import torch
import torchaudio
from datasets import load_dataset
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
test_dataset = load_dataset("common_voice", "lt", split="test[:2%]") 
processor = Wav2Vec2Processor.from_pretrained("seccily/wav2vec-lt-lite")
model = Wav2Vec2ForCTC.from_pretrained("seccily/wav2vec-lt-lite")
resampler = torchaudio.transforms.Resample(48_000, 16_000)

Test Result: 59.47