Mangaocr Hoogberta V2

🚀 漫画OCR模型（MangaOCR）

本项目是一个图像转文字的模型，利用Trocr技术，能够将漫画图像中的文字准确识别出来，为漫画文字处理提供了高效的解决方案。

🚀 快速开始

以下是在PyTorch中使用该模型的示例代码：

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 = predict(image_path)
print(pred)

💻 使用示例

基础用法

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 = predict(image_path)
print(pred)

高级用法

# 你可以根据实际需求，对预测函数进行扩展，例如批量处理图片等。
from transformers import TrOCRProcessor, VisionEncoderDecoderModel
from PIL import Image
import os

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_folder = "your_image_folder"
for image_name in os.listdir(image_folder):
    image_path = os.path.join(image_folder, image_name)
    pred = predict(image_path)
    print(f"Image: {image_name}, Prediction: {pred}")

测试示例

你可以使用以下图片链接进行模型测试：

• 测试图片1
• 测试图片2
• 测试图片3
• 测试图片4
• 测试图片5
• 测试图片6