Update src/streamlit_app.py
Browse files- src/streamlit_app.py +34 -38
src/streamlit_app.py
CHANGED
|
@@ -1,40 +1,36 @@
|
|
| 1 |
-
import altair as alt
|
| 2 |
-
import numpy as np
|
| 3 |
-
import pandas as pd
|
| 4 |
import streamlit as st
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
|
| 6 |
-
"""
|
| 7 |
-
# Welcome to Streamlit!
|
| 8 |
-
|
| 9 |
-
Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
|
| 10 |
-
If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
|
| 11 |
-
forums](https://discuss.streamlit.io).
|
| 12 |
-
|
| 13 |
-
In the meantime, below is an example of what you can do with just a few lines of code:
|
| 14 |
-
"""
|
| 15 |
-
|
| 16 |
-
num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
|
| 17 |
-
num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
|
| 18 |
-
|
| 19 |
-
indices = np.linspace(0, 1, num_points)
|
| 20 |
-
theta = 2 * np.pi * num_turns * indices
|
| 21 |
-
radius = indices
|
| 22 |
-
|
| 23 |
-
x = radius * np.cos(theta)
|
| 24 |
-
y = radius * np.sin(theta)
|
| 25 |
-
|
| 26 |
-
df = pd.DataFrame({
|
| 27 |
-
"x": x,
|
| 28 |
-
"y": y,
|
| 29 |
-
"idx": indices,
|
| 30 |
-
"rand": np.random.randn(num_points),
|
| 31 |
-
})
|
| 32 |
-
|
| 33 |
-
st.altair_chart(alt.Chart(df, height=700, width=700)
|
| 34 |
-
.mark_point(filled=True)
|
| 35 |
-
.encode(
|
| 36 |
-
x=alt.X("x", axis=None),
|
| 37 |
-
y=alt.Y("y", axis=None),
|
| 38 |
-
color=alt.Color("idx", legend=None, scale=alt.Scale()),
|
| 39 |
-
size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
|
| 40 |
-
))
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
import streamlit as st
|
| 2 |
+
from transformers import TrOCRProcessor, VisionEncoderDecoderModel
|
| 3 |
+
from PIL import Image
|
| 4 |
+
import torch
|
| 5 |
+
|
| 6 |
+
# Configuration de la page
|
| 7 |
+
st.set_page_config(page_title="OCR Manuscrit avec TrOCR", layout="centered")
|
| 8 |
+
|
| 9 |
+
st.title("✍️ OCR de texte manuscrit avec TrOCR")
|
| 10 |
+
st.write("Chargez une image contenant du texte manuscrit pour en extraire le contenu.")
|
| 11 |
+
|
| 12 |
+
# Chargement du modèle TrOCR pour manuscrit
|
| 13 |
+
@st.cache_resource
|
| 14 |
+
def load_model():
|
| 15 |
+
processor = TrOCRProcessor.from_pretrained("microsoft/trocr-base-handwritten")
|
| 16 |
+
model = VisionEncoderDecoderModel.from_pretrained("microsoft/trocr-base-handwritten")
|
| 17 |
+
return processor, model
|
| 18 |
+
|
| 19 |
+
processor, model = load_model()
|
| 20 |
+
|
| 21 |
+
# Upload de l'image
|
| 22 |
+
uploaded_file = st.file_uploader("📤 Charger une image manuscrite (format .png ou .jpg)", type=["png", "jpg", "jpeg"])
|
| 23 |
+
|
| 24 |
+
if uploaded_file is not None:
|
| 25 |
+
image = Image.open(uploaded_file).convert("RGB")
|
| 26 |
+
st.image(image, caption="🖼️ Image chargée", use_column_width=True)
|
| 27 |
+
|
| 28 |
+
if st.button("🔍 Lancer la reconnaissance"):
|
| 29 |
+
with st.spinner("Reconnaissance en cours..."):
|
| 30 |
+
pixel_values = processor(images=image, return_tensors="pt").pixel_values
|
| 31 |
+
generated_ids = model.generate(pixel_values)
|
| 32 |
+
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
|
| 33 |
+
|
| 34 |
+
st.success("✅ Texte reconnu :")
|
| 35 |
+
st.text_area("📝 Résultat OCR", generated_text, height=150)
|
| 36 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|