ejemplo con ajuste 2

app.py

@@ -1,4 +1,12 @@
-gr.Interface(
+from transformers import pipeline
+import gradio as gr
+
+modelo = pipeline("automatic-speech-recognition", model="facebook/wav2vec2-large-xlsr-53-spanish")
+
+def transcribe(audio):
+  text = modelo(audio)["text"]
+  return text
+    gr.Interface(
     fn=transcribe,
     inputs=gr.Audio(type="filepath"),
     outputs=["textbox"]