app.py

import gradio as gr
from transformers import pipeline
import numpy as np

transcriber = pipeline("automatic-speech-recognition", model="filipzawadka/whisper-small-pl-2")
#transcriber = pipeline("automatic-speech-recognition", model="openai/whisper-small.en")


def transcribe(audio):
    print(audio)
    return transcriber("./common_voice_pl_38051254.mp3")["text"]


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

demo.launch()