Initial commit

.dockerignore

@@ -0,0 +1,6 @@
+__pycache__/
+*.pyc
+*.pyo
+*.pyd
+.env
+venv/

.gitattributes

@@ -0,0 +1,4 @@
+*.pdf filter=lfs diff=lfs merge=lfs -text
+*.xlsx filter=lfs diff=lfs merge=lfs -text
+*.docx filter=lfs diff=lfs merge=lfs -text
+*.pptx filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,7 @@
+from fastapi import FastAPI
+
+app = FastAPI()
+
+@app.get("/")
+def home():
+    return {"message": "Hello, Huging Face!"}

document-translation

@@ -0,0 +1 @@
+Subproject commit de121a8cd759d996b71d7c28bff6504a66162227

main.py

@@ -0,0 +1,105 @@
+"""from fastapi import FastAPI, File, UploadFile, HTTPException, Form
+from fastapi.responses import HTMLResponse, JSONResponse
+from fastapi.staticfiles import StaticFiles
+from transformers import pipeline
+import textwrap
+import fitz  # PyMuPDF for PDF
+from docx import Document
+import openpyxl  # For Excel
+from pptx import Presentation
+import os
+
+app = FastAPI()
+
+# Serve static files (like index.html)
+app.mount("/static", StaticFiles(directory="static"), name="static")
+
+@app.get("/", response_class=HTMLResponse)
+async def read_root():
+    with open("static/index.html", "r") as file:
+        html_content = file.read()
+    return HTMLResponse(content=html_content)
+
+# Language codes mapping
+LANGUAGE_CODES = {
+    "Anglais": "en",
+    "Français": "fr",
+    "Arabe": "ar",
+    "Espagnol": "es",
+    "Allemand": "de",
+    "Italien": "it",
+    "Portugais": "pt",
+    "Néerlandais": "nl"
+}
+
+# Function to load translation model for dynamic language pairs
+def load_translator(src_lang: str, tgt_lang: str):
+    src_code = LANGUAGE_CODES.get(src_lang)
+    tgt_code = LANGUAGE_CODES.get(tgt_lang)
+
+    if not src_code or not tgt_code:
+        raise ValueError(f"Unsupported language pair: {src_lang} -> {tgt_lang}")
+
+    try:
+        model_name = f"Helsinki-NLP/opus-mt-{src_code}-{tgt_code}"
+        return pipeline("translation", model=model_name)
+    except Exception as e:
+        if src_code != "en" and tgt_code != "en":
+            model_src_to_en = pipeline("translation", model=f"Helsinki-NLP/opus-mt-{src_code}-en")
+            model_en_to_tgt = pipeline("translation", model=f"Helsinki-NLP/opus-mt-en-{tgt_code}")
+            return (model_src_to_en, model_en_to_tgt)
+        else:
+            raise ValueError(f"No available translation model for {src_lang} -> {tgt_lang}")
+
+# Function to split text into manageable chunks
+def chunk_text(text, max_length=400):
+    return textwrap.wrap(text, max_length)
+
+# Extract text from different file types
+def extract_text(file: UploadFile):
+    if file.filename.endswith(".txt"):
+        return file.file.read().decode("utf-8")
+    elif file.filename.endswith(".pdf"):
+        doc = fitz.open(stream=file.file.read(), filetype="pdf")
+        return "\n".join([page.get_text() for page in doc])
+    elif file.filename.endswith(".docx"):
+        doc = Document(file.file)
+        return "\n".join([para.text for para in doc.paragraphs])
+    elif file.filename.endswith(".xlsx"):
+        wb = openpyxl.load_workbook(file.file)
+        sheets = wb.sheetnames
+        text = ""
+        for sheet in sheets:
+            ws = wb[sheet]
+            for row in ws.iter_rows():
+                text += "\t".join([str(cell.value or "") for cell in row]) + "\n"
+        return text
+    elif file.filename.endswith(".pptx"):
+        prs = Presentation(file.file)
+        text = ""
+        for slide in prs.slides:
+            for shape in slide.shapes:
+                if hasattr(shape, "text"):
+                    text += shape.text + "\n"
+        return text
+    else:
+        raise HTTPException(status_code=400, detail="Unsupported file type.")
+
+# Upload and translate files
+@app.post("/upload/")
+async def upload_file(file: UploadFile = File(...), src_lang: str = Form(...), tgt_lang: str = Form(...)):
+    try:
+        text = extract_text(file)
+        translators = load_translator(src_lang, tgt_lang)
+
+        chunks = chunk_text(text)
+        if isinstance(translators, tuple):
+            translated_chunks = [translators[1](translators[0](chunk, max_length=400)[0]['translation_text'], max_length=400)[0]['translation_text'] for chunk in chunks]
+        else:
+            translated_chunks = [translators(chunk, max_length=400)[0]['translation_text'] for chunk in chunks]
+
+        translated_text = " ".join(translated_chunks)
+        return JSONResponse(content={"filename": file.filename, "translated_text": translated_text})
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Translation failed: {str(e)}")
+"""

