image-to-string

simpleimagetostring.sh

#!/bin/bash

mkdir -p trocr_app
cd trocr_app

cat << 'EOF' > ocr.py
import sys
from PIL import Image
from transformers import TrOCRProcessor, VisionEncoderDecoderModel

if len(sys.argv) != 2:
    print("Usage: python ocr.py <image_path>")
    sys.exit(1)

image_path = sys.argv[1]

try:
    processor = TrOCRProcessor.from_pretrained('microsoft/trocr-base-printed')
    model = VisionEncoderDecoderModel.from_pretrained('microsoft/trocr-base-printed')

    image = Image.open(image_path).convert('RGB')

    pixel_values = processor(images=image, return_tensors="pt").pixel_values
    generated_ids = model.generate(pixel_values)
    generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]

    print("Extracted Text:")
    print(generated_text)
except Exception as e:
    print(f"An error occurred: {e}")
EOF

cat << 'EOF' > requirements.txt
transformers
torch
Pillow
EOF

cat << 'EOF' > Dockerfile
FROM python:3.9-slim

RUN apt-get update && apt-get install -y \
    git \
    libgl1-mesa-glx \
    && rm -rf /var/lib/apt/lists/*

WORKDIR /app

COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

COPY ocr.py .

RUN mkdir /models && \
    python -c "\
from transformers import TrOCRProcessor, VisionEncoderDecoderModel; \
processor = TrOCRProcessor.from_pretrained('microsoft/trocr-base-printed'); \
processor.save_pretrained('/models'); \
model = VisionEncoderDecoderModel.from_pretrained('microsoft/trocr-base-printed'); \
model.save_pretrained('/models')"

ENV MODEL_DIR=/models

ENTRYPOINT ["python", "ocr.py"]
EOF

docker build -t trocr_app .

echo "docker run --rm -v \$(pwd):/gary trocr_app /gary/your_image_file.png"