change of models

app.py

@@ -1,52 +1,62 @@
 import gradio as gr
-from transformers import T5ForConditionalGeneration, T5Tokenizer, pipeline
+from transformers import pipeline
 
-# Initialize T5 model and tokenizer 
-model_name = "t5-base"
-tokenizer = T5Tokenizer.from_pretrained(model_name)
-model = T5ForConditionalGeneration.from_pretrained(model_name)
-
-# Use pipeline for translation
-translator = pipeline("translation", model=model, tokenizer=tokenizer)
+# Initialiser les pipelines de traduction pour chaque paire de langues
+# Utiliser des modèles Helsinki-NLP qui sont spécifiquement entraînés pour la traduction
+translation_models = {
+    "English-French": pipeline("translation", model="Helsinki-NLP/opus-mt-en-fr"),
+    "French-English": pipeline("translation", model="Helsinki-NLP/opus-mt-fr-en"),
+    "English-Spanish": pipeline("translation", model="Helsinki-NLP/opus-mt-en-es"),
+    "Spanish-English": pipeline("translation", model="Helsinki-NLP/opus-mt-es-en"),
+    "English-Japanese": pipeline("translation", model="Helsinki-NLP/opus-mt-en-jap"),
+    "Japanese-English": pipeline("translation", model="Helsinki-NLP/opus-mt-jap-en"),
+    "English-Chinese": pipeline("translation", model="Helsinki-NLP/opus-mt-en-zh"),
+    "Chinese-English": pipeline("translation", model="Helsinki-NLP/opus-mt-zh-en"),
+    "French-Spanish": pipeline("translation", model="Helsinki-NLP/opus-mt-fr-es"),
+    "Spanish-French": pipeline("translation", model="Helsinki-NLP/opus-mt-es-fr"),
+    "French-Japanese": pipeline("translation", model="Helsinki-NLP/opus-mt-fr-jap"),
+    "Japanese-French": pipeline("translation", model="Helsinki-NLP/opus-mt-jap-fr"),
+    "French-Chinese": pipeline("translation", model="Helsinki-NLP/opus-mt-fr-zh"),
+    "Chinese-French": pipeline("translation", model="Helsinki-NLP/opus-mt-zh-fr"),
+    "Spanish-Japanese": pipeline("translation", model="Helsinki-NLP/opus-mt-es-jap"),
+    "Japanese-Spanish": pipeline("translation", model="Helsinki-NLP/opus-mt-jap-es"),
+    "Spanish-Chinese": pipeline("translation", model="Helsinki-NLP/opus-mt-es-zh"),
+    "Chinese-Spanish": pipeline("translation", model="Helsinki-NLP/opus-mt-zh-es"),
+    "Japanese-Chinese": pipeline("translation", model="Helsinki-NLP/opus-mt-jap-zh"),
+    "Chinese-Japanese": pipeline("translation", model="Helsinki-NLP/opus-mt-zh-jap")
+}
 
-# Language codes for T5
-language_codes = {
-    "English": "en",
-    "French": "fr",
-    "Japanese": "ja",
-    "Spanish": "es",
-    "Mandarin": "zh"
+# Mappages des noms des langues
+language_names = {
+    "English": "English",
+    "French": "French",
+    "Japanese": "Japanese",
+    "Spanish": "Spanish",
+    "Chinese": "Chinese"  # Renommé de "Mandarin" à "Chinese" pour correspondre aux noms des modèles
 }
 
 def translate(text, source_lang, target_lang):
-    """Translate text using T5 model"""
+    """Traduire le texte en utilisant le modèle approprié"""
     if not text:
         return ""
     
     if source_lang == target_lang:
         return text
     
-    source_code = language_codes[source_lang]
-    target_code = language_codes[target_lang]
-    
-    # Format input for T5 (needs to be in format: "translate {source} to {target}: {text}")
-    input_text = f"translate {source_code} to {target_code}: {text}"
+    # Construire la clé du modèle
+    model_key = f"{source_lang}-{target_lang}"
     
-    try:
-        # Use the pipeline to handle translation
-        result = translator(input_text, max_length=512)
-        translation = result[0]["translation_text"]
-        
-        # Check if the output starts with the target language code and fix it
-        prefix = f"{target_code} {target_code}: "
-        if translation.startswith(prefix):
-            translation = translation[len(prefix):]
-        
-        return translation
-    except Exception as e:
-        return f"Translation error: {str(e)}"
+    # Vérifier si ce modèle existe
+    if model_key in translation_models:
+        try:
+            result = translation_models[model_key](text)
+            return result[0]["translation_text"]
+        except Exception as e:
+            return f"Erreur de traduction: {str(e)}"
+    else:
+        return f"La traduction de {source_lang} vers {target_lang} n'est pas prise en charge."
 
