Update app.py

app.py

@@ -1,92 +1,53 @@
 import gradio as gr
 from transformers import pipeline
 
-def create_speech_analyzer():
-    # Initialize models with error handling
-    try:
-        # Load Whisper model for speech recognition
-        transcriber = pipeline(
-            "automatic-speech-recognition", 
-            model="openai/whisper-medium",
-            max_new_tokens=128
-        )
-        
-        # Load sentiment analysis model
-        sentiment_model = pipeline(
-            "sentiment-analysis",
-            model="distilbert-base-uncased-finetuned-sst-2-english"
-        )
-        
-        return transcriber, sentiment_model
-    
-    except Exception as e:
-        raise RuntimeError(f"Error loading models: {str(e)}")
+# Load Whisper for speech-to-text
+whisper = pipeline("automatic-speech-recognition", model="openai/whisper-medium")
 
-def analyze_speech(audio_file):
-    """
-    Analyze speech audio for transcription and sentiment.
-    
-    Args:
-        audio_file: Path to audio file or audio data
-        
-    Returns:
-        dict: Contains transcription, sentiment and confidence score
-    """
+# Load a sentiment analysis model
+sentiment_analyzer = pipeline("sentiment-analysis", model="distilbert-base-uncased-finetuned-sst-2-english")
+
+# Function to process audio and analyze tone
+def analyze_call(audio_file):
     try:
-        # Get model instances
-        transcriber, sentiment_model = create_speech_analyzer()
-        
-        # Transcribe audio
-        transcription = transcriber(audio_file)["text"]
+        # Step 1: Transcribe audio to text using Whisper
+        transcription = whisper(audio_file)["text"]
         
-        # Analyze sentiment
-        sentiment_result = sentiment_model(transcription)[0]
+        # Step 2: Analyze sentiment of the transcription
+        sentiment_result = sentiment_analyzer(transcription)[0]
         
-        return {
+        # Prepare the output
+        output = {
             "transcription": transcription,
             "sentiment": sentiment_result["label"],
-            "confidence": f"{sentiment_result['score']:.2%}"
+            "confidence": round(sentiment_result["score"], 4)
         }
-        
+        return output
     except Exception as e:
-        return {
-            "transcription": f"Error processing audio: {str(e)}",
-            "sentiment": "ERROR",
-            "confidence": "0%"
-        }
+        return {"error": str(e)}
 
-def create_interface():
-    """Create and configure the Gradio interface"""
-    return gr.Interface(
-        fn=analyze_speech,
-        inputs=gr.Audio(
-            sources=["microphone", "upload"],  # Changed from source to sources
-            type="filepath",
-            label="Upload or Record Audio"
-        ),
-        outputs=[
-            gr.Textbox(label="Transcription"),
-            gr.Textbox(label="Sentiment Analysis"),
-            gr.Textbox(label="Confidence Score")
-        ],
-        title="Real-Time Speech Sentiment Analyzer",
-        description="""
-        This tool transcribes speech and analyzes its sentiment in real-time.
-        Upload an audio file or record directly through your microphone.
-        """,
-        theme=gr.themes.Soft(),
-        examples=[],  # Add example audio files here if desired
-        cache_examples=True
+# Gradio Interface
+def gradio_interface(audio):
+    if audio is None:
+        return "Please record or upload an audio file."
+    result = analyze_call(audio)
+    if "error" in result:
+        return f"Error: {result['error']}"
+    return (
+        f"**Transcription:** {result['transcription']}\n\n"
+        f"**Sentiment:** {result['sentiment']}\n\n"
+        f"**Confidence:** {result['confidence']}"
     )
 
-def main():
-    # Create and launch the interface
-    interface = create_interface()
-    interface.launch(
-        share=True,  # Enable sharing via public URL
-        debug=True,  # Enable debug mode for better error messages
-        server_name="0.0.0.0"  # Allow external connections
-    )
+# Create Gradio app
+interface = gr.Interface(
+    fn=gradio_interface,
+    inputs=gr.Audio(source="microphone", type="filepath", label="Record or Upload Audio"),
+    outputs=gr.Textbox(label="Analysis Result", lines=5),
+    title="Real-Time Call Analysis",
+    description="Record or upload audio to analyze tone and sentiment in real time.",
+    live=False  # Set to False to avoid constant re-runs
+)
 
-if __name__ == "__main__":
-    main()
+# Launch the app
+interface.launch()