Update README.md

README.md

@@ -34,17 +34,18 @@ The model is fine-tuned on the [VoxCeleb1 dataset](https://www.robots.ox.ac.uk/~
 # Usage
 ## Speaker Verification
 ```python
-from transformers import Wav2Vec2FeatureExtractor, UniSpeechSatForXVector
+from transformers import Wav2Vec2FeatureExtractor, WavLMForXVector
 from datasets import load_dataset
 import torch
 
 dataset = load_dataset("hf-internal-testing/librispeech_asr_demo", "clean", split="validation")
 
 feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained('microsoft/wavlm-base-plus-sv')
-model = UniSpeechSatForXVector.from_pretrained('microsoft/wavlm-base-plus-sv')
+model = WavLMForXVector.from_pretrained('microsoft/wavlm-base-plus-sv')
 
 # audio files are decoded on the fly
-inputs = feature_extractor(dataset[:2]["audio"]["array"], return_tensors="pt")
+audio = [x["array"] for x in dataset[:2]["audio"]]
+inputs = feature_extractor(audio, padding=True, return_tensors="pt")
 embeddings = model(**inputs).embeddings
 embeddings = torch.nn.functional.normalize(embeddings, dim=-1).cpu()