Update sentiment_analysis.py

sentiment_analysis.py

@@ -1,8 +1,7 @@
 import os
 import json
 import time
-import speech_recognition as sr
-from vosk import Model, KaldiRecognizer
+from speech_recognition import Recognizer, Microphone, AudioData, UnknownValueError, RequestError
 from transformers import pipeline, AutoModelForSequenceClassification, AutoTokenizer
 from huggingface_hub import login
 from product_recommender import ProductRecommender
@@ -28,35 +27,10 @@ model = AutoModelForSequenceClassification.from_pretrained(model_name)
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 sentiment_analyzer = pipeline("sentiment-analysis", model=model, tokenizer=tokenizer)
 
-# Vosk Speech Recognition Model
-vosk_model_path = config["vosk_model_path"]
-
-if not vosk_model_path:
-    raise ValueError("Error: vosk_model_path is not set in the .env file.")
-
-try:
-    vosk_model = Model(vosk_model_path)
-    print("Vosk model loaded successfully.")
-except Exception as e:
-    raise ValueError(f"Failed to load Vosk model: {e}")
-
-recognizer = KaldiRecognizer(vosk_model, 16000)
-audio = pyaudio.PyAudio()
-
-stream = audio.open(format=pyaudio.paInt16,
-                    channels=1,
-                    rate=16000,
-                    input=True,
-                    frames_per_buffer=4000)
-stream.start_stream()
+# Speech Recognition Setup
+recognizer = Recognizer()
 
 # Function to analyze sentiment
-def preprocess_text(text):
-    """Preprocess text for better sentiment analysis."""
-    # Strip whitespace and convert to lowercase
-    processed = text.strip().lower()
-    return processed
-
 def preprocess_text(text):
     """Preprocess text for better sentiment analysis."""
     return text.strip().lower()
@@ -104,74 +78,79 @@ def transcribe_with_chunks(objections_dict):
     model = SentenceTransformer('all-MiniLM-L6-v2')
 
     try:
-        while True:
-            data = stream.read(4000, exception_on_overflow=False)
-
-            if recognizer.AcceptWaveform(data):
-                result = recognizer.Result()
-                text = json.loads(result)["text"]
-
-                if "start listening" in text.lower():
-                    is_listening = True
-                    print("Listening started. Speak into the microphone.")
-                    continue
-                elif "stop listening" in text.lower():
-                    is_listening = False
-                    print("Listening stopped.")
-                    if current_chunk:
-                        chunk_text = " ".join(current_chunk)
-                        sentiment, score = analyze_sentiment(chunk_text)
-                        chunks.append((chunk_text, sentiment, score))
-                        current_chunk = []
-                    continue
-
-                if is_listening and text.strip():
-                    print(f"Transcription: {text}")
-                    current_chunk.append(text)
-
-                    if time.time() - chunk_start_time > 3:
+        with Microphone() as source:
+            recognizer.adjust_for_ambient_noise(source)
+            print("Microphone calibrated. Please speak.")
+            
+            while True:
+                print("Listening for speech...")
+                try:
+                    audio_data = recognizer.listen(source, timeout=5)
+                    text = recognizer.recognize_google(audio_data)
+
+                    if "start listening" in text.lower():
+                        is_listening = True
+                        print("Listening started. Speak into the microphone.")
+                        continue
+                    elif "stop listening" in text.lower():
+                        is_listening = False
+                        print("Listening stopped.")
                         if current_chunk:
                             chunk_text = " ".join(current_chunk)
-                            
-                            # Always process sentiment
                             sentiment, score = analyze_sentiment(chunk_text)
                             chunks.append((chunk_text, sentiment, score))
-
-                            # Get objection responses and check similarity score
-                            query_embedding = model.encode([chunk_text])
-                            distances, indices = objection_handler.index.search(query_embedding, 1)
-                            
-                            # If similarity is high enough, show objection response
-                            if distances[0][0] < 1.5:  # Threshold for similarity
-                                responses = objection_handler.handle_objection(chunk_text)
-                                if responses:
-                                    print("\nSuggested Response:")
-                                    for response in responses:
-                                        print(f"→ {response}")
-                            
-                            # Get product recommendations and check similarity score
-                            distances, indices = product_recommender.index.search(query_embedding, 1)
-                            
-                            # If similarity is high enough, show recommendations
-                            if distances[0][0] < 1.5:  # Threshold for similarity
-                                recommendations = product_recommender.get_recommendations(chunk_text)
-                                if recommendations:
-                                    print(f"\nRecommendations for this response:")
-                                    for idx, rec in enumerate(recommendations, 1):
-                                        print(f"{idx}. {rec}")
-                            
-                            print("\n")
                             current_chunk = []
-                            chunk_start_time = time.time()
+                        continue
+
+                    if is_listening and text.strip():
+                        print(f"Transcription: {text}")
+                        current_chunk.append(text)
+
+                        if time.time() - chunk_start_time > 3:
+                            if current_chunk:
+                                chunk_text = " ".join(current_chunk)
+                                
+                                # Always process sentiment
+                                sentiment, score = analyze_sentiment(chunk_text)
+                                chunks.append((chunk_text, sentiment, score))
+
+                                # Get objection responses and check similarity score
+                                query_embedding = model.encode([chunk_text])
+                                distances, indices = objection_handler.index.search(query_embedding, 1)
+                                
+                                # If similarity is high enough, show objection response
+                                if distances[0][0] < 1.5:  # Threshold for similarity
+                                    responses = objection_handler.handle_objection(chunk_text)
+                                    if responses:
+                                        print("\nSuggested Response:")
+                                        for response in responses:
+                                            print(f"→ {response}")
+                                
+                                # Get product recommendations and check similarity score
+                                distances, indices = product_recommender.index.search(query_embedding, 1)
+                                
+                                # If similarity is high enough, show recommendations
+                                if distances[0][0] < 1.5:  # Threshold for similarity
+                                    recommendations = product_recommender.get_recommendations(chunk_text)
+                                    if recommendations:
+                                        print(f"\nRecommendations for this response:")
+                                        for idx, rec in enumerate(recommendations, 1):
+                                            print(f"{idx}. {rec}")
+                                
+                                print("\n")
+                                current_chunk = []
+                                chunk_start_time = time.time()
+                except UnknownValueError:
+                    print("Could not understand the audio.")
+                except RequestError as e:
+                    print(f"Could not request results from Google Speech Recognition service; {e}")
 
     except KeyboardInterrupt:
         print("\nExiting...")
-        stream.stop_stream()
-
-    return chunks
+        return chunks
 
 if __name__ == "__main__":
     objections_file_path = r"C:\Users\shaik\Downloads\Sales Calls Transcriptions - Sheet3.csv"
     objections_dict = load_objections(objections_file_path)
     transcribed_chunks = transcribe_with_chunks(objections_dict)
-    print("Final transcriptions and sentiments:", transcribed_chunks)
+    print("Final transcriptions and sentiments:", transcribed_chunks)