Update app.py

app.py

@@ -9,11 +9,6 @@ from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassifica
 from wordcloud import WordCloud
 import matplotlib.pyplot as plt
 import io
-import speech_recognition as sr
-from gtts import gTTS
-import os
-
-
 
 # Download NLTK resources
 nltk.download('punkt')
@@ -35,22 +30,6 @@ def load_classification_model():
 def load_qa_model():
     return pipeline("question-answering", model="deepset/roberta-base-squad2")
 
-def recognize_speech():
-    recognizer = sr.Recognizer()
-    with sr.Microphone() as source:
-        st.info("Listening... Speak now.")
-        try:
-            audio = recognizer.listen(source, timeout=5)  # Listen for 5 seconds
-            question_text = recognizer.recognize_google(audio)  # Convert speech to text
-            st.success(f"You said: {question_text}")  # Show recognized text
-            return question_text
-        except sr.UnknownValueError:
-            st.error("Sorry, could not understand the audio.")
-        except sr.RequestError:
-            st.error("Could not request results, check your internet connection.")
-    return Non
-
-
 # Preprocessing function (same as in Section 01)
 def preprocess_text(text):
     # Lowercase
@@ -106,32 +85,6 @@ st.markdown("""
     </style>
     """, unsafe_allow_html=True)
 
-st.markdown("""
-    <script>
-    function startRecording() {
-        var recognition = new webkitSpeechRecognition() || new SpeechRecognition();
-        recognition.lang = 'en-US';
-        recognition.interimResults = false;
-        recognition.maxAlternatives = 1;
-        
-        recognition.onresult = function(event) {
-            var transcript = event.results[0][0].transcript;
-            var questionInput = document.getElementById("question_input");
-            questionInput.value = transcript;
-            questionInput.dispatchEvent(new Event('input', { bubbles: true }));
-        };
-
-        recognition.onerror = function(event) {
-            alert("Error occurred: " + event.error);
-        };
-
-        recognition.start();
-    }
-    </script>
-""", unsafe_allow_html=True)
-
-
-
 # App title and description
 st.title("📰 Daily Mirror News Analyzer")
 st.markdown("""
@@ -209,13 +162,7 @@ with tab2:
         st.warning("Please upload a CSV file.")
    
     
-    # Input field for voice/text-based questions
-    question = st.text_input("Enter your question:", key="question_input")
-    
-    # Button to start voice recording
-    st.button("🎙 Speak", on_click=lambda: st.markdown('<script>startRecording()</script>', unsafe_allow_html=True))
-
- 
+    question = st.text_input("Enter your question:")
     
     if st.button("Get Answer") and context and question:
         with st.spinner("Searching for answers..."):
@@ -227,9 +174,6 @@ with tab2:
             
             st.subheader("Details")
             st.write(f"Confidence: {result['score']:.2f}")
-
-            
-
             
 
 with tab3:
@@ -251,7 +195,7 @@ with tab3:
                 st.warning("This text appears negative.")
     
     # Named Entity Recognition
-    st.subheader("🏷️ Named Entity Recognition")
+    st.subheader("🏷 Named Entity Recognition")
     ner_text = st.text_area("Enter text for entity recognition:", height=100)
     if st.button("Extract Entities"):
         with st.spinner("Identifying entities..."):
@@ -269,7 +213,7 @@ with tab3:
             st.table(pd.DataFrame(entities))
     
     # Text Summarization
-    st.subheader("✍️ Text Summarization")
+    st.subheader("✍ Text Summarization")
     summary_text = st.text_area("Enter text to summarize:", height=150)
     if st.button("Generate Summary"):
         with st.spinner("Generating summary..."):