o ¡¿¯iÓã@sTdZddlmZddlZddlmZddlmZddlm Z Gdd„dej j ƒZ dS) z,Fastspeech2 related loss module for ESPnet2.é)ÚTupleN)Úcheck_argument_types)ÚDurationPredictorLoss)Úmake_non_pad_maskcseZdZdZddedef‡fdd„ Zdejd ejd ejd ejd ejd ejdejdejdejdejdejdeejejejejffdd„Z ‡Z S)ÚFastSpeech2Lossz%Loss function module for FastSpeech2.TFÚ use_maskingÚuse_weighted_maskingcsntƒsJ‚tƒ ¡||ks|rJ‚||_||_|jrdnd}tjj|d|_tjj |d|_ t |d|_ dS)a!Initialize feed-forward Transformer loss module. Args: use_masking (bool): Whether to apply masking for padded part in loss calculation. use_weighted_masking (bool): Whether to weighted masking in loss calculation. ÚnoneÚmean)Ú reductionN) rÚsuperÚ__init__rrÚtorchÚnnÚL1LossÚ l1_criterionÚMSELossÚ mse_criterionrÚduration_criterion)Úselfrrr ©Ú __class__©úP/home/ubuntu/.local/lib/python3.10/site-packages/espnet2/tts/fastspeech2/loss.pyr s zFastSpeech2Loss.__init__Ú after_outsÚ before_outsÚd_outsÚp_outsÚe_outsÚysÚdsÚpsÚesÚilensÚolensÚreturnc Csâ|jrRt| ƒ d¡ |j¡} | | ¡}|dur| | ¡}| | ¡}t| ƒ |j¡} | | ¡}| | ¡}t| ƒ d¡ |j¡}| |¡}| |¡}| |¡}|  |¡} | ||¡}|durd|| ||¡7}| ||¡}| ||¡}| || ¡}|j rët| ƒ d¡ |j¡} |   ¡| j ddd  ¡}||  d¡|  d¡}t| ƒ |j¡} |   ¡| j ddd  ¡}||  d¡}|  |¡ | ¡  ¡}|  |¡ | ¡  ¡}|  d¡}| d¡}|  |¡ |¡  ¡}|  |¡ |¡  ¡}||||fS)aWCalculate forward propagation. Args: after_outs (Tensor): Batch of outputs after postnets (B, T_feats, odim). before_outs (Tensor): Batch of outputs before postnets (B, T_feats, odim). d_outs (LongTensor): Batch of outputs of duration predictor (B, T_text). p_outs (Tensor): Batch of outputs of pitch predictor (B, T_text, 1). e_outs (Tensor): Batch of outputs of energy predictor (B, T_text, 1). ys (Tensor): Batch of target features (B, T_feats, odim). ds (LongTensor): Batch of durations (B, T_text). ps (Tensor): Batch of target token-averaged pitch (B, T_text, 1). es (Tensor): Batch of target token-averaged energy (B, T_text, 1). ilens (LongTensor): Batch of the lengths of each input (B,). olens (LongTensor): Batch of the lengths of each target (B,). Returns: Tensor: L1 loss value. Tensor: Duration predictor loss value. Tensor: Pitch predictor loss value. Tensor: Energy predictor loss value. éÿÿÿÿNéT)ÚdimÚkeepdimré)rrÚ unsqueezeÚtoÚdeviceÚ masked_selectrrrrÚfloatÚsumÚsizeÚmul)rrrrrrrr r!r"r#r$Ú out_masksÚduration_masksÚ pitch_masksÚl1_lossÚ duration_lossÚ pitch_lossÚ energy_lossÚ out_weightsÚduration_weightsÚ pitch_weightsrrrÚforward+sJ%             ÿÿ  ÿ zFastSpeech2Loss.forward)TF) Ú__name__Ú __module__Ú __qualname__Ú__doc__Úboolr rÚTensorrr=Ú __classcell__rrrrrs8þýüûúùø ÷ ö õ ô ór) rAÚtypingrrÚ typeguardrÚ9espnet.nets.pytorch_backend.fastspeech.duration_predictorrÚ&espnet.nets.pytorch_backend.nets_utilsrrÚModulerrrrrÚs