stream #0:0: Audio: mp3 (libmp3lame), 44100 Hz, mono, fltp
    Metadata:
      encoder         : Lavc57.107.100 libmp3lame
size=      96kB time=00:00:12.17 bitrate=  64.3kbits/s speed=67.9x
video:0kB audio:95kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.232599%
LY output to `/tmp/tmprvn1r7he/score.ly'...
Changing working directory to: `/tmp/tmprvn1r7he'
Processing `/tmp/tmprvn1r7he/score.ly'
Parsing...
Interpreting music...[8][8]
Preprocessing graphical objects...
Interpreting music...
MIDI output to `score.midi'...
Finding the ideal number of pages...
Fitting music on 1 page...
Drawing systems...
Layout output to `score.ps'...
Converting to PNG...
Success: compilation successfully completed

Prediction

andreasjansson/music-inpainting-bert:58bdc207

Model

andreasjansson/music-inpainting-bert:58bdc207

s75tnt2fzndm3f7j23k67ioose

Status

Succeeded

Source

Web

Hardware

–

Total duration

5.8s

Created

almost 3 years ago

Input

seed: -1
notes: e.4 f#8 g a | ? | ? | ? | ? | ? | b.4 a8 g f# | e.2
tempo: "120"
chords: Em | Gm | ? | ? | ? | ? | B7 | Em
sample_width: "20"
time_signature: "3"

{
  "seed": -1,
  "notes": "e.4 f#8 g a | ? | ? | ? | ? | ? | b.4 a8 g f# | e.2",
  "tempo": "120",
  "chords": "Em | Gm | ? | ? | ? | ? | B7 | Em",
  "sample_width": "20",
  "time_signature": "3"
}

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 andreasjansson/music-inpainting-bert using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "andreasjansson/music-inpainting-bert:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1",
  {
    input: {
      seed: -1,
      notes: "e.4 f#8 g a | ? | ? | ? | ? | ? | b.4 a8 g f# | e.2",
      tempo: "120",
      chords: "Em | Gm | ? | ? | ? | ? | B7 | Em",
      sample_width: "20",
      time_signature: "3"
    }
  }
);
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 andreasjansson/music-inpainting-bert using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "andreasjansson/music-inpainting-bert:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1",
    input={
        "seed": -1,
        "notes": "e.4 f#8 g a | ? | ? | ? | ? | ? | b.4 a8 g f# | e.2",
        "tempo": "120",
        "chords": "Em | Gm | ? | ? | ? | ? | B7 | Em",
        "sample_width": "20",
        "time_signature": "3"
    }
)
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 andreasjansson/music-inpainting-bert 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": "58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1",
    "input": {
      "seed": -1,
      "notes": "e.4 f#8 g a | ? | ? | ? | ? | ? | b.4 a8 g f# | e.2",
      "tempo": "120",
      "chords": "Em | Gm | ? | ? | ? | ? | B7 | Em",
      "sample_width": "20",
      "time_signature": "3"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Install Cog

brew install cog

If you don’t have Homebrew, there are other installation options available.

Pull and run andreasjansson/music-inpainting-bert using Cog (this will download the full model and run it in your local environment):

cog predict r8.im/andreasjansson/music-inpainting-bert@sha256:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1 \
  -i 'seed=-1' \
  -i 'notes="e.4 f#8 g a | ? | ? | ? | ? | ? | b.4 a8 g f# | e.2"' \
  -i 'tempo="120"' \
  -i 'chords="Em | Gm | ? | ? | ? | ? | B7 | Em"' \
  -i 'sample_width="20"' \
  -i 'time_signature="3"'

To learn more, take a look at the Cog documentation.

Pull and run andreasjansson/music-inpainting-bert using Docker (this will download the full model and run it in your local environment):

docker run -d -p 5000:5000 --gpus=all r8.im/andreasjansson/music-inpainting-bert@sha256:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "seed": -1,
      "notes": "e.4 f#8 g a | ? | ? | ? | ? | ? | b.4 a8 g f# | e.2",
      "tempo": "120",
      "chords": "Em | Gm | ? | ? | ? | ? | B7 | Em",
      "sample_width": "20",
      "time_signature": "3"
    }
  }' \
  http://localhost:5000/predictions

Output

mp3

Video Player is loading.

