deepseek_ocr_de

from transformers import TrOCRProcessor, VisionEncoderDecoderModel
from PIL import Image
import requests

# Load model and processor
processor = TrOCRProcessor.from_pretrained("YOUR_USERNAME/deepseek-ocr-german")
model = VisionEncoderDecoderModel.from_pretrained("YOUR_USERNAME/deepseek-ocr-german")

# Load image
url = "path_to_your_german_text_image.jpg"
image = Image.open(url).convert("RGB")

# Process
pixel_values = processor(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(generated_text)

from transformers import TrOCRProcessor, VisionEncoderDecoderModel
from PIL import Image

processor = TrOCRProcessor.from_pretrained("YOUR_USERNAME/deepseek-ocr-german")
model = VisionEncoderDecoderModel.from_pretrained("YOUR_USERNAME/deepseek-ocr-german")

# Multiple images
images = [Image.open(f"image_{i}.jpg").convert("RGB") for i in range(5)]

# Batch process
pixel_values = processor(images, return_tensors="pt", padding=True).pixel_values
generated_ids = model.generate(pixel_values)
generated_texts = processor.batch_decode(generated_ids, skip_special_tokens=True)

for text in generated_texts:
    print(text)

import torch
from transformers import TrOCRProcessor, VisionEncoderDecoderModel
from PIL import Image

device = "cuda" if torch.cuda.is_available() else "cpu"

processor = TrOCRProcessor.from_pretrained("YOUR_USERNAME/deepseek-ocr-german")
model = VisionEncoderDecoderModel.from_pretrained("YOUR_USERNAME/deepseek-ocr-german").to(device)

image = Image.open("german_text.jpg").convert("RGB")
pixel_values = processor(image, return_tensors="pt").pixel_values.to(device)

generated_ids = model.generate(pixel_values)
text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(text)