Update transcription_diarization.py

transcription_diarization.py

@@ -11,6 +11,7 @@ from collections import defaultdict
 import numpy as np
 from openai import OpenAI
 from config import openai_api_key
+import json
 
 client = OpenAI(api_key=openai_api_key)
 
@@ -47,14 +48,23 @@ def transcribe_audio(audio_path, language):
             response_format="verbose_json"
         )
 
-    transcription_txt = transcript.text
+    # Print the type and content of the response
+    print("Type of transcript:", type(transcript))
+    print("Content of transcript:")
+    print(json.dumps(transcript, indent=2, default=str))
+
+    # Convert the response to a dictionary if it's not already
+    if not isinstance(transcript, dict):
+        transcript = transcript.model_dump()
+
+    transcription_txt = transcript.get("text", "")
     transcription_chunks = []
 
-    for segment in transcript.segments:
+    for segment in transcript.get("segments", []):
         transcription_chunks.append({
-            "start": segment.start,
-            "end": segment.end,
-            "text": segment.text
+            "start": segment.get("start", 0),
+            "end": segment.get("end", 0),
+            "text": segment.get("text", "")
         })
 
     return transcription_txt, transcription_chunks