test

app.py

@@ -5,11 +5,8 @@ import numpy as np
 transcriber = pipeline("automatic-speech-recognition", model="filipzawadka/whisper-small-pl-2")
 
 def transcribe(audio):
-    sr, y = audio
-    y = y.astype(np.float32)
-    y /= np.max(np.abs(y))
-
-    return transcriber({"sampling_rate": sr, "raw": y})["text"]
+    print(audio)
+    return transcriber(audio)["text"]
 
 
 demo = gr.Interface(