diff --git a/README.md b/README.md
index 117abe2..429ada6 100644
--- a/README.md
+++ b/README.md
@@ -30,7 +30,7 @@ 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, Wav2Vec2Model
+ from transformers import Wav2Vec2Tokenizer, Wav2Vec2ForMaskedLM
  from datasets import load_dataset
  import soundfile as sf
  import torch