manuscript-ocr

Contents:

  • Getting Started
    • Installation
    • Quick Start
    • Main Components
  • Pipeline Usage Guide
    • Detector Requirements
      • Result Structure
    • Recognizer Requirements
    • Corrector Requirements
      • Built-in CharLM Corrector
    • Compatible Implementation Examples
      • Complete Detector Example
      • Using Custom Components
    • Pipeline Usage Examples
      • Basic Usage
      • Detection Only (Without Recognition)
      • With Visualization
      • Intermediate Results
      • Export/Import Page to JSON
      • With Profiling
      • Batch Processing
    • Component Configuration
      • Replacing Detector or Recognizer
      • Built-in Model Configuration
      • Size Filtering
      • Automatic Rotation Control
  • Library Structure
    • Module Descriptions
  • API Reference
    • Pipeline
      • Pipeline
        • Pipeline.detector
        • Pipeline.recognizer
        • Pipeline.corrector
        • Pipeline.min_text_size
        • Pipeline.rotate_threshold
        • Pipeline.__init__()
        • Pipeline.predict()
        • Pipeline.get_text()
        • Pipeline.last_detection_page
        • Pipeline.last_recognition_page
        • Pipeline.last_correction_page
    • Data Structures
      • Data Model
      • API Reference
        • Word
        • Line
        • Block
        • Page
    • Detectors
      • EAST
        • EAST.default_weights_name
        • EAST.pretrained_registry
        • EAST.__init__()
        • EAST.predict()
        • EAST.train()
        • EAST.export()
    • Recognizers
      • TRBA
        • TRBA.default_weights_name
        • TRBA.pretrained_registry
        • TRBA.config_registry
        • TRBA.charset_registry
        • TRBA.__init__()
        • TRBA.predict()
        • TRBA.train()
        • TRBA.export()
    • Correctors
      • CharLM
        • CharLM
        • Overview
        • Available Presets
        • Quick Example
        • Basic Usage
        • Advanced Configuration
        • Using Custom Lexicon
        • Training Custom Model
        • Export to ONNX
    • Utilities
      • read_image()
      • create_page_from_text()
      • visualize_page()
      • organize_page()
      • set_seed()
manuscript-ocr
  • Overview: module code

All modules for which code is available

  • manuscript._pipeline
  • manuscript.correctors._charlm
  • manuscript.data.structures
  • manuscript.detectors._east
  • manuscript.recognizers._trba
  • manuscript.utils.io
  • manuscript.utils.sorting
  • manuscript.utils.training
  • manuscript.utils.visualization

© Copyright 2026, Konstantin Kozhin.

Built with Sphinx using a theme provided by Read the Docs.