Update README.md

README.md

@@ -73,19 +73,19 @@ For more information, please take a look at the [official paper](https://arxiv.o
 To transcribe audio files the model can be used as a standalone acoustic model as follows:
 
 ```python
- from transformers import Wav2Vec2Processor, Data2VecForCTC
+ from transformers import Wav2Vec2Processor, Data2VecAudioForCTC
  from datasets import load_dataset
  import torch
  
  # load model and processor
  processor = Wav2Vec2Processor.from_pretrained("facebook/data2vec-audio-base-960h")
- model = Data2VecForCTC.from_pretrained("facebook/data2vec-audio-base-960h")
+ model = Data2VecAudioForCTC.from_pretrained("facebook/data2vec-audio-base-960h")
      
  # load dummy dataset and read soundfiles
  ds = load_dataset("patrickvonplaten/librispeech_asr_dummy", "clean", split="validation")
  
  # tokenize
- input_values = processor(ds[0]["audio"]["array"],, return_tensors="pt", padding="longest").input_values  # Batch size 1
+ input_values = processor(ds[0]["audio"]["array"], return_tensors="pt", padding="longest").input_values  # Batch size 1
  
  # retrieve logits
  logits = model(input_values).logits
@@ -100,14 +100,14 @@ To transcribe audio files the model can be used as a standalone acoustic model a
  This code snippet shows how to evaluate **facebook/data2vec-audio-base-960h** on LibriSpeech's "clean" and "other" test data.
  
 ```python
- from transformers import Wav2Vec2Processor, Data2VecForCTC
+ from transformers import Wav2Vec2Processor, Data2VecAudioForCTC
  from datasets import load_dataset
  import torch
  from jiwer import wer
  
  # load model and processor
  processor = Wav2Vec2Processor.from_pretrained("facebook/data2vec-audio-base-960h").to("cuda")
- model = Data2VecForCTC.from_pretrained("facebook/data2vec-audio-base-960h")
+ model = Data2VecAudioForCTC.from_pretrained("facebook/data2vec-audio-base-960h")
  
 
 librispeech_eval = load_dataset("librispeech_asr", "clean", split="test")