Update app.py

app.py

@@ -64,7 +64,10 @@ def detect_on_gpu(audio_path):
     with torch.no_grad():
         for batch_idx, batch in enumerate(audio_dataset):
             print(f"\n处理批次 {batch_idx + 1}")
-            print('waveforms shape:', batch['waveforms'].shape)
+            if len(batch['waveforms'].shape) == 1:
+                batch['waveforms'] = batch['waveforms'].unsqueeze(0)
+
+            print('shape:', batch['waveforms'].shape)
             waveforms = batch['waveforms'].numpy() # [B, T]
             features = feature_extractor(waveforms, sampling_rate=16000, return_attention_mask=True, padding_value=0, return_tensors="pt").to(device)
             outputs = model(features)