o rq i @sddlZddlZddlmZddlmmZGdddejZ Gddde Z de de de d e fd d Z Gd d d ejZ Gddde ZGdddejjZdS)NcsVeZdZ         dfdd Zd d Zd ed ed efddZddZZS)Conv1d_ONsameTreflectFc st||_||_||_||_| |_d|_| |_|dur&|dur&t d|dur/| |}t j |||j|j|jd|| d|_ dS)NFz.Must provide one of input_shape or in_channelsr)stridedilationpaddinggroupsbias)super__init__ kernel_sizerrr padding_mode unsqueezeskip_transpose ValueError_check_input_shapennConv1dconv) self out_channelsr input_shape in_channelsrrrr r rr __class__f/home/app/PaddleOCR-VL/.venv_paddleocr/lib/python3.10/site-packages/modelscope/models/audio/sv/TDNN.pyr s,   zConv1d_O.__init__cCs|js |dd}|jr|d}|jdkr"|||j|j|j}n#|jdkr8|jd|j}t ||df}n |jdkr>nt d|j| |}|jrR| d}|js[|dd}|S)zReturns the output of the convolution. Arguments --------- x : torch.Tensor (batch, time, channel) input to convolve. 2d or 4d tensors are expected. rrZcausalrZvalidz1Padding must be 'same', 'valid' or 'causal'. Got ) r transposerr_manage_paddingr rrFpadrrZsqueeze)rxZnum_padZwxrrrforward3s0        zConv1d_O.forwardr rrcCs.|jd}t||||}tj|||jd}|S)Nr)mode)shapeget_padding_elemr!r"r)rr#r rrL_inrrrrr \s zConv1d_O._manage_paddingcCsrt|dkr d|_d}n|jr|d}nt|dkr|d}n tdtt||jddkr7td|j|S)zIChecks the input shape and returns the number of input channels. Trz"conv1d expects 2d, 3d inputs. Got rz4The field kernel size must be an odd number. Got %s.)lenrrrstrr )rr&rrrrrns"     zConv1d_O._check_input_shape) NNrrrrTrF) __name__ __module__ __qualname__r r$intr r __classcell__rrrrr s(() rceZdZfddZZS)rctj|ddi|dSNrTr r rargskwargsrrrr zConv1d.__init__r-r.r/r r1rrrrrrr(rr rcCs|dkr%t||||d}||d||}|d|dg}|S|||dd|d}||d||dg}|S)zThis function computes the number of elements to add for zero-padding. Arguments --------- L_in : int stride: int kernel_size : int dilation : int rr))mathceil)r(rr rZn_stepsZL_outrrrrr's r'cs6eZdZ        d fdd Zdd ZZS) BatchNorm1d_ONh㈵>皙?TFc sVt||_||_|dur|r|d}n|dur|d}tj|||||d|_dS)Nrr)epsmomentumaffinetrack_running_stats)r r combine_batch_timerr BatchNorm1dnorm) rr input_sizerArBrCrDrErrrrr s    zBatchNorm1d_O.__init__cCs|j}|jr,|jdkr||d|d|d}n||d|d|d|d}n |js5|dd}||}|jrD||}|S|jsM|dd}|S)aReturns the normalized input tensor. Arguments --------- x : torch.Tensor (batch, time, [channels]) input to normalize. 2d or 3d tensors are expected in input 4d tensors can be used when combine_dims=True. r*rrr)r)r&rEndimZreshaperrrG)rr#Zshape_orZx_nrrrr$s       zBatchNorm1d_O.forward)NNr?r@TTFF)r-r.r/r r$r1rrrrr>sr>cr2)rFcr3r4r5r6rrrr r9zBatchNorm1d.__init__r:rrrrrFr;rFcsLeZdZdZdejjdgdgdgdddffd d Zdd d ZZ S)XvectoraLThis model extracts X-vectors for speaker recognition and diarization. Arguments --------- device : str Device used e.g. "cpu" or "cuda". activation : torch class A class for constructing the activation layers. tdnn_blocks : int Number of time-delay neural (TDNN) layers. tdnn_channels : list of ints Output channels for TDNN layer. tdnn_kernel_sizes : list of ints List of kernel sizes for each TDNN layer. tdnn_dilations : list of ints List of dilations for kernels in each TDNN layer. lin_neurons : int Number of neurons in linear layers. Example ------- >>> compute_xvect = Xvector('cpu') >>> input_feats = torch.rand([5, 10, 40]) >>> outputs = compute_xvect(input_feats) >>> outputs.shape torch.Size([5, 1, 512]) cpu)rMrMrMi)rLr*r*rr)rr)r*rrrMPc sdtt|_t|D]!} || } |jt|| || || d|t| dg|| }qdS)N)rrr r)rH) r r rZ ModuleListblocksrangeextendrrF) rZdeviceZ activationZ tdnn_blocksZ tdnn_channelsZtdnn_kernel_sizesZtdnn_dilationsZ lin_neuronsrZ block_indexrrrrr s   zXvector.__init__Nc CsR|dd}|jD]}z|||d}Wq ty ||}Yq w|dd}|S)z]Returns the x-vectors. Arguments --------- x : torch.Tensor rr))lengths)rrO TypeError)rr#Zlenslayerrrrr$s     zXvector.forward)N) r-r.r/__doc__torchrZ LeakyReLUr r$r1rrrrrJsrJ)numpynprVZtorch.nnrZtorch.nn.functionalZ functionalr!Modulerrr0r'r>rFrJrrrrs }<