app.py

import os

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


transcriber = pipeline(task="automatic-speech-recognition", model="geokanaan/Whisper_Base_Lebanese_Arabizi")

HF_TOKEN = os.getenv('WRITE')
hf_writer = gr.HuggingFaceDatasetSaver(HF_TOKEN, "flagged_Audio_Lebanese")

def transcribe(stream, new_chunk):
    sr, y = new_chunk
    y = y.astype(np.float32)
    y /= np.max(np.abs(y))

    if stream is not None:
        stream = np.concatenate([stream, y])
    else:
        stream = y
    return stream, transcriber({"sampling_rate": sr, "raw": stream})["text"]  

demo = gr.Interface(
    transcribe,
    ["state", gr.Audio(sources=["microphone"], streaming=True)],
    ["state", "text"],
    live=True,
    title="UNDER MAINTENANCE",
    description="Realtime demo for Lebanese Arabizi speech recognition",
    allow_flagging='manual',  # Enable manual flagging
)

demo.launch()