Current Time 00:00:000

Duration 00:00:000

Loaded: 0%

Stream Type LIVE

Remaining Time 00:00:000

midi

out.midi

score

{
  "completed_at": "2022-05-03T19:40:26.128693Z",
  "created_at": "2022-05-03T19:40:20.342151Z",
  "data_removed": false,
  "error": null,
  "id": "s75tnt2fzndm3f7j23k67ioose",
  "input": {
    "seed": -1,
    "notes": "e.4 f#8 g a | ? | ? | ? | ? | ? | b.4 a8 g f# | e.2",
    "tempo": "120",
    "chords": "Em | Gm | ? | ? | ? | ? | B7 | Em",
    "sample_width": "20",
    "time_signature": "3"
  },
  "logs": "Using seed: 28689\n0.0 20\n0.0 10\n0.1 10\n0.1 8\n0.2 8\n0.2 6\n0.3 6\n0.3 6\n0.4 5\n0.4 5\n0.5 5\n0.5 4\n0.6 4\n0.6 4\n0.7 3\n0.7 3\n0.8 3\n0.8 2\n0.9 2\n0.9 2\n0:0 (0/1 E4) Em/E 0\n0:1 (1/2 F#4) Em/E 0\n1:2 (0/1 G4), (1/2 A4) Em/E 0\n1:0 (0/1 E4) Gm/G 6\n1:1 (1/2 F#4) Gm/G 3\n2:2 (0/1 G4), (1/2 A4) Gm/G 5\n2:0 (0/1 B4) B7 4\n2:1 (1/2 A4) Em/E 8\n3:2 (0/1 G4), (1/2 F#4) B7 6\n3:0 (0/1 E4) Em/E 2\n3:1 (0/1 F#4) B/B 7\n4:2 (0/1 E4) Em/E 1\n4:0 (0/1 E4) Em/E 2\n4:1 (1/2 F#4) Em/E 5\n5:2 (0/1 G4), (1/2 F#4) Em/E 4\n5:0 (0/1 A4) Em/E 1\n5:1 (1/2 G4) Em/E 7\n6:2 (0/1 B4) D/D 3\n6:0 (0/1 B4) B7 0\n6:1 (1/2 A4) B7 0\n7:2 (0/1 G4), (1/2 F#4) B7 0\n7:0 (0/1 E4) Em/E 0\n22: Invalid pattern: 0\n0 pattern\nffmpeg version 3.4.8-0ubuntu0.2 Copyright (c) 2000-2020 the FFmpeg developers\n  built with gcc 7 (Ubuntu 7.5.0-3ubuntu1~18.04)\n  configuration: --prefix=/usr --extra-version=0ubuntu0.2 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --enable-gpl --disable-stripping --enable-avresample --enable-avisynth --enable-gnutls --enable-ladspa --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librubberband --enable-librsvg --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvorbis --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzmq --enable-libzvbi --enable-omx --enable-openal --enable-opengl --enable-sdl2 --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libopencv --enable-libx264 --enable-shared\n  libavutil      55. 78.100 / 55. 78.100\n  libavcodec     57.107.100 / 57.107.100\n  libavformat    57. 83.100 / 57. 83.100\n  libavdevice    57. 10.100 / 57. 10.100\n  libavfilter     6.107.100 /  6.107.100\n  libavresample   3.  7.  0 /  3.  7.  0\n  libswscale      4.  8.100 /  4.  8.100\n  libswresample   2.  9.100 /  2.  9.100\n  libpostproc    54.  7.100 / 54.  7.100\nGuessed Channel Layout for Input Stream #0.0 : mono\nInput #0, wav, from '/tmp/tmp1dnjwv2e/out.wav':\n  Duration: 00:00:12.50, bitrate: 2822 kb/s\n    Stream #0:0: Audio: pcm_f64le ([3][0][0][0] / 0x0003), 44100 Hz, mono, dbl, 2822 kb/s\nStream mapping:\n  Stream #0:0 -> #0:0 (pcm_f64le (native) -> mp3 (libmp3lame))\nPress [q] to stop, [?] for help\nOutput #0, mp3, to '/tmp/tmp1dnjwv2e/out.mp3':\n  Metadata:\n    TSSE            : Lavf57.83.100\n    Stream #0:0: Audio: mp3 (libmp3lame), 44100 Hz, mono, fltp\n    Metadata:\n      encoder         : Lavc57.107.100 libmp3lame\nsize=      96kB time=00:00:12.17 bitrate=  64.3kbits/s speed=68.7x\nvideo:0kB audio:95kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.232599%\nLY output to `/tmp/tmp1dnjwv2e/score.ly'...\nChanging working directory to: `/tmp/tmp1dnjwv2e'\nProcessing `/tmp/tmp1dnjwv2e/score.ly'\nParsing...\nInterpreting music...[8][8]\nPreprocessing graphical objects...\nInterpreting music...\nMIDI output to `score.midi'...\nFinding the ideal number of pages...\nFitting music on 1 page...\nDrawing systems...\nLayout output to `score.ps'...\nConverting to PNG...\nSuccess: compilation successfully completed",
  "metrics": {
    "predict_time": 5.467024,
    "total_time": 5.786542
  },
  "output": {
    "mp3": "https://replicate.delivery/mgxm/622fb988-66ef-4750-a4a7-17e272a2b563/out.mp3",
    "midi": "https://replicate.delivery/mgxm/26998427-15ca-4bd7-aa1b-488cf1f09037/out.midi",
    "score": "https://replicate.delivery/mgxm/b0e22731-7e46-4f81-a3e2-6f9efc975eae/score.png"
  },
  "started_at": "2022-05-03T19:40:20.661669Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/s75tnt2fzndm3f7j23k67ioose",
    "cancel": "https://api.replicate.com/v1/predictions/s75tnt2fzndm3f7j23k67ioose/cancel"
  },
  "version": "58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1"
}

