app.py

#                                                                                                                 
# speech recognition                                                                                              
#                                                                                                                 
import numpy as np
import gradio as gr
from transformers import pipeline

asr = pipeline("automatic-speech-recognition", model="openai/whisper-base")

def transcribe(audio):
    english = asr(audio)
    return english['text']

demo = gr.Interface(fn = transcribe,
                    inputs=gr.Audio(type="filepath"),
                    outputs = "text",
                    title = "Whisper Speech Recognition")

demo.launch()