hՊ,DSSKJrJr SSKJrJrJr SSKrSSKJ r /SQr "SS\RR5r "SS \RR5r"S S \5r"S S \RR\5r"SS\RR5r"SS\RR5r"SS\RR5rS\S\S\S\S\S\S\S\S\S\S\S\S \S!\S"\S#\S$\S%\S&\S'\S(\S)\4,S*jrS\S)\4S+jrg),)ABCabstractmethod)ListOptionalTupleN)Emformer)RNNTemformer_rnnt_baseemformer_rnnt_modelc^\rSrSrSrS\SS4U4SjjrS\RS\RS\ \R\R44S jr S r U=r $) _TimeReduction zCoalesces frames along time dimension into a fewer number of frames with higher feature dimensionality. Args: stride (int): number of frames to merge for each output frame. stridereturnNc.>[TU]5 XlgN)super__init__r)selfr __class__s N/var/www/auris/envauris/lib/python3.13/site-packages/torchaudio/models/rnnt.pyr_TimeReduction.__init__s  inputlengthscURup4nXDUR-- nUSS2SU2SS24nURURSS9nX`R-nURX7XPR-5nUR 5nX4$)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 rforward_TimeReduction.forwards*++adkk/* a*a'(++dkk+Akk)q[[9""$r)r) __name__ __module__ __qualname____firstlineno____doc__intrtorchTensorrr)__static_attributes__ __classcell__rs@rr r sWstU\\ELLU5<