search

keonlee9420 / Parallel-Tacotron2

PyTorch Implementation of Google's Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling
MIT License
189 stars 45 forks source link

fix mask and soft-dtw loss #9

Closed zhang-wy15 closed 3 years ago

zhang-wy15 commented 3 years ago

1 fix mask problem when calculating W in LearnUpsampling Module and attention matrix in VaribleLengthAttention module. 2 a new Jacobian matrix of Manhattan distance 3 deal with mel spectrograms of different lengths

keonlee9420 commented 3 years ago

Thanks for your contribution :)