ass}.from_pretrained("{checkpoint}")

    >>> # audio file is decoded on the fly
    >>> inputs = feature_extractor(
    ...     [d["array"] for d in dataset[:2]["audio"]], sampling_rate=sampling_rate, return_tensors="pt", padding=True
    ... )
    >>> with torch.no_grad():
    ...     embeddings = model(**inputs).embeddings

    >>> embeddings = torch.nn.functional.normalize(embeddings, dim=-1).cpu()

    >>> # the resulting embeddings can be used for cosine similarity-based retrieval
    >>> cosine_sim = torch.nn.CosineSimilarity(dim=-1)
    >>> similarity = cosine_sim(embeddings[0], embeddings[1])
    >>> threshold = 0.7  # the optimal threshold is dataset-dependent
    >>> if similarity < threshold:
    ...     print("Speakers are not the same!")
    >>> round(similarity.item(), 2)
    {expected_output}
    ```
a‘