app.py

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

transcriber = pipeline("automatic-speech-recognition", model="jonatasgrosman/wav2vec2-large-xlsr-53-arabic")

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="S2T: Transcription automatique en live de l'arabe en text by Papa Séga", 
    description="Utilisez le microphone pour parler en arabe et la transcription démarre en quelques secondes"
)

    
demo.launch()