Update app.py

app.py

@@ -9,10 +9,11 @@ from transformers import (
     SpeechT5HifiGan,
     AutoModelForCausalLM,
     AutoTokenizer
-)  # For emotion analysis, text-to-speech, and text generation
+)  # For sentiment analysis, text-to-speech, and text generation
 from datasets import load_dataset  # For loading datasets (e.g., speaker embeddings)
 import torch  # For tensor operations
 import soundfile as sf  # For saving audio as .wav files
+import sentencepiece  # For tokenization (required by SpeechT5Processor)
 
 ##########################################
 # Streamlit application title and input
@@ -45,99 +46,84 @@ def response_gen(user_review):
     """
     Generate a concise and logical response based on the sentiment of the user's comment.
     """
-    
     dominant_emotion = analyze_dominant_emotion(user_review)  # Get the dominant emotion of the user's comment
     emotion_label = dominant_emotion['label'].lower()  # Extract the emotion label in lowercase format
     
     # Define response templates for each emotion
-
-    emotion_strategies = {
-      "anger": {
-          "prompt": (
-              "Customer complaint: '{review}'\n\n"
-              "As a customer service representative, craft a professional response that:\n"
-              "- Begins with sincere apology and acknowledgment\n"
-              "- Clearly explains solution process with concrete steps\n"
-              "- Offers appropriate compensation/redemption\n"
-              "- Keeps tone humble and solution-focused (3-4 sentences)\n\n"
-              "Response:"
-          )
-      },
-      "disgust": {
-          "prompt": (
-              "Customer quality concern: '{review}'\n\n"
-              "As a customer service representative, craft a response that:\n"
-              "- Immediately acknowledges the product issue\n"
-              "- Explains quality control measures being taken\n"
-              "- Provides clear return/replacement instructions\n"
-              "- Offers goodwill gesture (3-4 sentences)\n\n"
-              "Response:"
-          )
-      },
-      "fear": {
-          "prompt": (
-              "Customer safety concern: '{review}'\n\n"
-              "As a customer service representative, craft a reassuring response that:\n"
-              "- Directly addresses the safety worries\n"
-              "- References relevant certifications/standards\n"
-              "- Offers dedicated support contact\n"
-              "- Provides satisfaction guarantee (3-4 sentences)\n\n"
-              "Response:"
-          )
-      },
-      "joy": {
-          "prompt": (
-              "Customer review: '{review}'\n\n"
-              "As a customer service representative, craft a concise response that:\n"
-              "- Specifically acknowledges both positive and constructive feedback\n"
-              "- Briefly mentions loyalty/referral programs\n"
-              "- Ends with shopping invitation (3-4 sentences)\n\n"
-              "Response:"
-          )
-      },
-      "neutral": {
-          "prompt": (
-              "Customer feedback: '{review}'\n\n"
-              "As a customer service representative, craft a balanced response that:\n"
-              "- Provides additional relevant product information\n"
-              "- Highlights key service features\n"
-              "- Politely requests more detailed feedback\n"
-              "- Maintains professional tone (3-4 sentences)\n\n"
-              "Response:"
-          )
-      },
-      "sadness": {
-          "prompt": (
-              "Customer disappointment: '{review}'\n\n"
-              "As a customer service representative, craft an empathetic response that:\n"
-              "- Shows genuine understanding of the issue\n"
-              "- Proposes personalized recovery solution\n"
-              "- Offers extended support options\n"
-              "- Maintains positive outlook (3-4 sentences)\n\n"
-              "Response:"
-          )
-      },
-      "surprise": {
-          "prompt": (
-              "Customer enthusiastic feedback: '{review}'\n\n"
-              "As a customer service representative, craft a response that:\n"
-              "- Matches customer's positive energy appropriately\n"
-              "- Highlights unexpected product benefits\n"
-              "- Invites to user community/events\n"
-              "- Maintains brand voice (3-4 sentences)\n\n"
-              "Response:"
-          )
-      }
-
+    emotion_prompts = {
+        "anger": (
+            f"Customer complaint: '{user_review}'\n\n"
+            "As a customer service representative, craft a professional response that:\n"
+            "- Begins with sincere apology and acknowledgment\n"
+            "- Clearly explains solution process with concrete steps\n"
+            "- Offers appropriate compensation/redemption\n"
+            "- Keeps tone humble and solution-focused (3-4 sentences)\n\n"
+            "Response:"
+        ),
+        "disgust": (
+            f"Customer quality concern: '{user_review}'\n\n"
+            "As a customer service representative, craft a response that:\n"
+            "- Immediately acknowledges the product issue\n"
+            "- Explains quality control measures being taken\n"
+            "- Provides clear return/replacement instructions\n"
+            "- Offers goodwill gesture (3-4 sentences)\n\n"
+            "Response:"
+        ),
+        "fear": (
+            f"Customer safety concern: '{user_review}'\n\n"
+            "As a customer service representative, craft a reassuring response that:\n"
+            "- Directly addresses the safety worries\n"
+            "- References relevant certifications/standards\n"
+            "- Offers dedicated support contact\n"
+            "- Provides satisfaction guarantee (3-4 sentences)\n\n"
+            "Response:"
+        ),
+        "joy": (
+            f"Customer review: '{user_review}'\n\n"
+            "As a customer service representative, craft a concise and enthusiastic response that:\n"
+            "- Thanks the customer for their feedback\n"
+            "- Acknowledges both positive and constructive comments\n"
+            "- Invites them to explore loyalty programs\n\n"
+            "Response:"
+        ),
+        "neutral": (
+            f"Customer feedback: '{user_review}'\n\n"
+            "As a customer service representative, craft a balanced response that:\n"
+            "- Provides additional relevant product information\n"
+            "- Highlights key service features\n"
+            "- Politely requests more detailed feedback\n"
+            "- Maintains professional tone (3-4 sentences)\n\n"
+            "Response:"
+        ),
+        "sadness": (
+            f"Customer disappointment: '{user_review}'\n\n"
+            "As a customer service representative, craft an empathetic response that:\n"
+            "- Shows genuine understanding of the issue\n"
+            "- Proposes personalized recovery solution\n"
+            "- Offers extended support options\n"
+            "- Maintains positive outlook (3-4 sentences)\n\n"
+            "Response:"
+        ),
+        "surprise": (
+            f"Customer enthusiastic feedback: '{user_review}'\n\n"
+            "As a customer service representative, craft a response that:\n"
+            "- Matches customer's positive energy appropriately\n"
+            "- Highlights unexpected product benefits\n"
+            "- Invites to user community/events\n"
+            "- Maintains brand voice (3-4 sentences)\n\n"
+            "Response:"
+        )
+    }
+    
     # Select the appropriate prompt based on the user's emotion, or default to neutral
     prompt = emotion_prompts.get(
-        emotion_label,
+        emotion_label, 
         f"Neutral feedback: '{user_review}'\n\nWrite a professional and concise response (50-200 words max).\n\nResponse:"
     )
     
