diff --git a/README.md b/README.md
index e6e9af0..c0a24e1 100644
--- a/README.md
+++ b/README.md
@@ -36,13 +36,13 @@ The original model can be found under https://github.com/pytorch/fairseq/tree/ma
 To transcribe audio files the model can be used as a standalone acoustic model as follows:
 
 ```python
- from transformers import Wav2Vec2Tokenizer, Wav2Vec2ForCTC
+ from transformers import Wav2Vec2CTCTokenizer, Wav2Vec2ForCTC
  from datasets import load_dataset
  import soundfile as sf
  import torch
  
  # load model and tokenizer
- tokenizer = Wav2Vec2Tokenizer.from_pretrained("facebook/wav2vec2-base-960h")
+ tokenizer = Wav2Vec2CTCTokenizer.from_pretrained("facebook/wav2vec2-base-960h")
  model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-960h")
  
  # define function to read in sound file
@@ -81,7 +81,7 @@ from jiwer import wer
 librispeech_eval = load_dataset("librispeech_asr", "clean", split="test")
 
 model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-960h").to("cuda")
-tokenizer = Wav2Vec2Tokenizer.from_pretrained("facebook/wav2vec2-base-960h")
+tokenizer = Wav2Vec2CTCTokenizer.from_pretrained("facebook/wav2vec2-base-960h")
 
 def map_to_array(batch):
     speech, _ = sf.read(batch["file"])