Spaces:
Sleeping
Sleeping
File size: 3,741 Bytes
4bb7f61 e43c159 4bb7f61 1f1c873 4bb7f61 be7919b 4bb7f61 e04e4a9 4bb7f61 0120ffb 4bb7f61 e25275e 0c84a8d e25275e 6d3dcaa 26648f7 e25275e fce03ed 1dd8382 798b1e0 26648f7 fce03ed e25275e 4bb7f61 e25275e fce03ed 4bb7f61 ae4476a 2c4e31b 4bb7f61 ae4476a e43c159 ae4476a e43c159 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 |
import streamlit as st
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
import pandas as pd
from fpdf import FPDF
# Interface utilisateur
st.set_page_config(
page_title="Traduction d'une phrase en pictogrammes ARASAAC",
page_icon="📝",
layout="wide"
)
# Charger le modèle et le tokenizer
# checkpoint = "Propicto/t2p-t5-large-orfeo"
checkpoint = "Propicto/t2p-nllb-200-distilled-600M-all"
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint)
# Lire le lexique
@st.cache_data
def read_lexicon(lexicon):
df = pd.read_csv(lexicon, sep='\t')
df['keyword_no_cat'] = df['lemma'].str.split(' #').str[0].str.strip().str.replace(' ', '_')
return df
lexicon = read_lexicon("lexicon.csv")
# Processus de sortie de la traduction
def process_output_trad(pred):
return pred.split()
def get_id_picto_from_predicted_lemma(df_lexicon, lemma):
if lemma.endswith("!"):
lemma = lemma[:-1]
id_picto = df_lexicon.loc[df_lexicon['keyword_no_cat'] == lemma, 'id_picto'].tolist()
return (id_picto[0], lemma) if id_picto else (0, lemma)
# Génération du contenu HTML pour afficher les pictogrammes
def generate_html(ids):
html_content = '<html><head><style>'
html_content += '''
figure {
display: inline-block;
text-align: center;
font-family: Arial, sans-serif;
margin: 0;
}
figcaption {
color: black;
background-color: white;
border-radius: 5px;
}
img {
background-color: white;
margin: 0;
padding: 0;
border-radius: 6px;
}
'''
html_content += '</style></head><body>'
for picto_id, lemma in ids:
if picto_id != 0: # ignore invalid IDs
img_url = f"https://static.arasaac.org/pictograms/{picto_id}/{picto_id}_500.png"
html_content += f'''
<figure>
<img src="{img_url}" alt="{lemma}" width="200" height="200"/>
<figcaption>{lemma}</figcaption>
</figure>
'''
html_content += '</body></html>'
return html_content
def generate_pdf(ids):
pdf = FPDF()
pdf.add_page()
pdf.set_auto_page_break(auto=True, margin=15)
for picto_id, lemma in ids:
if picto_id != 0: # ignore invalid IDs
img_url = f"https://static.arasaac.org/pictograms/{picto_id}/{picto_id}_500.png"
pdf.image(img_url, x=None, y=None, w=50, h=50)
pdf.ln(55)
pdf.set_font("Arial", size=12)
pdf.cell(200, 10, txt=lemma, ln=True, align='C')
pdf_path = "pictograms.pdf"
pdf.output(pdf_path)
return pdf_path
st.title("Traduction d'une phrase en pictogrammes ARASAAC")
sentence = st.text_input("Entrez une phrase en français:")
if sentence:
inputs = tokenizer(sentence, return_tensors="pt").input_ids
outputs = model.generate(inputs, max_new_tokens=40, do_sample=True, top_k=30, top_p=0.95)
pred = tokenizer.decode(outputs[0], skip_special_tokens=True)
sentence_to_map = process_output_trad(pred)
pictogram_ids = [get_id_picto_from_predicted_lemma(lexicon, lemma) for lemma in sentence_to_map]
html = generate_html(pictogram_ids)
st.components.v1.html(html, height=800, scrolling=True)
# Container to hold the download button
download_container = st.container()
with download_container:
pdf_path = generate_pdf(pictogram_ids)
with open(pdf_path, "rb") as pdf_file:
st.download_button(label="Télécharger la traduction en PDF", data=pdf_file, file_name="pictograms.pdf", mime="application/pdf") |