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(audio):
    sr, y = audio
    
    # Convert to mono if stereo
    if y.ndim > 1:
        y = y.mean(axis=1)
        
    y = y.astype(np.float32)
    y /= np.max(np.abs(y))

    return transcriber({"sampling_rate": sr, "raw": y})["text"]  

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

demo.launch()