Update app.py

app.py

@@ -1,3 +1,5 @@
+import numpy as np
+import sounddevice as sd
 import speech_recognition as sr
 from sentiment_analysis import analyze_sentiment
 from product_recommender import ProductRecommender
@@ -19,6 +21,110 @@ objection_handler = ObjectionHandler('objections.csv')
 product_recommender = ProductRecommender('recommendations.csv')
 model = SentenceTransformer('all-MiniLM-L6-v2')
 
+def record_audio(duration=5, sample_rate=16000):
+    """
+    Record audio using sounddevice and return as NumPy array
+    """
+    st.write("Recording...")
+    audio = sd.rec(int(duration * sample_rate), samplerate=sample_rate, channels=1, dtype='float32')
+    sd.wait()
+    st.write("Recording finished.")
+    return audio.flatten(), sample_rate
+    
+def numpy_to_audio_data(audio_data):
+    """
+    Convert NumPy array to AudioData for speech_recognition
+    """
+    # Convert float32 to int16
+    int_audio = (audio_data * 32767).astype(np.int16)
+    
+    # Create AudioData object
+    recognizer = sr.Recognizer()
+    audio_data = sr.AudioData(
+        int_audio.tobytes(), 
+        sample_rate=16000, 
+        sample_width=int_audio.dtype.itemsize
+    )
+    return audio_data
+
+def real_time_analysis():
+    recognizer = sr.Recognizer()
+    sentiment_scores = []
+    transcribed_chunks = []
+    total_text = ""
+
+    try:
+        while True:
+            # Record audio using sounddevice
+            audio_array, sample_rate = record_audio()
+            
+            # Convert NumPy array to AudioData
+            audio_data = numpy_to_audio_data(audio_array)
+
+            try:
+                # Transcribe using speech_recognition
+                text = recognizer.recognize_google(audio_data)
+                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)
+        call_summary = generate_comprehensive_summary(transcribed_chunks)
+        
+        st.subheader("Conversation Summary:")
+        st.write(total_text.strip())
+        st.subheader("Overall Sentiment:")
+        st.write(overall_sentiment)
+
+        # Store data in Google Sheets
+        store_data_in_sheet(
+            config["google_sheet_id"], 
+            transcribed_chunks, 
+            call_summary, 
+            overall_sentiment
+        )
+        st.success("Conversation data stored successfully in Google Sheets!")
+
+    except Exception as e:
+        st.error(f"Error in real-time analysis: {e}")
+
 def generate_comprehensive_summary(chunks):
     """
     Generate a comprehensive summary from conversation chunks
@@ -88,6 +194,7 @@ def generate_comprehensive_summary(chunks):
     
     return summary
 
+
 def is_valid_input(text):
     text = text.strip().lower()
     if len(text) < 3 or re.match(r'^[a-zA-Z\s]*$', text) is None:
@@ -109,87 +216,6 @@ def calculate_overall_sentiment(sentiment_scores):
         overall_sentiment = "NEUTRAL"
     return overall_sentiment
 
-def real_time_analysis():
-    recognizer = sr.Recognizer()
-    mic = sr.Microphone()
-
-    st.info("Say 'stop' to end the process.")
-
-    sentiment_scores = []
-    transcribed_chunks = []
-    total_text = ""
-
-    try:
-        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)
-        call_summary = generate_comprehensive_summary(transcribed_chunks)
-        
-        st.subheader("Conversation Summary:")
-        st.write(total_text.strip())
-        st.subheader("Overall Sentiment:")
-        st.write(overall_sentiment)
-
-        # Store data in Google Sheets
-        store_data_in_sheet(
-            config["google_sheet_id"], 
-            transcribed_chunks, 
-            call_summary, 
-            overall_sentiment
-        )
-        st.success("Conversation data stored successfully in Google Sheets!")
-
-    except Exception as e:
-        st.error(f"Error in real-time analysis: {e}")
-
 def handle_objection(text):
     query_embedding = model.encode([text])
     distances, indices = objection_handler.index.search(query_embedding, 1)
@@ -198,7 +224,6 @@ def handle_objection(text):
         return "\n".join(responses) if responses else "No objection response found."
     return "No objection response found."
 
-# (Previous imports remain the same)
 
 def run_app():
     st.set_page_config(page_title="Sales Call Assistant", layout="wide")