nnsvs.train_util.compute_distortions

nnsvs.train_util.compute_distortions(pred_out_feats, out_feats, lengths, out_scaler, model_config)[source]

Compute distortion measures between predicted and ground-truth acoustic features

Parameters:

  • pred_out_feats (nn.Tensor) – predicted acoustic features

  • out_feats (nn.Tensor) – ground-truth acoustic features

  • lengths (nn.Tensor) – lengths of the sequences

  • out_scaler (nn.Module) – scaler to denormalize features

  • model_config (dict) – model configuration

Returns:

a dict that includes MCD for mgc/bap, V/UV error and F0 RMSE

Return type:

dict