o ¡¿¯i@ ã@s<dZddlZddlmZddlmZGdd„dejjƒZdS)z#Variance predictor related modules.éN)Úcheck_argument_types)Ú LayerNormc sdeZdZdZ     ddeded ed ed ed ef ‡fd d„ Zddej dej dej fdd„Z ‡Z S)ÚVariancePredictoraVariance predictor module. This is a module of variacne predictor described in `FastSpeech 2: Fast and High-Quality End-to-End Text to Speech`_. .. _`FastSpeech 2: Fast and High-Quality End-to-End Text to Speech`: https://arxiv.org/abs/2006.04558 éé€éTçà?ÚidimÚn_layersÚn_chansÚ kernel_sizeÚbiasÚ dropout_ratec s¢tƒsJ‚tƒ ¡tj ¡|_t|ƒD]2}|dkr|n|}|jtj tjj |||d|dd|dtj  ¡t |ddtj  |¡¡g7_qtj  |d¡|_dS)a]Initilize duration predictor module. Args: idim (int): Input dimension. n_layers (int): Number of convolutional layers. n_chans (int): Number of channels of convolutional layers. kernel_size (int): Kernel size of convolutional layers. dropout_rate (float): Dropout rate. rér)ÚstrideÚpaddingr )ÚdimN)rÚsuperÚ__init__ÚtorchÚnnÚ ModuleListÚconvÚrangeÚ SequentialÚConv1dÚReLUrÚDropoutÚLinearÚlinear) Úselfr r r r r rÚidxÚin_chans©Ú __class__©ú^/home/ubuntu/.local/lib/python3.10/site-packages/espnet2/tts/fastspeech2/variance_predictor.pyrs*     ú  õ ÿzVariancePredictor.__init__NÚxsÚx_masksÚreturncCsJ| dd¡}|jD]}||ƒ}q | | dd¡¡}|dur#| |d¡}|S)aCalculate forward propagation. Args: xs (Tensor): Batch of input sequences (B, Tmax, idim). x_masks (ByteTensor): Batch of masks indicating padded part (B, Tmax). Returns: Tensor: Batch of predicted sequences (B, Tmax, 1). réÿÿÿÿrNg)Ú transposerrÚ masked_fill)r r'r(Úfr%r%r&ÚforwardBs   zVariancePredictor.forward)rrrTr)N) Ú__name__Ú __module__Ú __qualname__Ú__doc__ÚintÚboolÚfloatrrÚTensorr.Ú __classcell__r%r%r#r&rs* ùþýüûúù&)r) r2rÚ typeguardrÚ2espnet.nets.pytorch_backend.transformer.layer_normrrÚModulerr%r%r%r&Ús