Update app.py

app.py

@@ -24,7 +24,7 @@ def predict(speech_array, sampling_rate):
     inputs = {key: inputs[key].to(device) for key in inputs}
 
     with torch.no_grad():
-        logits = model_(**inputs).logits
+        logits = model.to(device)(**inputs).logits
 
     scores = F.softmax(logits, dim=1).detach().cpu().numpy()[0]
     outputs = [{"Emotion": config.id2label[i], "Score": f"{round(score * 100, 3):.1f}%"} for i, score in enumerate(scores)]
@@ -39,7 +39,6 @@ model = AutoModel.from_pretrained("Aniemore/wav2vec2-xlsr-53-russian-emotion-rec
 feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained("Aniemore/wav2vec2-xlsr-53-russian-emotion-recognition")
 
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-model.to(device)
 
 
 def transcribe(audio):