Updated app.py

app.py

@@ -2,7 +2,9 @@ import gradio as gr
 from transformers import pipeline
 import numpy as np
 
-transcriber = pipeline("automatic-speech-recognition", model="openai/whisper-base.en")
+model = "openai/whisper-base.en"
+
+pipe = pipeline("automatic-speech-recognition", model=model)
 
 def transcribe(audio):
     sr, y = audio
@@ -14,7 +16,7 @@ def transcribe(audio):
     y = y.astype(np.float32)
     y /= np.max(np.abs(y))
 
-    return transcriber({"sampling_rate": sr, "raw": y})["text"]  
+    return pipe({"sampling_rate": sr, "raw": y})["text"]  
 
 demo = gr.Interface(
     transcribe,

requirements.txt

@@ -1,3 +1,4 @@
 transformers
 torch
+torchaudio
 numpy