commit

app.py

@@ -3,6 +3,8 @@ from pytube import YouTube
 from moviepy.editor import *
 import speech_recognition as sr
 from transformers import pipeline
+from pydub import AudioSegment
+import os
 
 def download_and_extract_audio(youtube_link):
     yt = YouTube(youtube_link)
@@ -11,7 +13,12 @@ def download_and_extract_audio(youtube_link):
     base, ext = os.path.splitext(out_file)
     new_file = base + '.mp3'
     os.rename(out_file, new_file)
-    return new_file
+
+    # Convert MP3 to WAV for compatibility with speech_recognition
+    audio = AudioSegment.from_mp3(new_file)
+    wav_file = base + '.wav'
+    audio.export(wav_file, format="wav")
+    return wav_file
 
 def transcribe_audio(audio_path):
     recognizer = sr.Recognizer()