update

README.md

@@ -59,10 +59,10 @@ from meldataset import get_mel_spectrogram
 
 # load wav file and compute mel spectrogram
 wav, sr = librosa.load('/path/to/your/audio.wav', sr=model.h.sampling_rate, mono=True) # wav is np.ndarray with shape [T_time] and values in [-1, 1]
-wav = torch.FloatTensor(wav).to(device).unsqueeze(0) # wav is FloatTensor with shape [B(1), T_time]
+wav = torch.FloatTensor(wav).unsqueeze(0) # wav is FloatTensor with shape [B(1), T_time]
 
 # compute mel spectrogram from the ground truth audio
-mel = get_mel_spectrogram(wav, model.h) # mel is FloatTensor with shape [B(1), C_mel, T_frame]
+mel = get_mel_spectrogram(wav, model.h).to(device) # mel is FloatTensor with shape [B(1), C_mel, T_frame]
 
 # generate waveform from mel
 with torch.inference_mode():