Add tacotron model #855
Add tacotron model #855
Conversation
torchaudio/models/_tacotron2.py
Outdated
|
|
||
| return outputs | ||
|
|
||
| def infer(self, x: Tensor, input_lengths: Tensor) -> Tensor: |
There was a problem hiding this comment.
What's the difference with forward here?
Having an "infer" method would be a new convention, so we need to be careful before adding it.
There was a problem hiding this comment.
The difference here is the dropout layer. I agree, since the "infer" won't be used in the training, I will remove this part.
torchaudio/models/_tacotron2.py
Outdated
|
|
||
| return mel_outputs, gate_outputs, alignments | ||
|
|
||
| def infer(self, memory: Tensor, memory_lengths: Tensor) -> Tuple[Tensor]: |
torchaudio/models/_tacotron2.py
Outdated
| [mel_outputs, mel_outputs_postnet, gate_outputs, alignments], output_lengths | ||
| ) | ||
|
|
||
| def infer(self, inputs: Tensor, input_lengths: Tensor) -> Tuple[Tensor]: |
jimchen90
force-pushed
the
tacotron_model
branch
from
f32634f to
62caf96
Compare
|
Hi @jimchen90! Thank you for your pull request. We require contributors to sign our Contributor License Agreement, and yours needs attention. You currently have a record in our system, but we do not have a signature on file. In order for us to review and merge your code, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA. If you have received this in error or have any questions, please contact us at [email protected]. Thanks! |
|
Continuing this feature in #1621. |
|
Thank you for signing our Contributor License Agreement. We can now accept your code for this (and any) Facebook open source project. Thanks! |
4 participants
This is to add the first part of tacotron2 model.