Update app.py

app.py

@@ -1,9 +1,12 @@
 import gradio as gr
 import whisper
+import numpy as np
 
 model = whisper.load_model("base")
 
 def transcribe(audio):
+    if not isinstance(audio, np.ndarray):
+        audio = np.array(audio)
     audio = whisper.pad_or_trim(audio)
     mel = whisper.log_mel_spectrogram(audio).to(model.device)
     options = whisper.DecodingOptions()
@@ -12,4 +15,3 @@ def transcribe(audio):
 
 iface = gr.Interface(fn=transcribe, inputs="audio", outputs="text")
 iface.launch()
-