Update app.py

app.py

@@ -8,16 +8,17 @@ from huggingface_hub import login
 warnings.filterwarnings("ignore")
 
 
-# Load tokenizer and model
+# tokenizer, model
 tokenizer = WhisperTokenizer.from_pretrained("NbAiLabBeta/nb-whisper-medium")
 model = WhisperForConditionalGeneration.from_pretrained("NbAiLabBeta/nb-whisper-medium")
 processor = WhisperProcessor.from_pretrained("NbAiLabBeta/nb-whisper-medium")
 
-# Set up the device
-device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+# Set up device
+device = ('cuda')
+# device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
 torch_dtype = torch.float32
+model.to(device)
 
-@spaces.GPU
 def transcribe_audio(audio_file):
     audio_input, _ = sf.read(audio_file)
     inputs = processor(audio_input, sampling_rate=16000, return_tensors="pt")