Update app.py

app.py

@@ -2,6 +2,7 @@ from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 from elevenlabs import set_api_key
 from elevenlabs import clone, generate, play
 from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
+from pydub import AudioSegment
 from huggingface_hub.hf_api import HfFolder
 HfFolder.save_token('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')
 access_token = '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'
@@ -22,9 +23,9 @@ def translate(text):
     return result 
 
 
-def save_uploaded_file(uploaded_file, output_file_path):
-    with open(output_file_path, "wb") as f:
-        f.write(uploaded_file.getbuffer())
+def save_uploaded_file_as_mp3(uploaded_file, output_file_path):
+    audio = AudioSegment.from_file(uploaded_file)
+    audio.export(output_file_path, format="mp3")
 
 def ui(): 
     st.title('Multi Lingual Voice Cloner')
@@ -34,7 +35,7 @@ def ui():
     audio_file = st.file_uploader("Upload an audio file that needs to be cloned", type=[ "wav,Mp4","Mp3"])
     if audio_file is not None:
         output_file_path = "./output_audio.mp3"
-        save_uploaded_file(audio_file, output_file_path)
+        save_uploaded_file_as_mp3(audio_file, output_file_path)
         st.success(f"Audio file saved as {output_file_path}")
         user_api_key = st.sidebar.text_input(
             label="#### Your Eleven Labs API key here 👇",