cudanexus/ocr-surya:7ab5bede – Run with an API on Replicate

Version

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

cudanexus /ocr-surya:7ab5bede

Playground API

Input

image

*file

Upload PDF or Image

page_number

integer

Page Number

Default: 1

languages_choices

string

Languages

Default: "English"

languages_input

string

Shift + Return to add a new line

Languages (comma-separated list)

Default: "English"

action

string

Action

Default: "Run Text Detection"

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

npx create-replicate --model=cudanexus/ocr-surya

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 cudanexus/ocr-surya using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "cudanexus/ocr-surya:7ab5bedee2cd1f0c82b2df6718d19bf0b473f738f9db062f122e47e1467f96ce",
  {
    input: {
      action: "Run Text Detection",
      page_number: 1,
      languages_input: "English",
      languages_choices: "English"
    }
  }
);
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 cudanexus/ocr-surya using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "cudanexus/ocr-surya:7ab5bedee2cd1f0c82b2df6718d19bf0b473f738f9db062f122e47e1467f96ce",
    input={
        "action": "Run Text Detection",
        "page_number": 1,
        "languages_input": "English",
        "languages_choices": "English"
    }
)
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 cudanexus/ocr-surya 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": "7ab5bedee2cd1f0c82b2df6718d19bf0b473f738f9db062f122e47e1467f96ce",
    "input": {
      "action": "Run Text Detection",
      "page_number": 1,
      "languages_input": "English",
      "languages_choices": "English"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

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

Run this to download the model and run it in your local environment:

cog predict r8.im/cudanexus/ocr-surya@sha256:7ab5bedee2cd1f0c82b2df6718d19bf0b473f738f9db062f122e47e1467f96ce \
  -i 'action="Run Text Detection"' \
  -i 'page_number=1' \
  -i 'languages_input="English"' \
  -i 'languages_choices="English"'

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

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/cudanexus/ocr-surya@sha256:7ab5bedee2cd1f0c82b2df6718d19bf0b473f738f9db062f122e47e1467f96ce
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "action": "Run Text Detection",
      "page_number": 1,
      "languages_input": "English",
      "languages_choices": "English"
    }
  }' \
  http://localhost:5000/predictions

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

Output

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