EasyOCR | Roboflow Docs

EasyOCR is a multilingual optical character recognition model deployable via our Serverless Cloud API. Supported languages include English, Japanese, Kannada, Korean, Latin (covering Spanish, French, Italian, Portuguese, German, Polish, and Dutch), Telugu, and Simplified Chinese.

EasyOCR API

Run EasyOCR through the HTTP endpoint directly with curl, or with the inference-sdk wrapper.

Get your API Key

Create a Roboflow account, find your key on the Roboflow API settings page and make it available to your shell:

export ROBOFLOW_API_KEY="your-key-here"

Run the model

Call the /easy_ocr/ocr endpoint with curl:

curl --location 'https://serverless.roboflow.com/easy_ocr/ocr' \
  --header 'Content-Type: application/json' \
  --data '{
    "api_key": "'"$ROBOFLOW_API_KEY"'",
    "image": {"type": "url", "value": "https://media.roboflow.com/swift.png"},
    "language_codes": ["en"]
  }'

Get your API Key

Create a Roboflow account, find your key on the Roboflow API settings page and make it available to your shell:

export ROBOFLOW_API_KEY="your-key-here"

Install the dependencies

This package calls the model:

pip install -U inference-sdk supervision

Run the model

Run EasyOCR on an image:

import os
import supervision as sv
from inference_sdk import InferenceHTTPClient

image = sv.load_image_from_url("https://media.roboflow.com/swift.png")

client = InferenceHTTPClient(
    api_url="https://serverless.roboflow.com",
    api_key=os.environ["ROBOFLOW_API_KEY"],
)

result = client.ocr_image(
    inference_input=image,
    model="easy_ocr",
    language_codes=["en"],
)

print(result["result"]) # Extracted text

The code above prints inference results to the terminal:

was thinking earlier today that have gone through, to use the lingo, eras Of listening to each of Swift's Eras. Meta indeed: started listening to Ms. Swift's music after hearing the Midnights album: few weeks after hearing the album for the first time, found myself playing various songs on repeat. listened to the album in order multiple times:

EasyOCR inference speed

Latency measured with Roboflow Inference on 1x NVIDIA L4, batch size 1, mean after warmup.

Model	Latency (ms)
`easy_ocr`	19.7

Measured on a full document image (text detection plus recognition).

Set api_url to match your deployment target:

https://serverless.roboflow.com for the Serverless Cloud API.
http://localhost:9001 for a local Inference server.
Your Dedicated Deployment URL for a private endpoint.