Generated in

5.5 seconds

Tweak it ShareReport

Using seed: 28689
0.0 20
0.0 10
0.1 10
0.1 8
0.2 8
0.2 6
0.3 6
0.3 6
0.4 5
0.4 5
0.5 5
0.5 4
0.6 4
0.6 4
0.7 3
0.7 3
0.8 3
0.8 2
0.9 2
0.9 2
0:0 (0/1 E4) Em/E 0
0:1 (1/2 F#4) Em/E 0
1:2 (0/1 G4), (1/2 A4) Em/E 0
1:0 (0/1 E4) Gm/G 6
1:1 (1/2 F#4) Gm/G 3
2:2 (0/1 G4), (1/2 A4) Gm/G 5
2:0 (0/1 B4) B7 4
2:1 (1/2 A4) Em/E 8
3:2 (0/1 G4), (1/2 F#4) B7 6
3:0 (0/1 E4) Em/E 2
3:1 (0/1 F#4) B/B 7
4:2 (0/1 E4) Em/E 1
4:0 (0/1 E4) Em/E 2
4:1 (1/2 F#4) Em/E 5
5:2 (0/1 G4), (1/2 F#4) Em/E 4
5:0 (0/1 A4) Em/E 1
5:1 (1/2 G4) Em/E 7
6:2 (0/1 B4) D/D 3
6:0 (0/1 B4) B7 0
6:1 (1/2 A4) B7 0
7:2 (0/1 G4), (1/2 F#4) B7 0
7:0 (0/1 E4) Em/E 0
22: Invalid pattern: 0
0 pattern
ffmpeg version 3.4.8-0ubuntu0.2 Copyright (c) 2000-2020 the FFmpeg developers
  built with gcc 7 (Ubuntu 7.5.0-3ubuntu1~18.04)
  configuration: --prefix=/usr --extra-version=0ubuntu0.2 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --enable-gpl --disable-stripping --enable-avresample --enable-avisynth --enable-gnutls --enable-ladspa --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librubberband --enable-librsvg --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvorbis --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzmq --enable-libzvbi --enable-omx --enable-openal --enable-opengl --enable-sdl2 --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libopencv --enable-libx264 --enable-shared
  libavutil      55. 78.100 / 55. 78.100
  libavcodec     57.107.100 / 57.107.100
  libavformat    57. 83.100 / 57. 83.100
  libavdevice    57. 10.100 / 57. 10.100
  libavfilter     6.107.100 /  6.107.100
  libavresample   3.  7.  0 /  3.  7.  0
  libswscale      4.  8.100 /  4.  8.100
  libswresample   2.  9.100 /  2.  9.100
  libpostproc    54.  7.100 / 54.  7.100
Guessed Channel Layout for Input Stream #0.0 : mono
Input #0, wav, from '/tmp/tmp1dnjwv2e/out.wav':
  Duration: 00:00:12.50, bitrate: 2822 kb/s
    Stream #0:0: Audio: pcm_f64le ([3][0][0][0] / 0x0003), 44100 Hz, mono, dbl, 2822 kb/s
Stream mapping:
  Stream #0:0 -> #0:0 (pcm_f64le (native) -> mp3 (libmp3lame))
Press [q] to stop, [?] for help
Output #0, mp3, to '/tmp/tmp1dnjwv2e/out.mp3':
  Metadata:
    TSSE            : Lavf57.83.100
    Stream #0:0: Audio: mp3 (libmp3lame), 44100 Hz, mono, fltp
    Metadata:
      encoder         : Lavc57.107.100 libmp3lame
size=      96kB time=00:00:12.17 bitrate=  64.3kbits/s speed=68.7x
video:0kB audio:95kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.232599%
LY output to `/tmp/tmp1dnjwv2e/score.ly'...
Changing working directory to: `/tmp/tmp1dnjwv2e'
Processing `/tmp/tmp1dnjwv2e/score.ly'
Parsing...
Interpreting music...[8][8]
Preprocessing graphical objects...
Interpreting music...
MIDI output to `score.midi'...
Finding the ideal number of pages...
Fitting music on 1 page...
Drawing systems...
Layout output to `score.ps'...
Converting to PNG...
Success: compilation successfully completed

Prediction

andreasjansson/music-inpainting-bert:58bdc207

Model

andreasjansson/music-inpainting-bert:58bdc207

qfzlgox7krattbnistlqzyq6qe

Status

Succeeded

Source

Web

Hardware

–

Total duration

53.7s

Created

almost 3 years ago

Input

seed: -1
notes: e2 f#4 | g.4 f#8 e4 | b2 b4 | b.2 | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | e.2
tempo: "100"
chords: Em | Em | Em | Em | Fm | Fm | Em | Em | Fm | Fm | Em | Em | B7 | B7 | Em | Em
sample_width: "80"
time_signature: "3"

{
  "seed": -1,
  "notes": "e2 f#4 | g.4 f#8 e4 | b2 b4 | b.2 | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | e.2",
  "tempo": "100",
  "chords": "Em | Em | Em | Em | Fm | Fm | Em | Em | Fm | Fm | Em | Em | B7 | B7 | Em | Em",
  "sample_width": "80",
  "time_signature": "3"
}

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 andreasjansson/music-inpainting-bert using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "andreasjansson/music-inpainting-bert:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1",
  {
    input: {
      seed: -1,
      notes: "e2 f#4 | g.4 f#8 e4 | b2 b4 | b.2 | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | e.2",
      tempo: "100",
      chords: "Em | Em | Em | Em | Fm | Fm | Em | Em | Fm | Fm | Em | Em | B7 | B7 | Em | Em",
      sample_width: "80",
      time_signature: "3"
    }
  }
);
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 andreasjansson/music-inpainting-bert using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "andreasjansson/music-inpainting-bert:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1",
    input={
        "seed": -1,
        "notes": "e2 f#4 | g.4 f#8 e4 | b2 b4 | b.2 | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | e.2",
        "tempo": "100",
        "chords": "Em | Em | Em | Em | Fm | Fm | Em | Em | Fm | Fm | Em | Em | B7 | B7 | Em | Em",
        "sample_width": "80",
        "time_signature": "3"
    }
)
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 andreasjansson/music-inpainting-bert 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": "58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1",
    "input": {
      "seed": -1,
      "notes": "e2 f#4 | g.4 f#8 e4 | b2 b4 | b.2 | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | e.2",
      "tempo": "100",
      "chords": "Em | Em | Em | Em | Fm | Fm | Em | Em | Fm | Fm | Em | Em | B7 | B7 | Em | Em",
      "sample_width": "80",
      "time_signature": "3"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Install Cog

brew install cog

If you don’t have Homebrew, there are other installation options available.

