from transformers import pipeline
import gradio as gr
import time

pipe = pipeline("automatic-speech-recognition", model="Artanis1551/whisper_romanian3")


def transcribe(audio, state=""):
    text = pipe(audio)["text"]

    print(text)
    state += text + " "
    return state, state


gr.Interface(
    title="Romanian Speech Transcription",
    fn=transcribe,
    inputs=[gr.Audio(source="microphone", type="filepath", streaming=True), "state"],
    outputs=["textbox", "state"],
    live=True,
).launch()