Spaces:
Sleeping
Sleeping
File size: 2,644 Bytes
4bb7f61 1f1c873 4bb7f61 4c69fdf 4bb7f61 e04e4a9 4bb7f61 e25275e 6d3dcaa ae8f7ec e25275e fce03ed 798b1e0 fce03ed e25275e 4bb7f61 e25275e fce03ed 4bb7f61 2c4e31b 4bb7f61 2c4e31b |
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 |
import streamlit as st
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
import pandas as pd
# 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"
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):
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;
}
figcaption {
color: black;
background-color: white;
border-radius: 1px;
}
img {
background-color: white;
margin: 1px;
padding: 0;
}
'''
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
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) |