Update app.py

app.py

@@ -1,18 +1,17 @@
 from elevenlabs import VoiceSettings
 from elevenlabs.client import ElevenLabs
 from transformers import M2M100ForConditionalGeneration, M2M100Tokenizer
-import whisper
 from ai71  import AI71
 from datetime import datetime
 import os
 import time
 from pydub import AudioSegment
-# from IPython.display import Audio, display, Video, HTML
-# import assemblyai as aai
 from base64 import b64encode
 import gradio as gr
 import concurrent.futures
-import assemblyai as aai
+# from IPython.display import Audio, display, Video, HTML
+# import assemblyai as aai
+# import whisper
 
 # aai.settings.api_key = "d5b107f34d534b4ebdfbd869f8408f92"
 # transcriber = aai.Transcriber()
@@ -163,8 +162,9 @@ def summarize(meeting_texts=meeting_texts):
 
 # Placeholder function for speech to text conversion
 def speech_to_text(video):
+    print(video, type(video))
     print('Started transcribing')
-    audio = AudioSegment.from_file(video, format="mp4")
+    audio = AudioSegment.from_file(video)
     audio.export('temp.wav', format="wav")
     
     # transcript = transcriber.transcribe(video).text