Update app.py

app.py

@@ -1,6 +1,7 @@
 import gradio as gr
 import speech_recognition as sr
 from io import BytesIO
+from pydub import AudioSegment
 
 def transcribe_audio(audio_input):
     recognizer = sr.Recognizer()
@@ -14,8 +15,14 @@ def transcribe_audio(audio_input):
     # Use BytesIO to create a file-like object from the audio bytes
     audio_file = BytesIO(audio_data_bytes)
     
-    # Load the audio file from the file-like object
-    with sr.AudioFile(audio_file) as source:
+    # Convert audio to WAV format using pydub
+    audio_segment = AudioSegment.from_file(audio_file)
+    wav_io = BytesIO()
+    audio_segment.export(wav_io, format="wav")
+    wav_io.seek(0)  # Move to the beginning of the file-like object
+    
+    # Load the audio file from the file-like object in WAV format
+    with sr.AudioFile(wav_io) as source:
         audio_data = recognizer.record(source)
         
     try: