eustlb

from datasets import load_dataset, Audio
from transformers import VoxtralForConditionalGeneration, VoxtralProcessor
import os
import torch
from whisper.normalizers import EnglishTextNormalizer
import jiwer

os.environ["CUDA_VISIBLE_DEVICES"] = "0"
torch_device = "cuda" if torch.cuda.is_available() else "cpu" # "cpu"