Update app.py

app.py

@@ -35,16 +35,16 @@ def inference(text):
       lengths = lengths.to(device)
       spec, _, _ = tacotron2.infer(processed, lengths)
 
-
+  plt.imshow(spec[0].cpu().detach())
 
   with torch.no_grad():
       waveforms = waveglow.infer(spec)
 
   torchaudio.save("output_waveglow.wav", waveforms[0:1].cpu(), sample_rate=22050)
-  return "output_waveglow.wav",spec[0].cpu().detach().numpy()
+  return "output_waveglow.wav",plt
   
 title="TACOTRON 2"
 description="Gradio demo for TACOTRON 2: The Tacotron 2 model for generating mel spectrograms from text. To use it, simply add you text or click on one of the examples to load them. Read more at the links below."
 article = "<p style='text-align: center'><a href='https://arxiv.org/abs/1712.05884' target='_blank'>Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions</a> | <a href='https://github.com/NVIDIA/DeepLearningExamples/tree/master/PyTorch/SpeechSynthesis/Tacotron2' target='_blank'>Github Repo</a></p>"
 examples=[["life is like a box of chocolates"]]
-gr.Interface(inference,"text",[gr.outputs.Audio(type="file"),gr.outputs.Image(type="numpy",label="Spectrogram")],title=title,description=description,article=article,examples=examples).launch(enable_queue=True)
+gr.Interface(inference,"text",[gr.outputs.Audio(type="file"),gr.outputs.Image(type="plot",label="Spectrogram")],title=title,description=description,article=article,examples=examples).launch(enable_queue=True)