Update app.py

app.py

@@ -3,6 +3,7 @@ import torch
 import numpy as np
 import librosa
 from torchmetrics.functional.audio.nisqa import non_intrusive_speech_quality_assessment as tm_nisqa
+import spaces
 
 SR = 16000
 
@@ -29,6 +30,7 @@ def explain_dim(name: str):
         "Loudness": "Perceived loudness appropriateness (higher = more appropriate)."
     }[name]
 
+@spaces.GPU()
 def predict_nisqa(audio):
     if isinstance(audio, tuple):
         _sr, y = audio
@@ -36,8 +38,11 @@ def predict_nisqa(audio):
     else:
         y, _ = librosa.load(audio, sr=SR, mono=True)
 
-    wav = torch.tensor(y, dtype=torch.float32)
-    mos, noisiness, discontinuity, coloration, loudness = tm_nisqa(wav, SR).detach().cpu().numpy().tolist()
+    device = "cuda" if torch.cuda.is_available() else "cpu"
+    wav = torch.tensor(y, dtype=torch.float32, device=device)
+        mos, noisiness, discontinuity, coloration, loudness = (
+        tm_nisqa(wav, SR).detach().to("cpu").numpy().tolist()
+    )
 
     metrics = [
         ("MOS (overall)", mos, label_mos(mos), "Higher = better perceived quality."),