Pull and run andreasjansson/music-inpainting-bert using Cog (this will download the full model and run it in your local environment):

cog predict r8.im/andreasjansson/music-inpainting-bert@sha256:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1 \
  -i 'seed=-1' \
  -i 'notes="e2 f#4 | g.4 f#8 e4 | b2 b4 | b.2 | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | e.2"' \
  -i 'tempo="100"' \
  -i 'chords="Em | Em | Em | Em | Fm | Fm | Em | Em | Fm | Fm | Em | Em | B7 | B7 | Em | Em"' \
  -i 'sample_width="80"' \
  -i 'time_signature="3"'

To learn more, take a look at the Cog documentation.

Pull and run andreasjansson/music-inpainting-bert using Docker (this will download the full model and run it in your local environment):

docker run -d -p 5000:5000 --gpus=all r8.im/andreasjansson/music-inpainting-bert@sha256:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "seed": -1,
      "notes": "e2 f#4 | g.4 f#8 e4 | b2 b4 | b.2 | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | e.2",
      "tempo": "100",
      "chords": "Em | Em | Em | Em | Fm | Fm | Em | Em | Fm | Fm | Em | Em | B7 | B7 | Em | Em",
      "sample_width": "80",
      "time_signature": "3"
    }
  }' \
  http://localhost:5000/predictions

Output

mp3

Video Player is loading.

Current Time 00:00:000

Duration 00:00:000

Loaded: 0%

Stream Type LIVE

Remaining Time 00:00:000

midi

out.midi

score

{
  "completed_at": "2022-05-03T19:30:32.763896Z",
  "created_at": "2022-05-03T19:29:39.113688Z",
  "data_removed": false,
  "error": null,
  "id": "qfzlgox7krattbnistlqzyq6qe",
  "input": {
    "seed": -1,
    "notes": "e2 f#4 | g.4 f#8 e4 | b2 b4 | b.2 | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | e.2",
    "tempo": "100",
    "chords": "Em | Em | Em | Em | Fm | Fm | Em | Em | Fm | Fm | Em | Em | B7 | B7 | Em | Em",
    "sample_width": "80",
    "time_signature": "3"
  },
  "logs": "Using seed: 15436\n0.0 80\n0.1 12\n0.2 9\n0.3 7\n0.4 6\n0.5 5\n0.6 4\n0.7 3\n0.8 3\n0.9 2\n0:0 (0/1 E4) Em/E 0\n0:1  Em/E 0\n1:2 (0/1 F#4) Em/E 0\n1:0 (0/1 G4) Em/E 0\n1:1 (1/2 F#4) Em/E 0\n2:2 (0/1 E4) Em/E 0\n2:0 (0/1 B4) Em/E 0\n2:1  Em/E 0\n3:2 (0/1 B4) Em/E 0\n3:0 (0/1 B4) Em/E 0\n3:1  Em/E 0\n4:2  Em/E 0\n4:0 (0/1 G#4) Fm/F 6\n4:1  Fm/F 6\n5:2 (0/1 F4) Fm/F 5\n5:0 (0/1 G#4) Fm/F 4\n5:1  Fm/F 1\n6:2  Fm/F 2\n6:0 (0/1 G4) Em/E 3\n6:1 (0/1 E4) Em/E 8\n7:2  Em/E 8\n7:0  Em/E 5\n7:1  Em/E 5\n8:2  Em/E 6\n8:0 (0/1 F5) Fm/F 7\n8:1  Fm/F 4\n9:2 (0/1 F5) Fm/F 3\n9:0 (0/1 F5) Fm/F 2\n9:1  Fm/F 4\n10:2  Fm/F 9\n10:0 (0/1 E5) Em/E 3\n10:1  Em/E 5\n11:2 (0/1 B4) Em/E 7\n11:0 (0/1 B4) Em/E 2\n11:1  Em/E 4\n12:2  Em/E 2\n12:0 (0/1 F#4) B7 3\n12:1 (0/1 B4) B7 1\n13:2 (0/1 E-5) B7 8\n13:0 (0/1 F#5) B7 7\n13:1 (1/2 E5) B7 1\n14:2 (0/1 E-5) B7 6\n14:0 (0/1 B4) Em/E 7\n14:1  Em/E 8\n15:2 (0/1 E4), (1/2 G4) Em/E 1\n15:0 (0/1 E4) Em/E 0\n46: Invalid pattern: 0\n0 pattern\nffmpeg version 3.4.8-0ubuntu0.2 Copyright (c) 2000-2020 the FFmpeg developers\n  built with gcc 7 (Ubuntu 7.5.0-3ubuntu1~18.04)\n  configuration: --prefix=/usr --extra-version=0ubuntu0.2 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --enable-gpl --disable-stripping --enable-avresample --enable-avisynth --enable-gnutls --enable-ladspa --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librubberband --enable-librsvg --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvorbis --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzmq --enable-libzvbi --enable-omx --enable-openal --enable-opengl --enable-sdl2 --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libopencv --enable-libx264 --enable-shared\n  libavutil      55. 78.100 / 55. 78.100\n  libavcodec     57.107.100 / 57.107.100\n  libavformat    57. 83.100 / 57. 83.100\n  libavdevice    57. 10.100 / 57. 10.100\n  libavfilter     6.107.100 /  6.107.100\n  libavresample   3.  7.  0 /  3.  7.  0\n  libswscale      4.  8.100 /  4.  8.100\n  libswresample   2.  9.100 /  2.  9.100\n  libpostproc    54.  7.100 / 54.  7.100\nGuessed Channel Layout for Input Stream #0.0 : mono\nInput #0, wav, from '/tmp/tmp_345nbx1/out.wav':\n  Duration: 00:00:29.20, bitrate: 2822 kb/s\n    Stream #0:0: Audio: pcm_f64le ([3][0][0][0] / 0x0003), 44100 Hz, mono, dbl, 2822 kb/s\nStream mapping:\n  Stream #0:0 -> #0:0 (pcm_f64le (native) -> mp3 (libmp3lame))\nPress [q] to stop, [?] for help\nOutput #0, mp3, to '/tmp/tmp_345nbx1/out.mp3':\n  Metadata:\n    TSSE            : Lavf57.83.100\n    Stream #0:0: Audio: mp3 (libmp3lame), 44100 Hz, mono, fltp\n    Metadata:\n      encoder         : Lavc57.107.100 libmp3lame\nsize=     226kB time=00:00:28.83 bitrate=  64.1kbits/s speed=71.9x\nvideo:0kB audio:226kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.098302%\nLY output to `/tmp/tmp_345nbx1/score.ly'...\nChanging working directory to: `/tmp/tmp_345nbx1'\nProcessing `/tmp/tmp_345nbx1/score.ly'\nParsing...\nInterpreting music...[8][16][16]\nPreprocessing graphical objects...\nInterpreting music...\nMIDI output to `score.midi'...\nFinding the ideal number of pages...\nFitting music on 1 page...\nDrawing systems...\nLayout output to `score.ps'...\nConverting to PNG...\nSuccess: compilation successfully completed",
  "metrics": {
    "predict_time": 20.019826,
    "total_time": 53.650208
  },
  "output": {
    "mp3": "https://replicate.delivery/mgxm/70f4aa51-bf99-471b-b9f0-a6ffc234926e/out.mp3",
    "midi": "https://replicate.delivery/mgxm/4a3375d4-e29e-4fbd-8351-0641e0466a21/out.midi",
    "score": "https://replicate.delivery/mgxm/4fd2a875-d3a5-47f9-bfcf-b7cd8a99ca1c/score.png"
  },
  "started_at": "2022-05-03T19:30:12.744070Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/qfzlgox7krattbnistlqzyq6qe",
    "cancel": "https://api.replicate.com/v1/predictions/qfzlgox7krattbnistlqzyq6qe/cancel"
  },
  "version": "58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1"
}

