Update app.py

app.py

@@ -27,7 +27,7 @@ def predict(speech_array, sampling_rate):
         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)]
+    outputs = [{config.id2label[i]: f"{round(score * 100, 3):.1f}%"} for i, score in enumerate(scores)]
     return outputs
  
 
@@ -43,7 +43,7 @@ device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
 def transcribe(audio):
     sr, audio = audio[0], audio[1]
-    return predict(audio, sr)
+    return predict(audio, sr)[0]
 
 
 def get_asr_interface():
@@ -53,7 +53,7 @@ def get_asr_interface():
             gr.inputs.Audio(source="upload", type="numpy")
         ],
         outputs=[
-            "textbox"
+            "json"
         ])
         
 interfaces = [