Optimizing graphics card memory

During inference it does not store gradients, which take up most of the video memory

tortoise/api.py

@@ -225,6 +225,7 @@ class TextToSpeech:
         properties.
         :param voice_samples: List of 2 or more ~10 second reference clips, which should be torch tensors containing 22.05kHz waveform data.
         """
+        with torch.no_grad():
             voice_samples = [v.to('cuda') for v in voice_samples]
 
             auto_conds = []