|
--- |
|
tags: |
|
- trocr |
|
- image-to-text |
|
widget: |
|
- src: "https://huggingface.co/dsupa/mangaocr-hoogberta-v1/to_test_hf_model/test1.JPG" |
|
example_title: test 1 |
|
- src: "https://huggingface.co/dsupa/mangaocr-hoogberta-v1/to_test_hf_model/test2.JPG" |
|
example_title: test 2 |
|
- src: "https://huggingface.co/dsupa/mangaocr-hoogberta-v1/to_test_hf_model/test3.JPG" |
|
example_title: test 3 |
|
- src: "https://huggingface.co/dsupa/mangaocr-hoogberta-v1/to_test_hf_model/test4.JPG" |
|
example_title: test 4 |
|
- src: "https://huggingface.co/dsupa/mangaocr-hoogberta-v1/to_test_hf_model/test5.JPG" |
|
example_title: test 5 |
|
- src: "https://huggingface.co/dsupa/mangaocr-hoogberta-v1/to_test_hf_model/test6.JPG" |
|
example_title: test 6 |
|
--- |
|
|
|
### How to use |
|
|
|
Here is how to use this model in PyTorch: |
|
|
|
```python |
|
from transformers import TrOCRProcessor, VisionEncoderDecoderModel |
|
from PIL import Image |
|
|
|
processor = TrOCRProcessor.from_pretrained('dsupa/mangaocr-hoogberta-v2') |
|
model = VisionEncoderDecoderModel.from_pretrained('dsupa/mangaocr-hoogberta-v2') |
|
|
|
def predict(image_path): |
|
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] |
|
|
|
return generated_text |
|
|
|
image_path = "your_img.jpg" |
|
pred = predit(image_path) |
|
print(pred) |
|
``` |