     # Load the tokenizer and language model for text generation
-    tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen1.5-0.5B") # Load tokenizer for processing text inputs
-    model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen1.5-0.5B") # Load language model for response generation
+    tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen1.5-0.5B")  # Load tokenizer for processing text inputs
+    model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen1.5-0.5B")  # Load language model for response generation
 
     inputs = tokenizer(prompt, return_tensors="pt")  # Tokenize the input prompt
     outputs = model.generate(
@@ -150,7 +136,7 @@ def response_gen(user_review):
 
     # Decode the generated response back into text
     response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    print(f" {response}")  # Debug print statement for generated text
+    print(f"Generated response: {response}")  # Print the response for debugging
     return response  # Return the generated response
 
 ##########################################
@@ -158,9 +144,8 @@ def response_gen(user_review):
 ##########################################
 def sound_gen(response):
     """
-    Convert the generated response to speech and save as a .wav file.
+    Convert the generated response to speech and save it as a .wav file.
     """
-    # Load the pre-trained TTS models for speech synthesis
     processor = SpeechT5Processor.from_pretrained("microsoft/speecht5_tts")  # Pre-trained processor for TTS
     model = SpeechT5ForTextToSpeech.from_pretrained("microsoft/speecht5_tts")  # Pre-trained TTS model
     vocoder = SpeechT5HifiGan.from_pretrained("microsoft/speecht5_hifigan")  # Vocoder for generating waveforms
@@ -179,10 +164,8 @@ def sound_gen(response):
     
     # Save the audio as a .wav file
     sf.write("customer_service_response.wav", speech.numpy(), samplerate=16000)
-    # Play the generated audio in the Streamlit app
     st.audio("customer_service_response.wav")  # Embed an audio player in the web app
 
-
 ##########################################
 # Main Function
 ##########################################
@@ -197,4 +180,4 @@ def main():
 
 # Run the main function when the script is executed
 if __name__ == "__main__":
-    main()
+    main()