Update app.py

app.py

@@ -18,6 +18,18 @@ def video_to_audio(video_file):
     audio.write_audiofile(temp_audio_path)
     return temp_audio_path
 
+# Function to convert MP3 audio to WAV
+def convert_mp3_to_wav(mp3_file):
+    # Load the MP3 file using pydub
+    audio = AudioSegment.from_mp3(mp3_file)
+    
+    # Create a temporary WAV file
+    temp_wav_path = tempfile.mktemp(suffix=".wav")
+    
+    # Export the audio to the temporary WAV file
+    audio.export(temp_wav_path, format="wav")
+    return temp_wav_path
+
 # Function to transcribe audio to text
 def transcribe_audio(audio_file):
     # Initialize recognizer
@@ -55,12 +67,16 @@ if uploaded_video is not None:
     st.write("Converting video to audio...")
     audio_file = video_to_audio(tmp_video_path)
     
+    # Convert the extracted MP3 audio to WAV
+    st.write("Converting audio to WAV...")
+    wav_audio_file = convert_mp3_to_wav(audio_file)
+    
     # Provide the audio file to the user for download
-    st.audio(audio_file, format='audio/mp3')
+    st.audio(wav_audio_file, format='audio/wav')
     
     # Transcribe audio to text
     st.write("Transcribing audio to text...")
-    transcription = transcribe_audio(audio_file)
+    transcription = transcribe_audio(wav_audio_file)
     
     # Show the transcription
     st.text_area("Transcription", transcription, height=300)
@@ -68,3 +84,4 @@ if uploaded_video is not None:
     # Cleanup temporary files
     os.remove(tmp_video_path)
     os.remove(audio_file)
+    os.remove(wav_audio_file)