File size: 818 Bytes
4bad891 5cbdb9e e95ce5b 5cbdb9e d84fe22 5cbdb9e e8ff96d 7ea1125 95ce231 e8ff96d 95ce231 7ea1125 95ce231 81f21b6 e8ff96d 5cbdb9e d84fe22 5cbdb9e d84fe22 95ce231 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 |
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()
|