Generated in

20.0 seconds

Tweak it ShareReport

Using seed: 15436
0.0 80
0.1 12
0.2 9
0.3 7
0.4 6
0.5 5
0.6 4
0.7 3
0.8 3
0.9 2
0:0 (0/1 E4) Em/E 0
0:1  Em/E 0
1:2 (0/1 F#4) Em/E 0
1:0 (0/1 G4) Em/E 0
1:1 (1/2 F#4) Em/E 0
2:2 (0/1 E4) Em/E 0
2:0 (0/1 B4) Em/E 0
2:1  Em/E 0
3:2 (0/1 B4) Em/E 0
3:0 (0/1 B4) Em/E 0
3:1  Em/E 0
4:2  Em/E 0
4:0 (0/1 G#4) Fm/F 6
4:1  Fm/F 6
5:2 (0/1 F4) Fm/F 5
5:0 (0/1 G#4) Fm/F 4
5:1  Fm/F 1
6:2  Fm/F 2
6:0 (0/1 G4) Em/E 3
6:1 (0/1 E4) Em/E 8
7:2  Em/E 8
7:0  Em/E 5
7:1  Em/E 5
8:2  Em/E 6
8:0 (0/1 F5) Fm/F 7
8:1  Fm/F 4
9:2 (0/1 F5) Fm/F 3
9:0 (0/1 F5) Fm/F 2
9:1  Fm/F 4
10:2  Fm/F 9
10:0 (0/1 E5) Em/E 3
10:1  Em/E 5
11:2 (0/1 B4) Em/E 7
11:0 (0/1 B4) Em/E 2
11:1  Em/E 4
12:2  Em/E 2
12:0 (0/1 F#4) B7 3
12:1 (0/1 B4) B7 1
13:2 (0/1 E-5) B7 8
13:0 (0/1 F#5) B7 7
13:1 (1/2 E5) B7 1
14:2 (0/1 E-5) B7 6
14:0 (0/1 B4) Em/E 7
14:1  Em/E 8
15:2 (0/1 E4), (1/2 G4) Em/E 1
15:0 (0/1 E4) Em/E 0
46: Invalid pattern: 0
0 pattern
ffmpeg version 3.4.8-0ubuntu0.2 Copyright (c) 2000-2020 the FFmpeg developers
  built with gcc 7 (Ubuntu 7.5.0-3ubuntu1~18.04)
  configuration: --prefix=/usr --extra-version=0ubuntu0.2 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --enable-gpl --disable-stripping --enable-avresample --enable-avisynth --enable-gnutls --enable-ladspa --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librubberband --enable-librsvg --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvorbis --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzmq --enable-libzvbi --enable-omx --enable-openal --enable-opengl --enable-sdl2 --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libopencv --enable-libx264 --enable-shared
  libavutil      55. 78.100 / 55. 78.100
  libavcodec     57.107.100 / 57.107.100
  libavformat    57. 83.100 / 57. 83.100
  libavdevice    57. 10.100 / 57. 10.100
  libavfilter     6.107.100 /  6.107.100
  libavresample   3.  7.  0 /  3.  7.  0
  libswscale      4.  8.100 /  4.  8.100
  libswresample   2.  9.100 /  2.  9.100
  libpostproc    54.  7.100 / 54.  7.100
Guessed Channel Layout for Input Stream #0.0 : mono
Input #0, wav, from '/tmp/tmp_345nbx1/out.wav':
  Duration: 00:00:29.20, bitrate: 2822 kb/s
    Stream #0:0: Audio: pcm_f64le ([3][0][0][0] / 0x0003), 44100 Hz, mono, dbl, 2822 kb/s
Stream mapping:
  Stream #0:0 -> #0:0 (pcm_f64le (native) -> mp3 (libmp3lame))
Press [q] to stop, [?] for help
Output #0, mp3, to '/tmp/tmp_345nbx1/out.mp3':
  Metadata:
    TSSE            : Lavf57.83.100
    Stream #0:0: Audio: mp3 (libmp3lame), 44100 Hz, mono, fltp
    Metadata:
      encoder         : Lavc57.107.100 libmp3lame
size=     226kB time=00:00:28.83 bitrate=  64.1kbits/s speed=71.9x
video:0kB audio:226kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.098302%
LY output to `/tmp/tmp_345nbx1/score.ly'...
Changing working directory to: `/tmp/tmp_345nbx1'
Processing `/tmp/tmp_345nbx1/score.ly'
Parsing...
Interpreting music...[8][16][16]
Preprocessing graphical objects...
Interpreting music...
MIDI output to `score.midi'...
Finding the ideal number of pages...
Fitting music on 1 page...
Drawing systems...
Layout output to `score.ps'...
Converting to PNG...
Success: compilation successfully completed

