.

app.py

@@ -15,15 +15,15 @@ def speech_to_text(tmp_filename, model_size):
 
     # detect the spoken language
     _, probs = model.detect_language(mel)
-    print(f"Detected language: {max(probs, key=probs.get)}")
+    #print(f"Detected language: {max(probs, key=probs.get)}")
 
     # decode the audio
     options = whisper.DecodingOptions()
     result = whisper.decode(model, mel, options)
 
     # print the recognized text
-    print(result.text)
-    return f"Detected language: {max(probs, key=probs.get)}", result.text
+    #print(result.text)
+    return result.text
 
 
 gr.Interface(
@@ -39,5 +39,5 @@ gr.Interface(
     inputs=[
         gr.Audio(label="Record your voice on your mic",source="microphone", type="filepath"),
         gr.Dropdown(label="Select model size",value="base",choices=["tiny", "base", "small", "medium", "large"])],
-    outputs=["text","text"]).launch()
+    outputs="text").launch()