Update app.py

app.py

@@ -35,8 +35,8 @@ def transcribe_with_diarization(audio_path):
         print(waveform)
         interval_audio = waveform[:,start_sample:end_sample]
             # Export the interval audio as a temporary WAV file
-        torchaudio.save("interval_audio.wav", interval_audio,sample_rate)
-        transcript = asr_pipe("interval_audio.wav")
+        torchaudio.save("interval_audio.mp3", interval_audio,sample_rate)
+        transcript = asr_pipe("interval_audio.mp3")
         print(transcript)        
         start_time = segment.start
         end_time = segment.end
@@ -53,7 +53,7 @@ iface = gr.Interface(
     fn=transcribe_with_diarization,
     inputs=[
         gr.File(label="Audio File"),
-        gr.Audio(source="microphone", type="filepath", filetype="wav")
+        gr.Audio(source="microphone", type="filepath")
     ],
     outputs="text",
     title="Whisper small Hindi with Speaker Diarization",