Update app.py

app.py

@@ -1,32 +1,51 @@
+import gradio as gr
+from speech_to_text import SpeechToText
+from sentiment_analysis import SentimentAnalyzer
 import os
-from fastapi import FastAPI, UploadFile, File
-import tempfile
 
-# Ensure Whisper is installed
-os.system("pip install openai-whisper torch transformers")
-
-import whisper
-from transformers import pipeline
-
-app = FastAPI()
-
-# Load Models
-speech_model = whisper.load_model("base")
-sentiment_analyzer = pipeline("sentiment-analysis")
-
-@app.post("/analyze/")
-async def analyze(audio: UploadFile = File(...)):
-    with tempfile.NamedTemporaryFile(delete=False) as temp:
-        temp.write(await audio.read())
-        temp_path = temp.name
-
-    # Transcribe Speech
-    transcription = speech_model.transcribe(temp_path)["text"]
-
-    # Analyze Sentiment
-    sentiment = sentiment_analyzer(transcription)
-
-    return {
-        "transcription": transcription,
-        "sentiment": sentiment[0]
-    }
+# Initialize models
+stt = SpeechToText()
+sentiment_analyzer = SentimentAnalyzer()
+
+def process_audio(audio_path):
+    try:
+        # Get transcription
+        transcription = stt.transcribe(audio_path)
+        
+        # Analyze sentiment
+        sentiment = sentiment_analyzer.analyze(transcription)
+        
+        return {
+            "transcription": transcription,
+            "sentiment": sentiment
+        }
+    except Exception as e:
+        return {
+            "transcription": f"Error: {str(e)}",
+            "sentiment": [{"label": "ERROR", "score": 0.0}]
+        }
+
+# Create Gradio interface
+def create_interface():
+    with gr.Blocks() as demo:
+        gr.Markdown("# Voice Intelligence Demo")
+        
+        with gr.Row():
+            audio_input = gr.Audio(source="microphone", type="filepath")
+            
+        with gr.Row():
+            transcription_output = gr.Textbox(label="Transcription")
+            sentiment_output = gr.JSON(label="Sentiment Analysis")
+            
+        audio_input.change(
+            fn=process_audio,
+            inputs=[audio_input],
+            outputs=[transcription_output, sentiment_output]
+        )
+    
+    return demo
+
+# Launch the app
+if __name__ == "__main__":
+    demo = create_interface()
+    demo.launch()