Update session_analysis.py

session_analysis.py

@@ -1,4 +1,6 @@
 import streamlit as st
+from google.cloud import speech_v1
+import io
 import pandas as pd
 import plotly.express as px
 import plotly.graph_objects as go
@@ -64,23 +66,37 @@ def process_media_file(file, type):
     progress_bar = st.progress(0)
     
     try:
-        # Simulated processing steps
-        for i in range(5):
-            status.text(f"Step {i+1}/5: " + get_processing_step_name(i))
-            progress_bar.progress((i + 1) * 20)
-            
+        # Convert file to audio if needed
+        if type == "Video Recording":
+            status.text("Converting video to audio...")
+            progress_bar.progress(20)
+            # Add video to audio conversion here if needed
+            audio_content = convert_video_to_audio(file)
+        else:
+            audio_content = file.read()
+
         # Generate transcript
-        transcript = generate_transcript(file)
+        status.text("Generating transcript...")
+        progress_bar.progress(60)
+        
+        transcript = generate_transcript(audio_content)
+        
         if transcript:
             st.session_state.current_transcript = transcript
+            status.text("Analyzing content...")
+            progress_bar.progress(80)
             analyze_session_content(transcript)
             
+        progress_bar.progress(100)
+        status.text("Processing complete!")
+            
     except Exception as e:
         st.error(f"Error processing file: {str(e)}")
     finally:
         status.empty()
         progress_bar.empty()
 
+
 def get_processing_step_name(step):
     steps = [
         "Loading media file",
@@ -207,6 +223,50 @@ def analyze_session_content(content):
     except Exception as e:
         st.error(f"Error during analysis: {str(e)}")
 
+
+def generate_transcript(audio_content):
+    """
+    Generate transcript from audio content using Google Speech-to-Text
+    Note: This requires the Google Cloud Speech-to-Text API
+    """
+    try:
+        # Initialize Speech-to-Text client
+        client = speech_v1.SpeechClient()
+
+        # Configure audio and recognition settings
+        audio = speech_v1.RecognitionAudio(content=audio_content)
+        config = speech_v1.RecognitionConfig(
+            encoding=speech_v1.RecognitionConfig.AudioEncoding.LINEAR16,
+            sample_rate_hertz=16000,
+            language_code="en-US",
+            enable_automatic_punctuation=True,
+        )
+
+        # Perform the transcription
+        response = client.recognize(config=config, audio=audio)
+
+        # Combine all transcriptions
+        transcript = ""
+        for result in response.results:
+            transcript += result.alternatives[0].transcript + " "
+
+        return transcript.strip()
+
+    except Exception as e:
+        st.error(f"Error in transcript generation: {str(e)}")
+        return None
+
+def convert_video_to_audio(video_file):
+    """
+    Convert video file to audio content
+    Note: This is a placeholder - you'll need to implement actual video to audio conversion
+    """
+    # Placeholder for video to audio conversion
+    # You might want to use libraries like moviepy or ffmpeg-python
+    st.warning("Video to audio conversion not implemented yet")
+    return None
+
+    
 def process_analysis_results(raw_analysis):
     """Process and structure the analysis results"""
     # Parse the raw analysis text and extract structured data