nsors="pt").input_values  # Batch size 1

        >>> # compute masked indices
        >>> batch_size, raw_sequence_length = input_values.shape
        >>> sequence_length = model._get_feat_extract_output_lengths(raw_sequence_length).item()
        >>> mask_time_indices = _compute_mask_indices(
        ...     shape=(batch_size, sequence_length), mask_prob=0.2, mask_length=2
        ... )
        >>> sampled_negative_indices = _sample_negative_indices(
        ...     features_shape=(batch_size, sequence_length),
        ...     num_negatives=model.config.num_negatives,
        ...     mask_time_indices=mask_time_indices,
        ... )
        >>> mask_time_indices = torch.tensor(data=mask_time_indices, device=input_values.device, dtype=torch.long)
        >>> sampled_negative_indices = torch.tensor(
        ...     data=sampled_negative_indices, device=input_values.device, dtype=torch.long
        ... )

        >>> with torch.no_grad():
        ...     outputs = model(input_values, mask_time_indices=mask_time_indices)

        >>> # compute cosine similarity between predicted (=projected_states) and target (=projected_quantized_states)
        >>> cosine_sim = torch.cosine_similarity(outputs.projected_states, outputs.projected_quantized_states, dim=-1)

        >>> # show that cosine similarity is much higher than random
        >>> cosine_sim[mask_time_indices.to(torch.bool)].mean() > 0.5
        tensor(True)

        >>> # for contrastive loss training model should be put into train mode
        >>> model = model.train()
        >>> loss = model(
        ...     input_values, mask_time_indices=mask_time_indices, sampled_negative_indices=sampled_negative_indices
        ... ).loss
        ```N)