Update app.py

app.py

@@ -3,8 +3,13 @@ import gradio as gr
 import whisper
 from gtts import gTTS
 import io
+import logging
 from huggingface_hub import InferenceClient
 
+# Set up logging
+logging.basicConfig(level=logging.DEBUG)
+logger = logging.getLogger(__name__)
+
 # Initialize the Hugging Face Inference Client
 client = InferenceClient("mistralai/Mistral-7B-Instruct-v0.1")
 
@@ -16,172 +21,29 @@ def format_prompt(message, history):
     You are a smart mood analyser, who determines user mood. Based on the user input, classify the mood of the user into one of the four moods {Happy, Sad, Instrumental, Party}. If you are finding it difficult to classify into one of these four moods, keep the conversation going on until we classify the user's mood. Return a single-word reply from one of the options if you have classified. Suppose you classify a sentence as happy, then just respond with "happy".
 
     Note: Do not write anything else other than the classified mood if classified.
-
     Note: If any question or any user text cannot be classified, follow up with a question to know the user's mood until you classify the mood.
-
     Note: Mood should be classified only from any of these 4 classes {Happy, Sad, Instrumental, Party}, if not any of these 4 then continue with a follow-up question until you classify the mood.
-
     Note: if user asks something like i need a coffee then do not classify the mood directly and ask more follow-up questions as asked in examples.
 
-            Examples
-            User: What is C programming?
-            LLM Response: C programming is a programming language. How are you feeling now after knowing the answer?
-
-            User: Can I get a coffee?
-            LLM Response: It sounds like you're in need of a little pick-me-up. How are you feeling right now? Are you looking for something upbeat, something to relax to, or maybe some instrumental music while you enjoy your coffee?
-            User: I feel like rocking
-            LLM Response: Party
-
-            User: I'm feeling so energetic today!
-            LLM Response: Happy
-
-            User: I'm feeling down today.
-            LLM Response: Sad
-
-            User: I'm ready to have some fun tonight!
-            LLM Response: Party
-
-            User: I need some background music while I am stuck in traffic.
-            LLM Response: Instrumental
-
-            User: Hi
-            LLM Response: Hi, how are you doing?
-
-            User: Feeling okay only.
-            LLM Response: Are you having a good day?
-            User: I don't know
-            LLM Response: Do you want to listen to some relaxing music?
-            User: No
-            LLM Response: How about listening to some rock and roll music?
-            User: Yes
-            LLM Response: Party
-
-            User: Where do I find an encyclopedia?
-            LLM Response: You can find it in any of the libraries or on the Internet. Does this answer make you happy?
-
-            User: I need a coffee
-            LLM Response: It sounds like you're in need of a little pick-me-up. How are you feeling right now? Are you looking for something upbeat, something to relax to, or maybe some instrumental music while you enjoy your coffee?
-
-            User: I just got promoted at work!
-            LLM Response: Happy
-
-            User: Today is my birthday!
-            LLM Response: Happy
-
-            User: I won a prize in the lottery.
-            LLM Response: Happy
-
-            User: I am so excited about my vacation next week!
-            LLM Response: Happy
-
-            User: I aced my exams!
-            LLM Response: Happy
-
-            User: I had a wonderful time with my family today.
-            LLM Response: Happy
-
-            User: I just finished a great workout!
-            LLM Response: Happy
-
-            User: I am feeling really good about myself today.
-            LLM Response: Happy
-
-            User: I finally finished my project and it was a success!
-            LLM Response: Happy
-
-            User: I just heard my favorite song on the radio.
-            LLM Response: Happy
-
-            User: My pet passed away yesterday.
-            LLM Response: Sad
-
-            User: I lost my job today.
-            LLM Response: Sad
-
-            User: I'm feeling really lonely.
-            LLM Response: Sad
-
-            User: I didn't get the results I wanted.
-            LLM Response: Sad
-
-            User: I had a fight with my best friend.
-            LLM Response: Sad
+    Examples:
+    User: I'm feeling so energetic today!
+    LLM Response: Happy
 
-            User: I'm feeling really overwhelmed with everything.
-            LLM Response: Sad
+    User: I'm feeling down today.
+    LLM Response: Sad
 
-            User: I just got some bad news.
-            LLM Response: Sad
+    User: I need some background music while I am stuck in traffic.
+    LLM Response: Instrumental
 
-            User: I'm missing my family.
-            LLM Response: Sad
+    User: Let's have a blast tonight!
+    LLM Response: Party
 
-            User: I am feeling really down today.
-            LLM Response: Sad
+    User: Hi
+    LLM Response: Hi, how are you doing?
 