Prediction

andreasjansson/music-inpainting-bert:58bdc207

Model

andreasjansson/music-inpainting-bert:58bdc207

6d4inmhz6vadrpbq6g7zgmrbu4

Status

Succeeded

Source

Web

Hardware

–

Total duration

7.6s

Created

almost 3 years ago by @andreasjansson

Input

seed: -1
notes: e2 f#4 | g.4 f#8 e4 | b2 b4 | b.2 | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | e.2
tempo: "100"
chords: Em | Em | Em | Em | Am | Am | ? | ? | ? | ? | ? | ? | B7 | B7 | Em | Em
sample_width: "80"
time_signature: "3"

{
  "seed": -1,
  "notes": "e2 f#4 | g.4 f#8 e4 | b2 b4 | b.2 | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | e.2",
  "tempo": "100",
  "chords": "Em | Em | Em | Em | Am | Am | ? | ? | ? | ? | ? | ? | B7 | B7 | Em | Em",
  "sample_width": "80",
  "time_signature": "3"
}

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 andreasjansson/music-inpainting-bert using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "andreasjansson/music-inpainting-bert:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1",
  {
    input: {
      seed: -1,
      notes: "e2 f#4 | g.4 f#8 e4 | b2 b4 | b.2 | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | e.2",
      tempo: "100",
      chords: "Em | Em | Em | Em | Am | Am | ? | ? | ? | ? | ? | ? | B7 | B7 | Em | Em",
      sample_width: "80",
      time_signature: "3"
    }
  }
);
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 andreasjansson/music-inpainting-bert using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "andreasjansson/music-inpainting-bert:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1",
    input={
        "seed": -1,
        "notes": "e2 f#4 | g.4 f#8 e4 | b2 b4 | b.2 | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | e.2",
        "tempo": "100",
        "chords": "Em | Em | Em | Em | Am | Am | ? | ? | ? | ? | ? | ? | B7 | B7 | Em | Em",
        "sample_width": "80",
        "time_signature": "3"
    }
)
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 andreasjansson/music-inpainting-bert 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": "58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1",
    "input": {
      "seed": -1,
      "notes": "e2 f#4 | g.4 f#8 e4 | b2 b4 | b.2 | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | e.2",
      "tempo": "100",
      "chords": "Em | Em | Em | Em | Am | Am | ? | ? | ? | ? | ? | ? | B7 | B7 | Em | Em",
      "sample_width": "80",
      "time_signature": "3"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Install Cog

brew install cog

If you don’t have Homebrew, there are other installation options available.

Pull and run andreasjansson/music-inpainting-bert using Cog (this will download the full model and run it in your local environment):

cog predict r8.im/andreasjansson/music-inpainting-bert@sha256:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1 \
  -i 'seed=-1' \
  -i 'notes="e2 f#4 | g.4 f#8 e4 | b2 b4 | b.2 | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | e.2"' \
  -i 'tempo="100"' \
  -i 'chords="Em | Em | Em | Em | Am | Am | ? | ? | ? | ? | ? | ? | B7 | B7 | Em | Em"' \
  -i 'sample_width="80"' \
  -i 'time_signature="3"'

To learn more, take a look at the Cog documentation.

Pull and run andreasjansson/music-inpainting-bert using Docker (this will download the full model and run it in your local environment):

docker run -d -p 5000:5000 --gpus=all r8.im/andreasjansson/music-inpainting-bert@sha256:58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "seed": -1,
      "notes": "e2 f#4 | g.4 f#8 e4 | b2 b4 | b.2 | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | e.2",
      "tempo": "100",
      "chords": "Em | Em | Em | Em | Am | Am | ? | ? | ? | ? | ? | ? | B7 | B7 | Em | Em",
      "sample_width": "80",
      "time_signature": "3"
    }
  }' \
  http://localhost:5000/predictions

Output

mp3

Video Player is loading.

