mtg/maest:170cfd0b – Run with an API on Replicate

Version

You're looking at a specific version of this model. Jump to the model overview.

mtg /maest:170cfd0b

Playground API

Input

Video Player is loading.

Current Time 00:00:000

Duration 00:00:000

Loaded: 0%

Stream Type LIVE

Remaining Time 00:00:000

audio

file

Audio file to process

url

string

Shift + Return to add a new line

YouTube URL to process (overrides audio input)

top_n

integer

Top n music styles to show

Default: 10

output_format

string

Output either a bar chart visualization or a JSON blob

Default: "Visualization"

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

npx create-replicate --model=mtg/maest

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

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

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

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

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

const output = await replicate.run(
  "mtg/maest:170cfd0b56fb97ed732c815431e52546efac47b8a2b0096d58dd40b099191e01",
  {
    input: {
      audio: "https://replicate.delivery/pbxt/JosNxmt74AOVcCi1uwCHKFJR1jvzi7U2ffKcUPUFUz9J1z1b/07%20-%20The%20Enemy.mp3",
      top_n: 10,
      output_format: "Visualization"
    }
  }
);

// To access the file URL:
console.log(output.url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", 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 mtg/maest using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "mtg/maest:170cfd0b56fb97ed732c815431e52546efac47b8a2b0096d58dd40b099191e01",
    input={
        "audio": "https://replicate.delivery/pbxt/JosNxmt74AOVcCi1uwCHKFJR1jvzi7U2ffKcUPUFUz9J1z1b/07%20-%20The%20Enemy.mp3",
        "top_n": 10,
        "output_format": "Visualization"
    }
)
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 mtg/maest 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": "mtg/maest:170cfd0b56fb97ed732c815431e52546efac47b8a2b0096d58dd40b099191e01",
    "input": {
      "audio": "https://replicate.delivery/pbxt/JosNxmt74AOVcCi1uwCHKFJR1jvzi7U2ffKcUPUFUz9J1z1b/07%20-%20The%20Enemy.mp3",
      "top_n": 10,
      "output_format": "Visualization"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-11-04T18:08:22.028391Z",
  "created_at": "2023-11-04T18:08:05.361577Z",
  "data_removed": false,
  "error": null,
  "id": "fn2yrujbnqrudkjmv5sigwmyla",
  "input": {
    "audio": "https://replicate.delivery/pbxt/JosNxmt74AOVcCi1uwCHKFJR1jvzi7U2ffKcUPUFUz9J1z1b/07%20-%20The%20Enemy.mp3",
    "top_n": 10,
    "output_format": "Visualization"
  },
  "logs": "loading audio...\nrunning the model...\nplotting...\n2023-11-04 18:08:12.037336: W tensorflow/core/grappler/optimizers/loop_optimizer.cc:906] Skipping loop optimization for Merge node with control input: StatefulPartitionedCall/StatefulPartitionedCall/assert_equal_193/Assert/AssertGuard/branch_executed/_1407\n2023-11-04 18:08:20.984002: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero\n2023-11-04 18:08:20.985428: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1733] Found device 0 with properties:\npciBusID: 0000:00:05.0 name: Tesla T4 computeCapability: 7.5\ncoreClock: 1.59GHz coreCount: 40 deviceMemorySize: 14.58GiB deviceMemoryBandwidth: 298.08GiB/s\n2023-11-04 18:08:20.986119: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero\n2023-11-04 18:08:20.987442: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero\n2023-11-04 18:08:20.988540: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1871] Adding visible gpu devices: 0\n2023-11-04 18:08:20.988584: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1258] Device interconnect StreamExecutor with strength 1 edge matrix:\n2023-11-04 18:08:20.988594: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1264]      0\n2023-11-04 18:08:20.988602: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1277] 0:   N\n2023-11-04 18:08:20.988783: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero\n2023-11-04 18:08:20.990431: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero\n2023-11-04 18:08:20.991548: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1418] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 13421 MB memory) -> physical GPU (device: 0, name: Tesla T4, pci bus id: 0000:00:05.0, compute capability: 7.5)\n/root/.pyenv/versions/3.10.13/lib/python3.10/site-packages/seaborn/_core.py:1225: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\nif pd.api.types.is_categorical_dtype(vector):\n/root/.pyenv/versions/3.10.13/lib/python3.10/site-packages/seaborn/_core.py:1225: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\nif pd.api.types.is_categorical_dtype(vector):\n/root/.pyenv/versions/3.10.13/lib/python3.10/site-packages/seaborn/_core.py:1225: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\nif pd.api.types.is_categorical_dtype(vector):\ndone!",
  "metrics": {
    "predict_time": 16.69758,
    "total_time": 16.666814
  },
  "output": "https://replicate.delivery/pbxt/jBekyAv1ExXUVac0vcvVaJdaZoJ6K6IRWpcKSPyFoczK1h6IA/out.png",
  "started_at": "2023-11-04T18:08:05.330811Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/fn2yrujbnqrudkjmv5sigwmyla",
    "cancel": "https://api.replicate.com/v1/predictions/fn2yrujbnqrudkjmv5sigwmyla/cancel"
  },
  "version": "170cfd0b56fb97ed732c815431e52546efac47b8a2b0096d58dd40b099191e01"
}

Generated in

16.7 seconds

Tweak itReport

loading audio...
running the model...
plotting...
2023-11-04 18:08:12.037336: W tensorflow/core/grappler/optimizers/loop_optimizer.cc:906] Skipping loop optimization for Merge node with control input: StatefulPartitionedCall/StatefulPartitionedCall/assert_equal_193/Assert/AssertGuard/branch_executed/_1407
2023-11-04 18:08:20.984002: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2023-11-04 18:08:20.985428: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1733] Found device 0 with properties:
pciBusID: 0000:00:05.0 name: Tesla T4 computeCapability: 7.5
coreClock: 1.59GHz coreCount: 40 deviceMemorySize: 14.58GiB deviceMemoryBandwidth: 298.08GiB/s
2023-11-04 18:08:20.986119: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2023-11-04 18:08:20.987442: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2023-11-04 18:08:20.988540: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1871] Adding visible gpu devices: 0
2023-11-04 18:08:20.988584: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1258] Device interconnect StreamExecutor with strength 1 edge matrix:
2023-11-04 18:08:20.988594: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1264]      0
2023-11-04 18:08:20.988602: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1277] 0:   N
2023-11-04 18:08:20.988783: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2023-11-04 18:08:20.990431: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2023-11-04 18:08:20.991548: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1418] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 13421 MB memory) -> physical GPU (device: 0, name: Tesla T4, pci bus id: 0000:00:05.0, compute capability: 7.5)
/root/.pyenv/versions/3.10.13/lib/python3.10/site-packages/seaborn/_core.py:1225: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
if pd.api.types.is_categorical_dtype(vector):
/root/.pyenv/versions/3.10.13/lib/python3.10/site-packages/seaborn/_core.py:1225: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
if pd.api.types.is_categorical_dtype(vector):
/root/.pyenv/versions/3.10.13/lib/python3.10/site-packages/seaborn/_core.py:1225: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
if pd.api.types.is_categorical_dtype(vector):
done!