Update README.md

README.md

@@ -27,7 +27,8 @@ In a nutshell: This PR adds a new Wav2Vec2WithLMProcessor class as drop-in repla
 The only change from the existing ASR pipeline will be:
 
 ```diff
-from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
+-from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
++from transformers import Wav2Vec2ForCTC, Wav2Vec2ProcessorWithLM
 from datasets import load_dataset
 
 ds = load_dataset("common_voice", "es", split="test", streaming=True)
@@ -35,14 +36,16 @@ ds = load_dataset("common_voice", "es", split="test", streaming=True)
 sample = next(iter(ds))
 
 model = Wav2Vec2ForCTC.from_pretrained("patrickvonplaten/wav2vec2-large-xlsr-53-spanish-with-lm")
-processor = Wav2Vec2Processor.from_pretrained("patrickvonplaten/wav2vec2-large-xlsr-53-spanish-with-lm")
+-processor = Wav2Vec2Processor.from_pretrained("patrickvonplaten/wav2vec2-large-xlsr-53-spanish-with-lm")
++processor = Wav2Vec2ProcessorWithLM.from_pretrained("patrickvonplaten/wav2vec2-large-xlsr-53-spanish-with-lm")
 
 input_values = processor(sample["audio"]["array"], return_tensors="pt").input_values
 
 logits = model(input_values).logits
-prediction_ids = torch.argmax(logits, dim=-1)
 
-transcription = processor.batch_decode(prediction_ids)
+-prediction_ids = torch.argmax(logits, dim=-1)
+-transcription = processor.batch_decode(prediction_ids)
++transcription = processor.batch_decode(logits)
 
 print(transcription)
 ```