Update transcription_diarization.py

transcription_diarization.py

@@ -3,10 +3,27 @@ import time
 import json
 import os
 import urllib.parse
+from moviepy.editor import VideoFileClip
 import requests
 from botocore.exceptions import ClientError
 from config import aws_access_key_id, aws_secret_access_key
 
+def convert_to_mono_audio(video_path, output_format='wav'):
+    base_name = os.path.splitext(os.path.basename(video_path))[0]
+    output_path = f"{base_name}_mono.{output_format}"
+    
+    try:
+        video = VideoFileClip(video_path)
+        audio = video.audio
+        audio = audio.set_channels(1)  # Convert to mono
+        audio.write_audiofile(output_path)
+        video.close()
+        audio.close()
+        return output_path
+    except Exception as e:
+        print(f"Error during audio conversion: {str(e)}")
+        return None
+
 def upload_to_s3(local_file_path, bucket_name, s3_file_key):
     s3_client = boto3.client('s3',
                              aws_access_key_id=aws_access_key_id,
@@ -106,6 +123,13 @@ def extract_transcriptions_with_speakers(transcript_data):
 
 
 def diarize_audio(video_path):
+    # Convert video to mono audio
+    output_format = 'wav'
+    mono_audio_path = convert_to_mono_audio(video_path, output_format)
+    
+    if not mono_audio_path:
+        return "Audio conversion failed."
+    
     bucket_name = 'transcriptionjobbucket'
     s3_file_key = os.path.basename(video_path)
     file_uri = upload_to_s3(video_path, bucket_name, s3_file_key)