Update README.md

README.md

@@ -28,6 +28,7 @@ The only change from the existing ASR pipeline will be:
 
 ```diff
 import torch
+import torchaudio.functional as F
 -from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 +from transformers import Wav2Vec2ForCTC, Wav2Vec2ProcessorWithLM
 from datasets import load_dataset
@@ -36,11 +37,13 @@ ds = load_dataset("common_voice", "es", split="test", streaming=True)
 
 sample = next(iter(ds))
 
+resampled_audio = F.resample(torch.tensor(sample["audio"]["array"]), 48_000, 16_000).n
+
 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 = Wav2Vec2ProcessorWithLM.from_pretrained("patrickvonplaten/wav2vec2-large-xlsr-53-spanish-with-lm")
 
-input_values = processor(sample["audio"]["array"], return_tensors="pt").input_values
+input_values = processor(resampled_audio, return_tensors="pt").input_values
 
 with torch.no_grad():
     logits = model(input_values).logits