Update app.py

app.py

@@ -19,8 +19,7 @@ class Speech2Text:
 
     def feature2logits(self, features):
         with torch.no_grad():
-            return wav2vec_model(features.input_values.to(device),
-                                 attention_mask=features.attention_mask.to(device)).logits.numpy()[0]
+            return wav2vec_model(features.input_values[0].to(device)).logits.numpy()[0]
 
     def __call__(self, path):
         logits = self.feature2logits(self.wav2feature(path))
@@ -34,6 +33,7 @@ processor = Wav2Vec2Processor.from_pretrained(model_name)
 s2t = Speech2Text()
 
 def asr(path):
+    print(path)
     return s2t(path)
     
 # themes="default", "huggingface", "seafoam", "grass", "peach"