-# Example texts in different languages with descriptive labels
+# Exemples de textes dans différentes langues avec des étiquettes descriptives
 examples = {
     "English": {
         "Basic greeting": "Hello, how are you today?",
@@ -76,7 +86,7 @@ examples = {
         "Clima": "Hoy es un hermoso día soleado.",
         "Pregunta": "¿Dónde está la estación de tren más cercana?"
     },
-    "Mandarin": {
+    "Chinese": {
         "问候": "你好，今天好吗？",
         "旅行": "我希望有一天能去日本。",
         "食物": "我喜欢土豆和蔬菜。",
@@ -85,41 +95,41 @@ examples = {
     }
 }
 
-# Create Gradio interface
+# Créer l'interface Gradio
 with gr.Blocks() as demo:
-    gr.Markdown("# Multilingual Translation with T5")
+    gr.Markdown("# Traduction Multilingue")
     
     with gr.Row():
         source_lang = gr.Dropdown(
-            choices=list(language_codes.keys()),
-            label="Source Language",
+            choices=list(language_names.keys()),
+            label="Langue source",
             value="English"
         )
         target_lang = gr.Dropdown(
-            choices=list(language_codes.keys()),
-            label="Target Language",
+            choices=list(language_names.keys()),
+            label="Langue cible",
             value="French"
         )
     
     with gr.Row():
         with gr.Column():
-            source_text = gr.Textbox(label="Source Text", lines=5)
-            translate_btn = gr.Button(value="Translate")
+            source_text = gr.Textbox(label="Texte source", lines=5)
+            translate_btn = gr.Button(value="Traduire")
         
         with gr.Column():
-            target_text = gr.Textbox(label="Translation Result", lines=5)
+            target_text = gr.Textbox(label="Résultat de la traduction", lines=5)
     
-    # Add examples section
-    with gr.Accordion("Examples", open=True):
+    # Ajouter une section d'exemples
+    with gr.Accordion("Exemples", open=True):
         example_dropdown = gr.Dropdown(
             choices=list(examples["English"].keys()),
-            label="Select an example",
+            label="Sélectionner un exemple",
             interactive=True,
             value=list(examples["English"].keys())[0] if examples["English"] else None
         )
-        load_example_btn = gr.Button(value="Load Example")
+        load_example_btn = gr.Button(value="Charger l'exemple")
     
-    # Update example dropdown when source language changes
+    # Mettre à jour le menu déroulant d'exemples lorsque la langue source change
     def update_examples_dropdown(lang):
         return gr.Dropdown.update(
             choices=list(examples.get(lang, {}).keys()),
@@ -132,7 +142,7 @@ with gr.Blocks() as demo:
         outputs=[example_dropdown]
     )
     
-    # Load selected example into the source text
+    # Charger l'exemple sélectionné dans le texte source
     def load_selected_example(example_label, lang):
         return examples.get(lang, {}).get(example_label, "")
     
@@ -142,14 +152,14 @@ with gr.Blocks() as demo:
         outputs=[source_text]
     )
     
-    # Set up translation function
+    # Configurer la fonction de traduction
     translate_btn.click(
         translate,
         inputs=[source_text, source_lang, target_lang],
         outputs=target_text
     )
     
-    # Also translate when Enter is pressed in the source text box
+    # Traduire également lorsque la touche Entrée est appuyée dans la zone de texte source
     source_text.submit(
         translate,
         inputs=[source_text, source_lang, target_lang],

requirements.txt

@@ -1,4 +1,5 @@
 gradio>=3.50.2
 transformers>=4.35.0
 torch>=2.0.0
-sentencepiece>=0.1.99
+sentencepiece>=0.1.99
+sacremoses>=0.0.53