app.py

import gradio as gr
from transformers import TrOCRProcessor, VisionEncoderDecoderModel
import requests
from PIL import Image

# Dictionary of model names and their corresponding HuggingFace model IDs
MODEL_OPTIONS = {
    "Microsoft Handwritten": "microsoft/trocr-base-handwritten",
    "Medieval Base": "medieval-data/trocr-medieval-base",
    "Medieval Latin Caroline": "medieval-data/trocr-medieval-latin-caroline",
    "Medieval Castilian Hybrida": "medieval-data/trocr-medieval-castilian-hybrida",
    "Medieval Humanistica": "medieval-data/trocr-medieval-humanistica",
    "Medieval Textualis": "medieval-data/trocr-medieval-textualis",
    "Medieval Cursiva": "medieval-data/trocr-medieval-cursiva",
    "Medieval Semitextualis": "medieval-data/trocr-medieval-semitextualis",
    "Medieval Praegothica": "medieval-data/trocr-medieval-praegothica",
    "Medieval Semihybrida": "medieval-data/trocr-medieval-semihybrida",
    "Medieval Print": "medieval-data/trocr-medieval-print"
}

# Load image examples
urls = [
    'https://huggingface.co./medieval-data/trocr-medieval-base/resolve/main/images/caroline-1.png'
]

for idx, url in enumerate(urls):
    image = Image.open(requests.get(url, stream=True).raw)
    image.save(f"image_{idx}.png")

def load_model(model_name):
    model_id = MODEL_OPTIONS[model_name]
    processor = TrOCRProcessor.from_pretrained(model_id)
    model = VisionEncoderDecoderModel.from_pretrained(model_id)
    return processor, model

def process_image(image, model_name):
    processor, model = load_model(model_name)
    
    # prepare image
    pixel_values = processor(image, return_tensors="pt").pixel_values
    
    # generate (no beam search)
    generated_ids = model.generate(pixel_values)
    
    # decode
    generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return generated_text

title = "Interactive demo: TrOCR Model Switcher"
description = "Demo for the Medieval TrOCR HTR Models."

iface = gr.Interface(
    fn=process_image,
    inputs=[
        gr.Image(type="pil"),
        gr.Dropdown(choices=list(MODEL_OPTIONS.keys()), label="Select Model")
    ],
    outputs=gr.Textbox(),
    title=title,
    description=description,
    examples=[
        ["image_0.png", "Medieval Latin Caroline"]
    ]
)

iface.launch(debug=True, share=True)