Alex/python.traduction
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

optimisation

Browse Source
This commit is contained in:
Alex
2026-01-14 23:54:12 +01:00
parent aee2716a41
commit 70e4932cd0
3 changed files with 62 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

38
Traduction/main.py
View File

@@ -3,23 +3,23 @@ import requests
import json
from reportlab.lib.pagesizes import letter
from reportlab.lib.units import inch
from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer, Flowable
from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer
from reportlab.lib.styles import getSampleStyleSheet, ParagraphStyle
from reportlab.lib.enums import TA_JUSTIFY
from reportlab.pdfbase import pdfmetrics
from reportlab.pdfbase.ttfonts import TTFont
import os
import os, time
# Configuration
DEBUG = True
PDF_PATH = "Traduction\TaniaBorecMemoir(Ukr).pdf"
PDF_PATH = "Traduction/TaniaBorecMemoir(Ukr).pdf"
OLLAMA_MODEL = "traductionUkrainienVersFrancais:latest"
OLLAMA_URL = "http://localhost:11434/api/generate"
TARGET_LANGUAGE = "français"
CHECKPOINT_FILE = "Traduction\checkpoint.json"
TEMP_OUTPUT_TXT = "Traduction\output_temp.txt"
FINAL_OUTPUT_PDF = PDF_PATH.replace(".pdf",f"({TARGET_LANGUAGE.upper()[:2]})_V8.pdf")
FINAL_OUTPUT_TXT = PDF_PATH.replace(".pdf",f"({TARGET_LANGUAGE.upper()[:2]})_V8.txt")
CHECKPOINT_FILE = "Traduction/checkpoint.json"
TEMP_OUTPUT_TXT = "Traduction/output_temp.txt"
FINAL_OUTPUT_PDF = PDF_PATH.replace(".pdf",f"({TARGET_LANGUAGE.upper()[:2]})_V9.pdf")
FINAL_OUTPUT_TXT = PDF_PATH.replace(".pdf",f"({TARGET_LANGUAGE.upper()[:2]})_V9.txt")
DEBUG = True
@@ -341,6 +341,7 @@ def main():
print(f"Batches manquants détectés : {missing_batches}")
# Traduction des paragraphes manquants
temps_cumule = 0.0
for i in missing_batches:
batch = paragraphs[i:i + batch_size]
paragraph_cumul = "\n".join(batch)
@@ -348,13 +349,24 @@ def main():
print(f"{15 * '-'} Traduction des paragraphes manquants {i+1} à {min(i + batch_size, len(paragraphs))} / {len(paragraphs)}")
try:
debut_chrono = time.time()
result = send_to_ollama(paragraph_cumul)
fin_chrono = time.time()
temps_paragraphe = fin_chrono - debut_chrono
temps_cumule += temps_paragraphe
# Conversion en minutes et secondes
minutes_paragraphe, secondes_paragraphe = divmod(temps_paragraphe, 60)
minutes_cumule, secondes_cumule = divmod(temps_cumule, 60)
print(f"{result}")
results[str(i)] = result
save_checkpoint(len(paragraphs), results) # Met à jour le dernier indice du batch
save_temp_results(results)
except Exception as e:
print(f"Erreur lors de la traduction du paragraphe {i}: {e}")
print(f" Temps de traduction : {int(minutes_paragraphe)} min {secondes_paragraphe:.2f} sec")
print(f" Temps cumulé : {int(minutes_cumule)} min {secondes_cumule:.2f} sec")
# Traitement des paragraphes suivants
for i in range(last_index + 1, len(paragraphs), batch_size):
@@ -364,7 +376,16 @@ def main():
print(f"{15 * '-'} Traduction des paragraphes {i+1} à {min(i + batch_size, len(paragraphs))} / {len(paragraphs)}")
try:
debut_chrono = time.time()
result = send_to_ollama(paragraph_cumul)
fin_chrono = time.time()
temps_paragraphe = fin_chrono - debut_chrono
temps_cumule += temps_paragraphe
# Conversion en minutes et secondes
minutes_paragraphe, secondes_paragraphe = divmod(temps_paragraphe, 60)
minutes_cumule, secondes_cumule = divmod(temps_cumule, 60)
print(f"{result}")
results[str(i)] = result
save_checkpoint(i + batch_size - 1, results)
@@ -372,6 +393,9 @@ def main():
except Exception as e:
print(f"Erreur : {e}")
continue
print(f" Temps de traduction : {int(minutes_paragraphe)} min {secondes_paragraphe:.2f} sec")
print(f" Temps cumulé : {int(minutes_cumule)} min {secondes_cumule:.2f} sec")
save_temp_results(results)
create_pdf_from_results(results, FINAL_OUTPUT_PDF)