Spaces:
Running
Running
File size: 5,752 Bytes
4210dc2 845d6a6 4210dc2 845d6a6 4210dc2 845d6a6 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 |
from fastapi import FastAPI, File, UploadFile, Form
from fastapi.responses import JSONResponse, RedirectResponse
from fastapi.staticfiles import StaticFiles
from fastapi.middleware.cors import CORSMiddleware
from transformers import pipeline, M2M100ForConditionalGeneration, M2M100Tokenizer, MarianMTModel, MarianTokenizer
import shutil
#
import os
import logging
from PyPDF2 import PdfReader
import docx
from PIL import Image
import openpyxl # 📌 Pour lire les fichiers Excel (.xlsx)
from pptx import Presentation
import fitz # PyMuPDF
import io
from docx import Document
import matplotlib.pyplot as plt
import seaborn as sns
import torch
import re
import pandas as pd
from transformers import AutoTokenizer, AutoModelForCausalLM
from fastapi.responses import FileResponse
import os
from fastapi.middleware.cors import CORSMiddleware
import matplotlib
matplotlib.use('Agg')
import re
import torch
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from transformers import AutoTokenizer, AutoModelForCausalLM
from fastapi import FastAPI, File, UploadFile, Form
from fastapi.responses import FileResponse
import os
from fastapi.middleware.cors import CORSMiddleware
from fastapi import FastAPI, File, UploadFile, Form
from fastapi.responses import JSONResponse, RedirectResponse
from fastapi.staticfiles import StaticFiles
from transformers import pipeline, M2M100ForConditionalGeneration, M2M100Tokenizer
import shutil
import os
import logging
from fastapi.middleware.cors import CORSMiddleware
from PyPDF2 import PdfReader
import docx
from PIL import Image # Pour ouvrir les images avant analyse
from transformers import MarianMTModel, MarianTokenizer
import os
import fitz
from transformers import M2M100ForConditionalGeneration, M2M100Tokenizer
import logging
import openpyxl
# Configuration du logging
logging.basicConfig(level=logging.INFO)
app = FastAPI()
# Configuration CORS
app.add_middleware(
CORSMiddleware,
allow_origins=["*"],
allow_credentials=True,
allow_methods=["*"],
allow_headers=["*"],
)
UPLOAD_DIR = "uploads"
os.makedirs(UPLOAD_DIR, exist_ok=True)
#traduction-----------------------------------------------------------------------------------------------------------
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
model_name = "facebook/m2m100_418M"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
# Fonction pour extraire le texte
def extract_text_from_pdf(file):
doc = fitz.open(stream=file.file.read(), filetype="pdf")
return "\n".join([page.get_text() for page in doc]).strip()
def extract_text_from_docx(file):
doc = Document(io.BytesIO(file.file.read()))
return "\n".join([para.text for para in doc.paragraphs]).strip()
def extract_text_from_pptx(file):
prs = Presentation(io.BytesIO(file.file.read()))
return "\n".join([shape.text for slide in prs.slides for shape in slide.shapes if hasattr(shape, "text")]).strip()
def extract_text_from_excel(file):
wb = openpyxl.load_workbook(io.BytesIO(file.file.read()), data_only=True)
text = [str(cell) for sheet in wb.worksheets for row in sheet.iter_rows(values_only=True) for cell in row if cell]
return "\n".join(text).strip()
@app.post("/translate/")
async def translate_document(file: UploadFile = File(...), target_lang: str = Form(...)):
"""API pour traduire un document."""
try:
logging.info(f"📥 Fichier reçu : {file.filename}")
logging.info(f"🌍 Langue cible reçue : {target_lang}")
if model is None or tokenizer is None:
return JSONResponse(status_code=500, content={"error": "Modèle de traduction non chargé"})
# Extraction du texte
if file.filename.endswith(".pdf"):
text = extract_text_from_pdf(file)
elif file.filename.endswith(".docx"):
text = extract_text_from_docx(file)
elif file.filename.endswith(".pptx"):
text = extract_text_from_pptx(file)
elif file.filename.endswith(".xlsx"):
text = extract_text_from_excel(file)
else:
return JSONResponse(status_code=400, content={"error": "Format non supporté"})
logging.info(f"📜 Texte extrait : {text[:50]}...")
if not text:
return JSONResponse(status_code=400, content={"error": "Aucun texte trouvé dans le document"})
# Vérifier si la langue cible est supportée
target_lang_id = tokenizer.get_lang_id(target_lang)
if target_lang_id is None:
return JSONResponse(
status_code=400,
content={"error": f"Langue cible '{target_lang}' non supportée. Langues disponibles : {list(tokenizer.lang_code_to_id.keys())}"}
)
# Traduction
tokenizer.src_lang = "fr"
encoded_text = tokenizer(text, return_tensors="pt", padding=True, truncation=True)
logging.info(f"🔍 ID de la langue cible : {target_lang_id}")
generated_tokens = model.generate(**encoded_text, forced_bos_token_id=target_lang_id)
translated_text = tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)[0]
logging.info(f"✅ Traduction réussie : {translated_text[:50]}...")
return {"translated_text": translated_text}
except Exception as e:
logging.error(f"❌ Erreur lors de la traduction : {e}")
return JSONResponse(status_code=500, content={"error": "Échec de la traduction"})
# Servir les fichiers statiques (HTML, CSS, JS)
app.mount("/static", StaticFiles(directory="static", html=True), name="static")
@app.get("/")
async def root():
return RedirectResponse(url="/static/principal.html")
|