Create app.py

app.py

@@ -0,0 +1,58 @@
+import streamlit as st
+from transformers import MarianMTModel, MarianTokenizer
+
+# Define a function to load the model and tokenizer based on selected languages
+def load_model_and_tokenizer(src_lang, tgt_lang):
+    model_name = f'Helsinki-NLP/opus-mt-{src_lang}-{tgt_lang}'
+    model = MarianMTModel.from_pretrained(model_name)
+    tokenizer = MarianTokenizer.from_pretrained(model_name)
+    return model, tokenizer
+
+# Define a function for translation
+def translate_text(text, model, tokenizer):
+    inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True)
+    translated = model.generate(**inputs)
+    return tokenizer.decode(translated[0], skip_special_tokens=True)
+
+# Streamlit UI
+st.set_page_config(page_title="Language Translator", layout="wide")
+st.title("🌍 Language Translator")
+st.markdown("Translate text quickly and easily between multiple languages using open-source models.")
+
+# Language options (You can extend this list as needed)
+language_codes = {
+    "English": "en", "Spanish": "es", "French": "fr", "German": "de", "Chinese": "zh", "Japanese": "ja", "Hindi": "hi", "Arabic": "ar", "Russian": "ru", "Portuguese": "pt",
+}
+
+# User inputs for source and target languages
+col1, col2 = st.columns(2)
+with col1:
+    source_language = st.selectbox("Select source language:", options=language_codes.keys(), index=0)
+with col2:
+    target_language = st.selectbox("Select target language:", options=language_codes.keys(), index=1)
+
+# Input text
+st.subheader("Input Text")
+input_text = st.text_area("Enter the text you want to translate:", height=150)
+
+# Translation logic
+if st.button("Translate"):
+    if not input_text.strip():
+        st.error("Please enter text to translate.")
+    elif source_language == target_language:
+        st.warning("Source and target languages are the same. Please select different languages.")
+    else:
+        try:
+            src_lang = language_codes[source_language]
+            tgt_lang = language_codes[target_language]
+            model, tokenizer = load_model_and_tokenizer(src_lang, tgt_lang)
+            translation = translate_text(input_text, model, tokenizer)
+
+            st.subheader("Translated Text")
+            st.text_area("Translation:", value=translation, height=150, disabled=True)
+        except Exception as e:
+            st.error(f"An error occurred: {e}")
+
+# Footer
+st.markdown("---")
+st.markdown("Developed using [Helsinki-NLP](https://huggingface.co/Helsinki-NLP) open-source models and Streamlit.")