Update app.py

app.py

@@ -145,40 +145,20 @@ def magnitude_to_complex_spectrogram(magnitude_spectrogram):
 
 def spectrogram_to_audio(magnitude_spectrogram):
     # Perform inverse log scaling
-    try:
-        magnitude_spectrogram = torch.expm1(magnitude_spectrogram)
-        if torch.isnan(magnitude_spectrogram).any():
-            raise ValueError("NaN values found in magnitude_spectrogram after expm1.")
-    except Exception as e:
-        raise ValueError(f"Error in expm1 operation: {e}")
+    magnitude_spectrogram = torch.expm1(magnitude_spectrogram)
 
     # Convert magnitude-only spectrogram to complex format
-    try:
-        complex_spectrogram = magnitude_to_complex_spectrogram(magnitude_spectrogram)
-        if torch.isnan(complex_spectrogram).any():
-            raise ValueError("Complex spectrogram contains NaN values after conversion.")
-    except Exception as e:
-        raise ValueError(f"Error in complex spectrogram creation: {e}")
+    complex_spectrogram = magnitude_to_complex_spectrogram(magnitude_spectrogram)
 
     # Inverse STFT to convert the spectrogram back to audio
-    try:
-        audio = torch.istft(complex_spectrogram, n_fft=n_fft, hop_length=hop_length)
-        if torch.isnan(audio).any():
-            raise ValueError("Generated audio contains NaN values after istft.")
-    except Exception as e:
-        raise ValueError(f"Error in istft operation: {e}")
-
-    # Normalize audio to the range [-1, 1] (standard audio range)
-    try:
-        if torch.max(torch.abs(audio)) != 0:
-            audio = audio / torch.max(torch.abs(audio))
-    except Exception as e:
-        raise ValueError(f"Error in audio normalization: {e}")
-
-    # Clip the audio to ensure it fits in the range [-1, 1]
+    audio = torch.istft(complex_spectrogram, n_fft=n_fft, hop_length=hop_length)
+
+    # Normalize and clip the audio
+    if torch.max(torch.abs(audio)) != 0:
+        audio = audio / torch.max(torch.abs(audio))
     audio = torch.clamp(audio, min=-1, max=1)
 
-    # Convert to 16-bit PCM format by scaling and casting to int16
+    # Convert to 16-bit PCM format
     audio = (audio * 32767).short()
 
     return audio