name: latin_g2_jpqd
description: Latin script text recognition model (CRNN) optimized with JPQD quantization
framework: ONNX
task: text-recognition
domain: computer-vision
subdomain: optical-character-recognition

model_info:
  architecture: CRNN (CNN + BiLSTM + CTC)
  language: Latin script languages
  supported_languages:
    - English
    - Spanish
    - French
    - German
    - Italian
    - Portuguese
    - Dutch
    - Polish
    - Czech
    - Romanian
    - And other Latin-based languages
  num_classes: 352
  original_source: EasyOCR
  optimization: JPQD quantization
  
specifications:
  input_shape: [1, 1, 32, 100]
  input_type: float32
  input_format: Grayscale
  output_shape: [1, 25, 352]  # sequence_length x num_classes
  output_type: float32
  batch_size: dynamic
  sequence_length: 25
  
performance:
  original_size_mb: 14.7
  optimized_size_mb: 8.5
  compression_ratio: 3.97
  inference_time_cpu_ms: ~12
  accuracy_retention: ">95%"
  
deployment:
  runtime: onnxruntime
  hardware: CPU-optimized
  precision: INT8 weights, FP32 activations
  memory_usage_mb: ~15
  
usage:
  preprocessing:
    - Convert to grayscale
    - Resize to 32x100 (height x width)
    - Normalize to [0,1]
    - Add batch and channel dimensions
  postprocessing:
    - Apply CTC decoding
    - Convert indices to characters
    - Remove blank tokens and duplicates

supported_characters:
  basic_latin: "a-z, A-Z, 0-9"
  latin_extended: "À-ÿ (Latin-1 Supplement)"
  punctuation: "Standard punctuation marks"
  symbols: "Common symbols and currency"
  diacritics: "Accented characters for European languages"
  
character_coverage:
  - "Basic Latin (U+0020-U+007F)"
  - "Latin-1 Supplement (U+0080-U+00FF)"
  - "Latin Extended-A (U+0100-U+017F)"
  - "Latin Extended-B (U+0180-U+024F)"
  - "Combining Diacritical Marks (U+0300-U+036F)"
  
training_data:
  type: Multilingual synthetic and real text images
  languages: Multiple Latin script languages
  domains: Documents, natural scenes, printed text, handwriting
  
use_cases:
  - Multilingual document processing
  - European language OCR
  - International text recognition
  - Multilingual forms processing

license: apache-2.0
tags:
  - text-recognition
  - latin
  - multilingual
  - crnn
  - lstm
  - ocr
  - onnx
  - quantized
  - jpqd
  - european-languages