Update README.md

README.md

@@ -32,13 +32,16 @@ The model is fine-tuned on the [LibriMix dataset](https://github.com/JorisCos/Li
 from transformers import Wav2Vec2FeatureExtractor, UniSpeechSatForAudioFrameClassification
 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-sd')
 model = UniSpeechSatForAudioFrameClassification.from_pretrained('microsoft/wavlm-base-sd')
+
 # audio file is decoded on the fly
 inputs = feature_extractor(dataset[0]["audio"]["array"], return_tensors="pt")
 logits = model(**inputs).logits
 probabilities = torch.sigmoid(logits[0])
+
 # labels is a one-hot array of shape (num_frames, num_speakers)
 labels = (probabilities > 0.5).long()
 ```