static/Dockerfile

@@ -0,0 +1,20 @@
+# Utilisation de l'image Python comme base
+FROM python:3.9
+
+# Définition du répertoire de travail
+WORKDIR /app
+
+# Copier les fichiers du projet dans l'image Docker
+COPY . .
+
+# Installer les dépendances
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Exposer le port utilisé par FastAPI
+EXPOSE 7860
+
+# Lancer l'application avec Uvicorn
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]
+
+
+ENV C:\Program Files\Docker\Docker

static/README.md

@@ -0,0 +1,10 @@
+# Document Translation API
+
+Cette application permet de traduire des documents (TXT, PDF, DOCX) en plusieurs langues en utilisant FastAPI et les modèles de traduction de Hugging Face.
+
+## Comment l'utiliser ?
+1. **Uploader un document** (TXT, PDF, DOCX)
+2. **Choisir la langue source et la langue cible**
+3. **Obtenir la traduction instantanée !**
+
+Déployé sur Hugging Face Spaces avec Docker. 🚀

static/index.html

@@ -0,0 +1,120 @@
+
+        <!DOCTYPE html>
+        <html lang="en">
+        <head>
+            <meta charset="UTF-8">
+            <meta name="viewport" content="width=device-width, initial-scale=1.0">
+            <title>Document Translation Service</title>
+            <style>
+                body {
+                    font-family: Arial, sans-serif;
+                    background-color: #f4f4f4;
+                    display: flex;
+                    justify-content: center;
+                    align-items: center;
+                    height: 100vh;
+                    margin: 0;
+                }
+                .container {
+                    background: white;
+                    padding: 2rem;
+                    border-radius: 8px;
+                    box-shadow: 0 4px 10px rgba(0,0,0,0.1);
+                    width: 100%;
+                    max-width: 500px;
+                }
+                h1 {
+                    font-size: 1.8rem;
+                    margin-bottom: 1rem;
+                    text-align: center;
+                    color: #333;
+                }
+                label {
+                    display: block;
+                    margin-bottom: 0.5rem;
+                    font-weight: bold;
+                }
+                input, select, button {
+                    width: 100%;
+                    padding: 0.75rem;
+                    margin-bottom: 1rem;
+                    border: 1px solid #ddd;
+                    border-radius: 4px;
+                }
+                button {
+                    background-color: #4caf50;
+                    color: white;
+                    font-size: 1rem;
+                    cursor: pointer;
+                    border: none;
+                }
+                button:hover {
+                    background-color: #45a049;
+                }
+                #result {
+                    background: #f4f4f4;
+                    padding: 1rem;
+                    border: 1px solid #ddd;
+                    border-radius: 4px;
+                    white-space: pre-wrap;
+                    min-height: 100px;
+                }
+                .error {
+                    color: red;
+                    font-weight: bold;
+                }
+            </style>
+        </head>
+        <body>
+            <div class="container">
+                <h1>Document Translator</h1>
+                <form id="uploadForm" enctype="multipart/form-data">
+                    <label for="file">Choose a file that you (TXT, PDF, DOCX, PPTX, XLSX):</label>
+                    <input type="file" id="file" name="file" accept=".txt,.pdf,.docx,.pptx,.xlsx" required>
+                    <label for="src_lang">Source Language:</label>
+                    <select id="src_lang" name="src_lang">
+                        <option>Anglais</option>
+                        <option>Fran�ais</option>
+                        <option>Arabe</option>
+                        <option>Espagnol</option>
+                        <option>Allemand</option>
+                        <option>Italien</option>
+                        <option>Portugais</option>
+                        <option>N�erlandais</option>
+                    </select>
+                    <label for="tgt_lang">Target Language:</label>
+                    <select id="tgt_lang" name="tgt_lang">
+                        <option>Anglais</option>
+                        <option>Fran�ais</option>
+                        <option>Arabe</option>
+                        <option>Espagnol</option>
+                        <option>Allemand</option>
+                        <option>Italien</option>
+                        <option>Portugais</option>
+                        <option>N�erlandais</option>
+                    </select>
+                    <button type="submit">Translate</button>
+                </form>
+                <h2>Translation Result:</h2>
+                <pre id="result"></pre>
+            </div>
+            <script>
+                document.getElementById('uploadForm').onsubmit = async function(event) {
+                    event.preventDefault();
+                    const formData = new FormData(this);
+                    const response = await fetch('/upload/', {
+                        method: 'POST',
+                        body: formData
+                    });
+                    const result = await response.json();
+                    if (result.translated_text) {
+                        document.getElementById('result').textContent = result.translated_text;
+                    } else {
+                        document.getElementById('result').textContent = 'Error: ' + result.detail;
+                        document.getElementById('result').classList.add('error');
+                    }
+                }
+            </script>
+        </body>
+        </html>
+        

static/requirements.txt

@@ -0,0 +1,9 @@
+fastapi
+uvicorn
+transformers
+torch
+textwrap3
+pymupdf
+python-docx
+openpyxl
+pillow

uploads/TD1 (1).docx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a80769ffc2bd30394ef3124842a08c2a72dda9c161488c363799f53520895ec2
+size 53350

uploads/Untitled.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb03deee8b41e265cde7eb86f14deae4cc505d9fef18a3cdaccde123f7ca6ae8
+size 349803

uploads/chapitre 2 RECONNAISSANCE DE FORMES ET CLASSIFICATION.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad0c7e09e566f603390d90611e4fd0c969d6920a064b4cf74fdbcde58fc8c7e
+size 1665388