Update README.md

README.md

@@ -31,14 +31,14 @@ 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, Wav2Vec2ForMaskedLM
+ from transformers import Wav2Vec2Tokenizer, Wav2Vec2ForCTC
  from datasets import load_dataset
  import soundfile as sf
  import torch
  
  # load model and tokenizer
  tokenizer = Wav2Vec2Tokenizer.from_pretrained("facebook/wav2vec2-large-960h")
- model = Wav2Vec2ForMaskedLM.from_pretrained("facebook/wav2vec2-large-960h")
+ model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-large-960h")
  
  # define function to read in sound file
  def map_to_array(batch):
@@ -67,7 +67,7 @@ This code snippet shows how to evaluate **facebook/wav2vec2-large-960h** on Libr
  
 ```python
 from datasets import load_dataset
-from transformers import Wav2Vec2ForMaskedLM, Wav2Vec2Tokenizer
+from transformers import Wav2Vec2ForCTC, Wav2Vec2Tokenizer
 import soundfile as sf
 import torch
 from jiwer import wer
@@ -75,7 +75,7 @@ from jiwer import wer
 
 librispeech_eval = load_dataset("librispeech_asr", "clean", split="test")
 
-model = Wav2Vec2ForMaskedLM.from_pretrained("facebook/wav2vec2-large-960h").to("cuda")
+model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-large-960h").to("cuda")
 tokenizer = Wav2Vec2Tokenizer.from_pretrained("facebook/wav2vec2-base-960h")
 
 def map_to_array(batch):