app.py

from transformers import pipeline
import gradio as gr
import time

pipe = pipeline(
    model="dvislobokov/whisper-large-v3-turbo-russian",
    tokenizer="dvislobokov/whisper-large-v3-turbo-russian",
    task='automatic-speech-recognition',
    device='cpu'
)

def transcribe(audio):
    start = time.time()
    text = pipe(audio, return_timestamps=True)['text']
    spent_time = (time.time() - start)
    return f'Spent time: {spent_time}\nText: {text}'

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

iface.launch(share=True)