Update app.py

app.py

@@ -240,8 +240,12 @@ def infer_batch(ref_audio, ref_text, gen_text_batches, exp_name, remove_silence,
         generated_wave = generated_wave.squeeze().cpu().numpy()
         
         generated_waves.append(generated_wave)
-        spectrograms.append(generated_mel_spec[0].cpu().numpy())
+ #       spectrograms.append(generated_mel_spec[0].cpu().numpy())
+# Ensure generated_mel_spec is in a compatible dtype (e.g., float32) before passing it to numpy
+        generated_mel_spec = generated_mel_spec.to(dtype=torch.float32)  # Convert to float32 if it's in bfloat16
 
+# Proceed with the rest of your operations
+        spectrograms.append(generated_mel_spec[0].cpu().numpy())
     # Combine all generated waves with cross-fading
     if cross_fade_duration <= 0:
         # Simply concatenate