Current Time 00:00:000

Duration 00:00:000

Loaded: 0%

Stream Type LIVE

Remaining Time 00:00:000

midi

out.midi

score

{
  "completed_at": "2022-05-03T19:42:15.728031Z",
  "created_at": "2022-05-03T19:42:08.098990Z",
  "data_removed": false,
  "error": null,
  "id": "6d4inmhz6vadrpbq6g7zgmrbu4",
  "input": {
    "seed": -1,
    "notes": "e2 f#4 | g.4 f#8 e4 | b2 b4 | b.2 | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | ? | e.2",
    "tempo": "100",
    "chords": "Em | Em | Em | Em | Am | Am | ? | ? | ? | ? | ? | ? | B7 | B7 | Em | Em",
    "sample_width": "80",
    "time_signature": "3"
  },
  "logs": "Using seed: 23529\n0.0 80\n0.0 10\n0.1 12\n0.1 8\n0.2 9\n0.2 6\n0.3 7\n0.3 6\n0.4 6\n0.4 5\n0.5 5\n0.5 4\n0.6 4\n0.6 4\n0.7 3\n0.7 3\n0.8 3\n0.8 2\n0.9 2\n0.9 2\n0:0 (0/1 E4) Em/E 0\n0:1  Em/E 0\n1:2 (0/1 F#4) Em/E 0\n1:0 (0/1 G4) Em/E 0\n1:1 (1/2 F#4) Em/E 0\n2:2 (0/1 E4) Em/E 0\n2:0 (0/1 B4) Em/E 0\n2:1  Em/E 0\n3:2 (0/1 B4) Em/E 0\n3:0 (0/1 B4) Em/E 0\n3:1  Em/E 0\n4:2  Em/E 0\n4:0 (0/1 G4) Am/A 7\n4:1 (0/1 F#4) Am/A 4\n5:2 (0/1 E4) Am/A 6\n5:0 (0/1 G4) Am/A 3\n5:1 (0/1 F#4) Am/A 5\n6:2 (0/1 E4) Am/A 1\n6:0 (0/1 F#4) Em/E 7\n6:1 (0/1 E4) Em/E 2\n7:2 (0/1 G4) Em/E 5\n7:0 (0/1 B4) Em/E 4\n7:1  Em/E 8\n8:2  Em/E 8\n8:0 (0/1 B4) Em/E 3\n8:1  Em/E 5\n9:2 (0/1 B4), (1/2 B4) Em/E 6\n9:0 (0/1 B4) Am/A 2\n9:1 (0/1 A4) Am/A 6\n10:2 (0/1 G4) Am/A 7\n10:0 (0/1 B4), (1/2 G4) Em/E 1\n10:1 (0/1 E4) Em/E 4\n11:2  Em/E 2\n11:0 (0/1 E4) Em/E 2\n11:1 (0/1 E-4) Em/E 9\n12:2 (0/1 D4) Em/E 1\n12:0 (0/1 E-4) B7 3\n12:1  B7 4\n13:2 (0/1 E-4), (1/2 E-4) B7 7\n13:0 (0/1 F#4) B7 5\n13:1 (0/1 E-4) B7 3\n14:2 (1/2 B3) B7 1\n14:0 (0/1 E4) Em/E 6\n14:1  Em/E 8\n15:2  Em/E 8\n15:0 (0/1 E4) Em/E 0\n46: Invalid pattern: 0\n0 pattern\nffmpeg version 3.4.8-0ubuntu0.2 Copyright (c) 2000-2020 the FFmpeg developers\n  built with gcc 7 (Ubuntu 7.5.0-3ubuntu1~18.04)\n  configuration: --prefix=/usr --extra-version=0ubuntu0.2 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --enable-gpl --disable-stripping --enable-avresample --enable-avisynth --enable-gnutls --enable-ladspa --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librubberband --enable-librsvg --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvorbis --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzmq --enable-libzvbi --enable-omx --enable-openal --enable-opengl --enable-sdl2 --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libopencv --enable-libx264 --enable-shared\n  libavutil      55. 78.100 / 55. 78.100\n  libavcodec     57.107.100 / 57.107.100\n  libavformat    57. 83.100 / 57. 83.100\n  libavdevice    57. 10.100 / 57. 10.100\n  libavfilter     6.107.100 /  6.107.100\n  libavresample   3.  7.  0 /  3.  7.  0\n  libswscale      4.  8.100 /  4.  8.100\n  libswresample   2.  9.100 /  2.  9.100\n  libpostproc    54.  7.100 / 54.  7.100\nGuessed Channel Layout for Input Stream #0.0 : mono\nInput #0, wav, from '/tmp/tmp_fuotcp4/out.wav':\n  Duration: 00:00:29.20, bitrate: 2822 kb/s\n    Stream #0:0: Audio: pcm_f64le ([3][0][0][0] / 0x0003), 44100 Hz, mono, dbl, 2822 kb/s\nStream mapping:\n  Stream #0:0 -> #0:0 (pcm_f64le (native) -> mp3 (libmp3lame))\nPress [q] to stop, [?] for help\nOutput #0, mp3, to '/tmp/tmp_fuotcp4/out.mp3':\n  Metadata:\n    TSSE            : Lavf57.83.100\n    Stream #0:0: Audio: mp3 (libmp3lame), 44100 Hz, mono, fltp\n    Metadata:\n      encoder         : Lavc57.107.100 libmp3lame\nsize=     226kB time=00:00:28.83 bitrate=  64.1kbits/s speed=68.2x\nvideo:0kB audio:226kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.098302%\nLY output to `/tmp/tmp_fuotcp4/score.ly'...\nChanging working directory to: `/tmp/tmp_fuotcp4'\nProcessing `/tmp/tmp_fuotcp4/score.ly'\nParsing...\nInterpreting music...[8][16][16]\nPreprocessing graphical objects...\nInterpreting music...\nMIDI output to `score.midi'...\nFinding the ideal number of pages...\nFitting music on 1 page...\nDrawing systems...\nLayout output to `score.ps'...\nConverting to PNG...\nSuccess: compilation successfully completed",
  "metrics": {
    "predict_time": 7.443402,
    "total_time": 7.629041
  },
  "output": {
    "mp3": "https://replicate.delivery/mgxm/967ac956-4d23-4b2e-8d25-70165285ced9/out.mp3",
    "midi": "https://replicate.delivery/mgxm/380e6ecf-b993-4e2e-9743-6efd965fca28/out.midi",
    "score": "https://replicate.delivery/mgxm/fd0dd91d-939c-447d-b252-83d920918c22/score.png"
  },
  "started_at": "2022-05-03T19:42:08.284629Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/6d4inmhz6vadrpbq6g7zgmrbu4",
    "cancel": "https://api.replicate.com/v1/predictions/6d4inmhz6vadrpbq6g7zgmrbu4/cancel"
  },
  "version": "58bdc2073c9c07abcc4200fe808e15b1a555dbb1390e70f5daa6b3d81bd11fb1"
}

