Update app.py

app.py

@@ -1,6 +1,7 @@
 
 from transformers import VitsModel, AutoTokenizer
 import torch
+import sounddevice as sd  # Example: using sounddevice for audio playback
 
 model = VitsModel.from_pretrained("facebook/mms-tts-eng")
 tokenizer = AutoTokenizer.from_pretrained("facebook/mms-tts-eng")
@@ -8,5 +9,9 @@ tokenizer = AutoTokenizer.from_pretrained("facebook/mms-tts-eng")
 text = "some example text in the English language"
 inputs = tokenizer(text, return_tensors="pt")
 
-with torch.no_grad():
+with torch.no_grad():  # Optionally remove if not needed
     output = model(**inputs).waveform
+
+# Play the generated audio
+sd.play(output.numpy(), samplerate=model.config.audio_config.sampling_rate)  
+sd.wait()  # Wait for playback to finish