Construct an linear object.

Apply rotary embeddings to input tensors using the given frequency tensor. This function applies rotary embeddings to the given query

Apply rotary embeddings to input tensors using the given frequency tensor. This function applies rotary embeddings to the given query

Convert a list of lists of token ids into a list of strings by calling decode. Args: sequences (`Union[List[int], List[L

Return tuple with min_len by repeating element at idx_repeat.

根据数字系统类型返回创建相应的数字系统，默认为 mid NUMBERING_TYPES = ['low', 'mid', 'high']: 中文数字系统类型 low: '兆' = '亿' * '十' = $10^{9}$, '京' = '兆' * '十', et

Reset the positional encodings.

Compute attention context vector. Args: value (torch.Tensor): Transformed value, size (#batch, n_head, time2, d_k

Transform query, key and value. Args: query (torch.Tensor): Query tensor (#batch, time1, size). key (torch.Tensor): K

Predict the sample from the previous timestep by reversing the SDE. This function propagates the diffusion process from the learned m

Create mask for subsequent steps (size, size) with chunk size, this is for streaming encoder Args: size (int): size of mask

Apply optional mask for encoder. Args: xs (torch.Tensor): padded input, (B, L, D), L for max length mask (torch.Tensor): mask for

Basic pipeline that lowercases and collapses whitespace without transliteration.