Generated in

7.5 seconds

Tweak it ShareReport

Using seed: 23529
0.0 80
0.0 10
0.1 12
0.1 8
0.2 9
0.2 6
0.3 7
0.3 6
0.4 6
0.4 5
0.5 5
0.5 4
0.6 4
0.6 4
0.7 3
0.7 3
0.8 3
0.8 2
0.9 2
0.9 2
0:0 (0/1 E4) Em/E 0
0:1  Em/E 0
1:2 (0/1 F#4) Em/E 0
1:0 (0/1 G4) Em/E 0
1:1 (1/2 F#4) Em/E 0
2:2 (0/1 E4) Em/E 0
2:0 (0/1 B4) Em/E 0
2:1  Em/E 0
3:2 (0/1 B4) Em/E 0
3:0 (0/1 B4) Em/E 0
3:1  Em/E 0
4:2  Em/E 0
4:0 (0/1 G4) Am/A 7
4:1 (0/1 F#4) Am/A 4
5:2 (0/1 E4) Am/A 6
5:0 (0/1 G4) Am/A 3
5:1 (0/1 F#4) Am/A 5
6:2 (0/1 E4) Am/A 1
6:0 (0/1 F#4) Em/E 7
6:1 (0/1 E4) Em/E 2
7:2 (0/1 G4) Em/E 5
7:0 (0/1 B4) Em/E 4
7:1  Em/E 8
8:2  Em/E 8
8:0 (0/1 B4) Em/E 3
8:1  Em/E 5
9:2 (0/1 B4), (1/2 B4) Em/E 6
9:0 (0/1 B4) Am/A 2
9:1 (0/1 A4) Am/A 6
10:2 (0/1 G4) Am/A 7
10:0 (0/1 B4), (1/2 G4) Em/E 1
10:1 (0/1 E4) Em/E 4
11:2  Em/E 2
11:0 (0/1 E4) Em/E 2
11:1 (0/1 E-4) Em/E 9
12:2 (0/1 D4) Em/E 1
12:0 (0/1 E-4) B7 3
12:1  B7 4
13:2 (0/1 E-4), (1/2 E-4) B7 7
13:0 (0/1 F#4) B7 5
13:1 (0/1 E-4) B7 3
14:2 (1/2 B3) B7 1
14:0 (0/1 E4) Em/E 6
14:1  Em/E 8
15:2  Em/E 8
15:0 (0/1 E4) Em/E 0
46: Invalid pattern: 0
0 pattern
ffmpeg version 3.4.8-0ubuntu0.2 Copyright (c) 2000-2020 the FFmpeg developers
  built with gcc 7 (Ubuntu 7.5.0-3ubuntu1~18.04)
  configuration: --prefix=/usr --extra-version=0ubuntu0.2 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --enable-gpl --disable-stripping --enable-avresample --enable-avisynth --enable-gnutls --enable-ladspa --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librubberband --enable-librsvg --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvorbis --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzmq --enable-libzvbi --enable-omx --enable-openal --enable-opengl --enable-sdl2 --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libopencv --enable-libx264 --enable-shared
  libavutil      55. 78.100 / 55. 78.100
  libavcodec     57.107.100 / 57.107.100
  libavformat    57. 83.100 / 57. 83.100
  libavdevice    57. 10.100 / 57. 10.100
  libavfilter     6.107.100 /  6.107.100
  libavresample   3.  7.  0 /  3.  7.  0
  libswscale      4.  8.100 /  4.  8.100
  libswresample   2.  9.100 /  2.  9.100
  libpostproc    54.  7.100 / 54.  7.100
Guessed Channel Layout for Input Stream #0.0 : mono
Input #0, wav, from '/tmp/tmp_fuotcp4/out.wav':
  Duration: 00:00:29.20, bitrate: 2822 kb/s
    Stream #0:0: Audio: pcm_f64le ([3][0][0][0] / 0x0003), 44100 Hz, mono, dbl, 2822 kb/s
Stream mapping:
  Stream #0:0 -> #0:0 (pcm_f64le (native) -> mp3 (libmp3lame))
Press [q] to stop, [?] for help
Output #0, mp3, to '/tmp/tmp_fuotcp4/out.mp3':
  Metadata:
    TSSE            : Lavf57.83.100
    Stream #0:0: Audio: mp3 (libmp3lame), 44100 Hz, mono, fltp
    Metadata:
      encoder         : Lavc57.107.100 libmp3lame
size=     226kB time=00:00:28.83 bitrate=  64.1kbits/s speed=68.2x
video:0kB audio:226kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.098302%
LY output to `/tmp/tmp_fuotcp4/score.ly'...
Changing working directory to: `/tmp/tmp_fuotcp4'
Processing `/tmp/tmp_fuotcp4/score.ly'
Parsing...
Interpreting music...[8][16][16]
Preprocessing graphical objects...
Interpreting music...
MIDI output to `score.midi'...
Finding the ideal number of pages...
Fitting music on 1 page...
Drawing systems...
Layout output to `score.ps'...
Converting to PNG...
Success: compilation successfully completed

Want to make some of these yourself?

Run this model