Update app.py

app.py

@@ -18,39 +18,37 @@ def translate(text_input, audio_input, source_lang, target_lang, auto_detect):
     translated_text = None
     translated_audio = None
 
-    # If text is provided
+    # If text input is provided
     if text_input:
         inputs = processor(text=text_input, src_lang=src, return_tensors="pt").to(device)
-        
-        # Generate speech
+
+        # Generate translated speech
         speech = model.generate(**inputs, tgt_lang=target_lang)[0].cpu().numpy().squeeze()
+        translated_audio = (16000, speech)
 
-        # Generate text
+        # Generate translated text
         text_tokens = model.generate(**inputs, tgt_lang=target_lang, generate_speech=False)
-        translated_text = processor.decode(text_tokens[0].tolist()[0], skip_special_tokens=True)
-
-        translated_audio = (16000, speech)
+        translated_text = processor.decode(text_tokens[0].tolist(), skip_special_tokens=True)
 
-    # If audio is provided
+    # If audio input is provided
     elif audio_input:
         waveform, sr = torchaudio.load(audio_input)
         waveform = torchaudio.functional.resample(waveform, sr, 16000)
         inputs = processor(audios=waveform, src_lang=src, return_tensors="pt").to(device)
 
-        # Generate speech
+        # Generate translated speech
         speech = model.generate(**inputs, tgt_lang=target_lang)[0].cpu().numpy().squeeze()
+        translated_audio = (16000, speech)
 
-        # Generate text
+        # Generate translated text
         text_tokens = model.generate(**inputs, tgt_lang=target_lang, generate_speech=False)
-        translated_text = processor.decode(text_tokens[0].tolist()[0], skip_special_tokens=True)
-
-        translated_audio = (16000, speech)
+        translated_text = processor.decode(text_tokens[0].tolist(), skip_special_tokens=True)
 
     if translated_text or translated_audio:
         return translated_text or "", translated_audio
     return "No input provided.", None
 
-# Gradio UI
+# Gradio Interface
 iface = gr.Interface(
     fn=translate,
     inputs=[
@@ -67,6 +65,6 @@ iface = gr.Interface(
     title="iVoice Translate (Text + Speech)"
 ).queue()
 
-# Launch server
+# Launch app
 if __name__ == "__main__":
-        iface.launch(server_name="0.0.0.0", share=True, server_port=int(os.environ.get("PORT", 7860)))
+    iface.launch(server_name="0.0.0.0", share=True, server_port=int(os.environ.get("PORT", 7860)))