Possible bug?

[ghostcow]

In feature_extract.py lines 241-242 /feat holds the extended features (upsampled features), and /feat_org holds the original features.

On the other hand, decode.py lines 74-77, /feat is loaded from the features file when upsampling_factor == 0, and /feat_org is loaded otherwise.

Shouldn't it be the other way around?

Thanks

[kan-bayashi]

upsampling_factor==0 represents that we do not use additional upsampling layer. In other words, when we set upsampling_factor>0, instead of the use of extended features (/feat), we use UpSampling layer with original features (/feat_org). Therefore, in decoding, if upsampling_factor != 0, /feat_org is loaded.

Sorry for my misleading script.

[ghostcow]

Thanks