Overview

The Crowdin ABBYY Vantage OCR integration enables seamless conversion of PDFs and image files directly into editable formats (DOCX or XLSX) within your Crowdin projects. Leveraging ABBYY Vantage's advanced OCR technology, scanned documents and images can be easily transformed into translatable texts, significantly streamlining your localization workflows.

Installation and Project Selection

When installing the ABBYY Vantage OCR app, select the projects where you want OCR processing to be enabled. The app automatically processes supported files in these projects. You can always modify these project selections later through Crowdin's Organization Settings.

Access and Configuration

After installation, configure the app in the "File Processors" section of your project's settings. You will need to provide your ABBYY Vantage credentials, including Tenant ID, Client ID, Client Secret, username, and password.

ABBYY Vantage OCR Skill Setup

• Create an OCR skill in ABBYY Vantage by duplicating the default OCR skill.
• Configure this skill in ABBYY UI:
  • Select the required input languages.
  • Set the output format to either DOCX or XLSX.
  • Ensure you check all permission boxes when creating the OAuth token.

Enter the skill name in the Crowdin app configuration exactly as it appears in ABBYY Vantage.

Handling Multiple Documents

If you require different OCR settings for various documents, configure the ABBYY Vantage OCR skill settings prior to each upload. This ensures each document is processed accurately according to its specific needs.

Note! It's not possible to edit the output format for the default OCR skill. Please copy the default OCR skill to configure the output format. IMPORTANT! Disable the JSON export option. Only docx or xlsx should be checked.

Supported Input Formats

ABBYY Vantage OCR supports processing the following file formats:

Important Notes:

• Maximum file size per upload: 30 MB
• Maximum image dimensions: 32512×32512 pixels

Screenshot