Update app.py

app.py

@@ -1,20 +1,9 @@
 import streamlit as st
-from transformers import pipeline
-from googletrans import Translator
+import deepl  # DeepL API client library
 
-# Function to handle translation using Hugging Face or Google Translate
-def translate_text(text, target_language="es"):
-    # Hugging Face pipeline for translation (can be used for various language pairs)
-    try:
-        translator = pipeline("translation", model="Helsinki-NLP/opus-mt-en-es")
-        result = translator(text, max_length=400)
-        return result[0]['translation_text']
-    except Exception as e:
-        st.error("Error translating text using Hugging Face. Trying Google Translate instead.")
-        # Fallback to Google Translate if Hugging Face fails
-        translator = Translator()
-        translated_text = translator.translate(text, dest=target_language).text
-        return translated_text
+# Initialize the DeepL Translator with your API key
+DEEPL_API_KEY = "your_deepL_api_key"  # Replace with your DeepL API key
+translator = deepl.Translator(DEEPL_API_KEY)
 
 # Streamlit UI setup
 st.set_page_config(page_title="AI-Powered Language Learning Assistant", page_icon="🧠", layout="wide")
@@ -32,40 +21,42 @@ Welcome to your AI-powered language assistant! Here you can:
 text_input = st.text_input("Enter the text you want to translate or practice", "")
 
 # Select target language for translation
-language = st.selectbox("Select the language to translate to", ["es", "fr", "de", "it", "pt", "ru"])
+language = st.selectbox("Select the language to translate to", ["ES", "FR", "DE", "IT", "PT", "RU"])
 
 if text_input:
-    # Translate text
+    # Translate text using DeepL API
     st.subheader(f"Original Text: {text_input}")
-    translated_text = translate_text(text_input, target_language=language)
+    translated_text = translator.translate_text(text_input, target_lang=language)
 
     # Display translation
     st.markdown(f"### Translated Text to {language.upper()}:")
-    st.write(translated_text)
+    st.write(translated_text.text)
 
     # Show pronunciation tip
     st.subheader("Pronunciation Tip:")
-    st.write("Use an app like Google Translate or Forvo to practice pronunciation. If you want help with specific words, type them below.")
-    
+    st.write("Use an app like Forvo or Google Translate to practice pronunciation. You can also use DeepL for listening practice on the translated text.")
+
     # Grammar Check (simple demo)
     st.subheader("Grammar Feedback:")
-    st.write("For more advanced grammar feedback, please use language tools like Grammarly or LanguageTool.")
+    st.write("For advanced grammar feedback, use grammar-checking tools like LanguageTool.")
 
 # Vocabulary practice section
 st.markdown("---")
 st.header("Vocabulary Practice")
 word_input = st.text_input("Enter a word to get its definition and synonyms", "")
 if word_input:
-    # Using Hugging Face API to fetch definitions and synonyms (this part can be expanded with a dedicated model)
+    # For vocabulary practice, let's use the Hugging Face BERT model for related words
+    from transformers import pipeline
+
     try:
         word_model = pipeline("fill-mask", model="bert-base-uncased")  # Using BERT to predict related words
         result = word_model(f"The synonym of {word_input} is [MASK].")
         st.write(f"Synonyms or related words for **{word_input}**: {result}")
     except Exception as e:
         st.error("Error fetching vocabulary practice data.")
-    
+
 # Footer for engagement
 st.markdown("""
 ---
-**Need more practice?** Visit [Google Translate](https://translate.google.com) for real-time translations and pronunciation!
+**Need more practice?** Visit [DeepL](https://www.deepl.com) for real-time translations and pronunciation!
 """)