Update app.py

app.py

@@ -1,34 +1,56 @@
+
 import streamlit as st
 from transformers import pipeline
 from pydub import AudioSegment
 import os
 
+# Set Streamlit page config
+st.set_page_config(page_title="Atma.ai - Session Summarizer", layout="centered")
+
 st.title("🧠 Atma.ai – Mental Health Session Summarizer")
+st.markdown("Upload a therapy session audio file to get a transcript, summary, and emotional insights.")
 
-uploaded_file = st.file_uploader("Upload an audio file", type=["wav", "mp3", "m4a"])
+# Upload audio
+uploaded_file = st.file_uploader("🎙️ Upload audio", type=["wav", "mp3", "m4a"])
 
 if uploaded_file:
     st.audio(uploaded_file)
-    
-    # Save the uploaded file
+
+    # Save and convert audio
     audio_path = "temp_audio.wav"
     audio = AudioSegment.from_file(uploaded_file)
     audio = audio.set_channels(1).set_frame_rate(16000)
     audio.export(audio_path, format="wav")
 
-    st.write("✅ Audio converted. Starting transcription...")
-
-    st.spinner("Transcribing with Whisper...")
+    # Transcribe
+    st.info("Transcribing audio using Whisper...")
     asr = pipeline("automatic-speech-recognition", model="openai/whisper-small")
-    result = asr(audio_path)
+    result = asr(audio_path, return_timestamps=True)
     transcript = result["text"]
 
-    st.subheader("Transcript")
+    st.subheader("📝 Transcript")
     st.write(transcript)
 
-    st.subheader("Summary")
+    # Summarize
+    st.info("Generating summary...")
     summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
-    summary = summarizer(transcript, max_length=200, min_length=40, do_sample=False)
+    summary = summarizer(transcript, max_length=250, min_length=50, do_sample=False)
+
+    st.subheader("📋 Summary")
     st.write(summary[0]["summary_text"])
 
-    os.remove(audio_path)  # clean up temp file
+    # Emotion tagging
+    st.info("Analyzing emotional tone...")
+    emotion_model = pipeline("text-classification", model="j-hartmann/emotion-english-distilroberta-base", return_all_scores=True)
+    emotion_results = emotion_model(transcript)
+
+    # Aggregate emotions
+    avg_scores = {}
+    for result in emotion_results[0]:
+        avg_scores[result['label']] = round(result['score'] * 100, 2)
+
+    st.subheader("💬 Emotional Insights")
+    for emotion, score in avg_scores.items():
+        st.write(f"{emotion}: {score}%")
+
+    os.remove(audio_path)