app.py

import gradio as gr
from transformers import pipeline

pipe = pipeline("automatic-speech-recognition", model="SpideyDLK/wav2vec2-large-xls-r-300m-sinhala-aug-data-with-original-split-part3")

def transcribe(audio):
    return pipe(audio)["text"]

gr.Interface(fn=transcribe,
             inputs=gr.Audio(sources=["microphone", "upload"], type="filepath"),
             outputs="text").launch()