| import streamlit as st |
| import torch |
| from transformers import AutoProcessor, AutoModelForVision2Seq |
| from PIL import Image |
|
|
| device = "cuda" if torch.cuda.is_available() else "cpu" |
|
|
| |
| @st.cache_resource |
| def load_model(): |
| model_name = "tjoab/latex_finetuned" |
| processor = AutoProcessor.from_pretrained(model_name) |
| model = AutoModelForVision2Seq.from_pretrained(model_name).to(device) |
| return processor, model |
|
|
|
|
|
|
| processor, model = load_model() |
|
|
| st.title("LaTeX Image to Text Converter") |
| st.write("Upload an image containing a handwritten or printed math expression, and get the LaTeX code.") |
|
|
| |
| uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg"]) |
|
|
| if uploaded_file: |
| image = Image.open(uploaded_file).convert("RGB") |
| st.image(image, caption="Uploaded Image", use_column_width=True) |
|
|
| |
| with st.spinner("Processing..."): |
| preproc_image = processor.image_processor(image, return_tensors="pt").pixel_values |
| preproc_image = preproc_image.to(device) |
|
|
| pred_ids = model.generate(preproc_image, max_length=128) |
| latex_pred = processor.batch_decode(pred_ids, skip_special_tokens=True)[0] |
|
|
| st.subheader("Predicted LaTeX Code:") |
| st.code(latex_pred, language="latex") |
|
|
