@j,ddlmZmZddlmZmZmZddlZddlm Z gdZ Gddej j Z Gdd ej j ZGd d eZGd d ej j eZGddej j ZGddej j ZGddej j Zdedededededededededededed ed!ed"ed#ed$ed%ed&ed'ed(ed)ef,d*Zded)efd+ZdS),)ABCabstractmethod)ListOptionalTupleN)Emformer)RNNTemformer_rnnt_baseemformer_rnnt_modelcxeZdZdZdeddffd ZdejdejdeejejffdZ xZ S) _TimeReductionzCoalesces frames along time dimension into a fewer number of frames with higher feature dimensionality. Args: stride (int): number of frames to merge for each output frame. stridereturnNcVt||_dSN)super__init__r)selfr __class__s GC:\Projects\Historical\venv\Lib\site-packages\torchaudio/models/rnnt.pyrz_TimeReduction.__init__s$  inputlengthsc|j\}}}|||jzz }|ddd|ddf}||jd}||jz}|||||jz}|}||fS)aForward pass. B: batch size; T: maximum input sequence length in batch; D: feature dimension of each input sequence frame. Args: input (torch.Tensor): input sequences, with shape `(B, T, D)`. lengths (torch.Tensor): with shape `(B,)` and i-th element representing number of valid frames for i-th batch element in ``input``. Returns: (torch.Tensor, torch.Tensor): torch.Tensor output sequences, with shape `(B, T // stride, D * stride)` torch.Tensor output lengths, with shape `(B,)` and i-th element representing number of valid frames for i-th batch element in output sequences. Ntrunc) rounding_mode)shaperdivreshape contiguous) rrrBTD num_framesT_maxoutputs rforwardz_TimeReduction.forwards*+1a!dk/* aaa*aaa'(++dk+AAdk)q%T[99""$$wr) __name__ __module__ __qualname____doc__intrtorchTensorrr' __classcell__rs@rr r sstU\ELU5