Skip to content
This repository was archived by the owner on Jul 7, 2023. It is now read-only.

Conversation

EugKar
Copy link
Contributor

@EugKar EugKar commented Jun 5, 2019

This pull request enables using partial_targets field of the inputs dictionary at inference time, when inputs field is also specified.
One of the cases when partial targets are useful is mutilingual speech recognition problem, as described in this paper: Multilingual End-to-End Speech Recognition with A Single Transformer on Low-Resource Languages. Language tags may be specified at partial_targets input, if there is prior knowledge of the speaker's language.

@googlebot
Copy link

Thanks for your pull request. It looks like this may be your first contribution to a Google open source project (if not, look below for help). Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

📝 Please visit https://cla.developers.google.com/ to sign.

Once you've signed (or fixed any issues), please reply here (e.g. I signed it!) and we'll verify it.


What to do if you already signed the CLA

Individual signers
Corporate signers

ℹ️ Googlers: Go here for more info.

@googlebot googlebot added the cla: no PR author has not signed CLA label Jun 5, 2019
@EugKar
Copy link
Contributor Author

EugKar commented Jun 5, 2019

I signed it!

@googlebot
Copy link

CLAs look good, thanks!

ℹ️ Googlers: Go here for more info.

@googlebot googlebot added cla: yes PR author has signed CLA and removed cla: no PR author has not signed CLA labels Jun 5, 2019
@afrozenator
Copy link
Contributor

Thanks a lot @EugKar !!

@afrozenator afrozenator merged commit f45ca84 into tensorflow:master Jun 7, 2019
tensorflow-copybara pushed a commit that referenced this pull request Jun 7, 2019
PiperOrigin-RevId: 252143053
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
cla: yes PR author has signed CLA
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants