Update app.py

app.py

@@ -2,7 +2,7 @@ import gradio as gr
 import whisper
 from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 from gtts import gTTS
-import sounddevice as sd
+import soundfile as sf
 import scipy.io.wavfile as wav
 import os
 
@@ -36,18 +36,19 @@ def translate_speech_to_speech(input_audio):
     
     # Text-to-speech (TTS) code from the first code snippet
     tts = gTTS(text=translated_text, lang=to_lang)
-    output_file = "translated_speech.mp3"
+    output_file = "translated_speech.wav"
     tts.save(output_file)
     
     # Load the translated audio and return as an output
-    translated_audio = open(output_file, "rb")
+    translated_audio, sr = sf.read(output_file, dtype="float32")
+    translated_audio = (translated_audio * 32767).astype("int16")
     
-    return translated_audio
+    return translated_audio, sr
 
 title = "Speech-to-Speech Translator"
 
 input_audio = gr.inputs.Audio(type=["mp3", "wav"])
-output_audio = gr.outputs.Audio(type=["mp3", "wav"])
+output_audio = gr.outputs.Audio(type=["mp3", "wav"], sample_rate=44100)
 
 stt_demo = gr.Interface(
     fn=translate_speech_to_speech,
@@ -61,3 +62,4 @@ if __name__ == "__main__":
     stt_demo.launch()
 
 
+