 from transformers import Wav2Vec2Processor, Wav2Vec2ForCTC
 from datasets import load_dataset
 import torch
 
 # load model and tokenizer
 processor = Wav2Vec2Processor.from_pretrained("Clementapa/wav2vec2-base-960h-phoneme-reco-dutch")
 model = Wav2Vec2ForCTC.from_pretrained("Clementapa/wav2vec2-base-960h-phoneme-reco-dutch")
     
 # load dummy dataset and read soundfiles
 ds = load_dataset("common_voice", "nl", split="validation")
 
 # tokenize
 input_values = processor(ds[0]["audio"]["array"], return_tensors="pt", padding="longest").input_values  # Batch size 1
 
 # retrieve logits
 logits = model(input_values).logits
 
 # take argmax and decode
 predicted_ids = torch.argmax(logits, dim=-1)
 transcription = processor.batch_decode(predicted_ids)