-            User: Nothing seems to be going right.
-            LLM Response: Sad
-
-            User: I need some music while I study.
-            LLM Response: Instrumental
-
-            User: I want to listen to something soothing while I work.
-            LLM Response: Instrumental
-
-            User: Do you have any recommendations for background music?
-            LLM Response: Instrumental
-
-            User: I'm looking for some relaxing tunes.
-            LLM Response: Instrumental
-
-            User: I need some music to focus on my tasks.
-            LLM Response: Instrumental
-
-            User: Can you suggest some ambient music for meditation?
-            LLM Response: Instrumental
-
-            User: What's good for background music during reading?
-            LLM Response: Instrumental
-
-            User: I need some calm music to help me sleep.
-            LLM Response: Instrumental
-
-            User: I prefer instrumental music while cooking.
-            LLM Response: Instrumental
-
-            User: What's the best music to play while doing yoga?
-            LLM Response: Instrumental
-
-            User: Let's have a blast tonight!
-            LLM Response: Party
-
-            User: I'm in the mood to dance!
-            LLM Response: Party
-
-            User: I want to celebrate all night long!
-            LLM Response: Party
-
-            User: Time to hit the club!
-            LLM Response: Party
-
-            User: I feel like partying till dawn.
-            LLM Response: Party
-
-            User: Let's get this party started!
-            LLM Response: Party
-
-            User: I'm ready to party hard tonight.
-            LLM Response: Party
-
-            User: I'm in the mood for some loud music and dancing!
-            LLM Response: Party
-
-            User: Tonight's going to be epic!
-            LLM Response: Party
-
-            User: Lets turn up the music and have some fun!
-            LLM Response: Party
-            """
+    User: I need a coffee
+    LLM Response: It sounds like you're in need of a little pick-me-up. How are you feeling right now? Are you looking for something upbeat, something to relax to, or maybe some instrumental music while you enjoy your coffee?
+    """
     prompt = f"<s>{fixed_prompt}"
     for user_prompt, bot_response in history:
         prompt += f"\n User:{user_prompt}\n LLM Response:{bot_response}"
@@ -229,14 +91,41 @@ def generate(
 
 def process_audio(audio_file):
     try:
+        logger.debug(f"Processing audio file: {audio_file}")
+        
+        # Check if audio_file is None or empty
+        if audio_file is None or not os.path.exists(audio_file):
+            logger.warning("No audio input detected")
+            return "No audio input detected. Please try again.", "", None
+
+        # Load audio file
+        audio = whisper.load_audio(audio_file)
+        
+        # Check if audio is empty
+        if len(audio) == 0:
+            logger.warning("Empty audio file detected")
+            return "The audio file appears to be empty. Please try again with a valid audio input.", "", None
+
         # Transcribe the audio using Whisper
-        result = model.transcribe(audio_file)
+        logger.debug("Transcribing audio")
+        result = model.transcribe(audio)
         text = result["text"]
         
+        # Check if transcription is empty
+        if not text.strip():
+            logger.warning("No speech detected in the audio")
+            return "No speech detected in the audio. Please try speaking more clearly or check your microphone.", "", None
+        
+        logger.debug(f"Transcribed text: {text}")
+        
         # Generate a response using the existing generate function
+        logger.debug("Generating response")
         response = generate(text, [])
         
+        logger.debug(f"Generated response: {response}")
+        
         # Convert the response text to speech
+        logger.debug("Converting response to speech")
         tts = gTTS(response)
         response_audio_io = io.BytesIO()
         tts.write_to_fp(response_audio_io)
@@ -247,9 +136,11 @@ def process_audio(audio_file):
         with open(response_audio_path, "wb") as audio_file:
             audio_file.write(response_audio_io.getvalue())
         
+        logger.debug("Audio processing completed successfully")
         return text, response, response_audio_path
     except Exception as e:
-        return f"An error occurred: {e}", "", None
+        logger.exception("An error occurred while processing audio")
+        return f"An error occurred: {str(e)}", "", None
 
 # Create the Gradio interface with customized UI
 with gr.Blocks(css="""
@@ -295,7 +186,7 @@ with gr.Blocks(css="""
     
     with gr.Row():
         with gr.Column():
-            audio_input = gr.Audio(sources="microphone", type="filepath", label="Upload Audio or Use Microphone")
+            audio_input = gr.Audio(source="microphone", type="filepath", label="Upload Audio or Use Microphone")
             submit_button = gr.Button("Submit")
         
         with gr.Column():
@@ -305,4 +196,5 @@ with gr.Blocks(css="""
     
     submit_button.click(fn=process_audio, inputs=audio_input, outputs=[transcription, response_text, response_audio])
 
-demo.launch(share=True)
+if __name__ == "__main__":
+    demo.launch(share=True)