Update app.py

app.py

@@ -1,5 +1,4 @@
-import sounddevice as sd
-import numpy as np
+import speech_recognition as sr
 from sentiment_analysis import analyze_sentiment
 from product_recommender import ProductRecommender
 from objection_handler import ObjectionHandler
@@ -20,58 +19,63 @@ model = SentenceTransformer('all-MiniLM-L6-v2')
 def real_time_analysis():
     st.info("Listening... Say 'stop' to end the process.")
 
-    samplerate = 16000  # Sample rate for audio capture
-    duration = 5  # Duration of each audio chunk in seconds
+    recognizer = sr.Recognizer()
     sentiment_scores = []
     transcribed_chunks = []
     total_text = ""
 
     try:
-        while True:
-            # Capture audio
-            audio_data = sd.rec(int(samplerate * duration), samplerate=samplerate, channels=1, dtype='float32')
-            sd.wait()  # Wait for the recording to finish
-
-            # Convert audio data to bytes for processing
-            audio_bytes = (audio_data * 32767).astype(np.int16).tobytes()
-
-            # Analyze the audio
-            text = analyze_audio(audio_bytes, samplerate)
-            if not text:
-                continue
-
-            st.write(f"*Recognized Text:* {text}")
-
-            if 'stop' in text.lower():
-                st.write("Stopping real-time analysis...")
-                break
-
-            # Append to the total conversation
-            total_text += text + " "
-            sentiment, score = analyze_sentiment(text)
-            sentiment_scores.append(score)
-
-            # Handle objection
-            objection_response = handle_objection(text)
-
-            # Get product recommendation
-            recommendations = []
-            if is_valid_input(text) and is_relevant_sentiment(score):
-                query_embedding = model.encode([text])
-                distances, indices = product_recommender.index.search(query_embedding, 1)
+        # Use the virtual microphone device
+        mic = sr.Microphone(device_index=0)  # Use the virtual microphone device index
 
-                if distances[0][0] < 1.5:  # Similarity threshold
-                    recommendations = product_recommender.get_recommendations(text)
-
-            transcribed_chunks.append((text, sentiment, score))
-
-            st.write(f"*Sentiment:* {sentiment} (Score: {score})")
-            st.write(f"*Objection Response:* {objection_response}")
-
-            if recommendations:
-                st.write("*Product Recommendations:*")
-                for rec in recommendations:
-                    st.write(rec)
+        while True:
+            with mic as source:
+                st.write("Listening...")
+                recognizer.adjust_for_ambient_noise(source)
+                audio = recognizer.listen(source)
+
+            try:
+                st.write("Recognizing...")
+                text = recognizer.recognize_google(audio)
+                st.write(f"*Recognized Text:* {text}")
+
+                if 'stop' in text.lower():
+                    st.write("Stopping real-time analysis...")
+                    break
+
+                # Append to the total conversation
+                total_text += text + " "
+                sentiment, score = analyze_sentiment(text)
+                sentiment_scores.append(score)
+
+                # Handle objection
+                objection_response = handle_objection(text)
+
+                # Get product recommendation
+                recommendations = []
+                if is_valid_input(text) and is_relevant_sentiment(score):
+                    query_embedding = model.encode([text])
+                    distances, indices = product_recommender.index.search(query_embedding, 1)
+
+                    if distances[0][0] < 1.5:  # Similarity threshold
+                        recommendations = product_recommender.get_recommendations(text)
+
+                transcribed_chunks.append((text, sentiment, score))
+
+                st.write(f"*Sentiment:* {sentiment} (Score: {score})")
+                st.write(f"*Objection Response:* {objection_response}")
+
+                if recommendations:
+                    st.write("*Product Recommendations:*")
+                    for rec in recommendations:
+                        st.write(rec)
+
+            except sr.UnknownValueError:
+                st.error("Speech Recognition could not understand the audio.")
+            except sr.RequestError as e:
+                st.error(f"Error with the Speech Recognition service: {e}")
+            except Exception as e:
+                st.error(f"Error during processing: {e}")
 
         # After conversation ends, calculate and display overall sentiment and summary
         overall_sentiment = calculate_overall_sentiment(sentiment_scores)
@@ -94,23 +98,6 @@ def real_time_analysis():
     except Exception as e:
         st.error(f"Error in real-time analysis: {e}")
 
-def analyze_audio(audio_bytes, samplerate):
-    """Analyze audio data and return transcribed text."""
-    try:
-        # Use a speech-to-text model or API to transcribe the audio
-        # For simplicity, we'll use a placeholder function
-        text = transcribe_audio(audio_bytes, samplerate)
-        return text
-    except Exception as e:
-        st.error(f"Error analyzing audio: {e}")
-        return None
-
-def transcribe_audio(audio_bytes, samplerate):
-    """Placeholder function for transcribing audio."""
-    # Replace this with your actual speech-to-text implementation
-    # For now, we'll just return a dummy text
-    return "This is a placeholder transcription."
-
 def generate_comprehensive_summary(chunks):
     """Generate a comprehensive summary from conversation chunks."""
     full_text = " ".join([chunk[0] for chunk in chunks])