translation

app.py

@@ -1,47 +1,53 @@
 import streamlit as st
-from transformers import pipeline
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer, TranslationPipeline
 
 print("Loading the model...")
 
 # Title and Description
-st.title("Sentiment Analysis Web App")
+st.title("Translation Web App")
 st.write("""
 ### Powered by Hugging Face and Streamlit
-This app uses a pre-trained NLP model from Hugging Face to analyze the sentiment of the text you enter.  
-Try entering a sentence to see if it's positive, negative, or neutral!
+This app uses a pre-trained NLP model from Hugging Face to translate text between languages.  
+Enter text in the source language, select source and target languages, and see the translation!
 """)
 
-# Initialize Hugging Face Sentiment Analysis Pipeline
+# Initialize Hugging Face Translation Pipeline
 @st.cache_resource
-def load_model():
-    print("before load model")
-    return pipeline("sentiment-analysis", model="distilbert-base-uncased-finetuned-sst-2-english")
+def load_translation_pipeline():
+    print("Loading translation model...")
+    model = AutoModelForSeq2SeqLM.from_pretrained('issai/tilmash')
+    tokenizer = AutoTokenizer.from_pretrained("issai/tilmash")
+    return TranslationPipeline(model=model, tokenizer=tokenizer, max_length=1000)
 
-sentiment_analyzer = load_model()
+tilmash = load_translation_pipeline()
 
-# Input Text from User
-user_input = st.text_area("Enter some text to analyze:", "Streamlit and Hugging Face make NLP fun!")
+languages = {
+    "Kazakh (Cyrillic)": "kaz_Cyrl",
+    "Russian (Cyrillic)": "rus_Cyrl",
+    "English (Latin)": "eng_Latn",
+    "Turkish (Latin)": "tur_Latn"
+}
 
-# Analyze Sentiment
-if st.button("Analyze Sentiment"):
-    print("button click")
+src_lang = st.selectbox("Select source language:", options=list(languages.keys()), index=0)
+tgt_lang = st.selectbox("Select target language:", options=list(languages.keys()), index=2)
+
+user_input = st.text_area("Enter text to translate:", "")
+
+if st.button("Translate Text"):
     if user_input.strip():
-        result = sentiment_analyzer(user_input)[0]
-        sentiment = result['label']
-        score = result['score']
-
-        # Display the Result
-        st.subheader("Sentiment Analysis Result")
-        st.write(f"**Sentiment:** {sentiment}")
-        st.write(f"**Confidence Score:** {score:.2f}")
+        result = tilmash(user_input, src_lang=languages[src_lang], tgt_lang=languages[tgt_lang])
+        translation = result[0]['translation_text']
+
+        st.subheader("Translation Result")
+        st.write(f"**Translated Text:** {translation}")
     else:
-        st.warning("Please enter some text to analyze!")
+        st.warning("Please enter some text to translate!")
 
 # Sidebar with About Information
 st.sidebar.title("About")
 st.sidebar.info("""
 This app demonstrates the use of Hugging Face's NLP models with Streamlit.  
-It uses the `distilbert-base-uncased-finetuned-sst-2-english` model for sentiment analysis.
+It uses the `issai/tilmash` model for translation between languages such as Kazakh, Russian, English, and Turkish.
 """)
 
-print('after')
+print('After translation operation')