o ´©iã@s*ddlZddlmZGdd„dejƒZdS)éNcs,eZdZdZ‡fdd„Z‡fdd„Z‡ZS)ÚMossFormerDecoderaÄA decoder layer that consists of ConvTranspose1d. Arguments --------- kernel_size : int Length of filters. in_channels : int Number of input channels. out_channels : int Number of output channels. Example --------- >>> x = torch.randn(2, 100, 1000) >>> decoder = Decoder(kernel_size=4, in_channels=100, out_channels=1) >>> h = decoder(x) >>> h.shape torch.Size([2, 1003]) cstt|ƒj|i|¤ŽdS)N)ÚsuperrÚ__init__)ÚselfÚargsÚkwargs©Ú __class__©ú_/home/ubuntu/.local/lib/python3.10/site-packages/funasr/models/mossformer/mossformer_decoder.pyrszMossFormerDecoder.__init__csr| ¡dvrtd |j¡ƒ‚tƒ | ¡dkr|nt |d¡¡}t |¡ ¡dkr2tj|dd}|St |¡}|S)aReturn the decoded output. Arguments --------- x : torch.Tensor Input tensor with dimensionality [B, N, L]. where, B = Batchsize, N = number of filters L = time points )ééz{} accept 3/4D tensor as inputr é)Údim) rÚ RuntimeErrorÚformatÚ__name__rÚforwardÚtorchÚ unsqueezeÚsqueeze)rÚxrr r rs $ ÿzMossFormerDecoder.forward)rÚ __module__Ú __qualname__Ú__doc__rrÚ __classcell__r r rr rs r)rÚtorch.nnÚnnÚConvTranspose1drr r r r Ús