Wav2Vec2Pretrain (HFTransformersInterface implementation) samples padded values for mask_time_indices and negative_sample_indices about speechbrain HOT 3 OPEN

   padding_mask = make_padding_masks(wav, wav_len=wav_lens)
   features_padding_mask = self.model._get_feature_vector_attention_mask(
            sequence_length, padding_mask, add_adapter=False
        )

    # 1. Compute the indices that will be masked
    mask_time_indices = _compute_mask_indices(
        (batch_size, sequence_length),
        mask_prob=self.mask_prob,
        mask_length=self.mask_length,
        attention_mask=features_padding_mask

    )
    torch_mask_time_indices = torch.tensor(
        mask_time_indices, device=wav.device, dtype=torch.long,
    )

    # 2. Sample the negative samples from the entire sequence.
    # Fairseq does it only on the masked indices, but this only work if you
    # have long sentences. For more versatily, we sample on the entire sequence.
    # value.
    full_sentence_indices = np.ones((batch_size, sequence_length))

    negative_sample_indices = torch.tensor(
        transformers.models.wav2vec2.modeling_wav2vec2._sample_negative_indices(
            (batch_size, sequence_length),
            num_negatives=self.config.num_negatives,
            # mask_time_indices=full_sentence_indices,
            mask_time_indices=features_padding_mask.detach().cpu().numpy()

        ),
        device=wav.device,
        dtype=torch.long,
    )