addons
addons copied to clipboard
RNN-Transducer Loss support
I found that there are no RNN-Transducer loss in the new version. I have to use third party pkg like wrap-transducer So, official support in both tf1.x and tf2 is therefore expected. Thanks!
Though this is potentially out of the scope of TensorFlow core, it might make sense to add to TensorFlow Addons as a loss function.
Rerouting the request to addons
; @seanpmorgan for visibility.
I'm not very familiar with this so I'll defer to @qlzh727 as RNN subpackage owner to evaluate if this makes sense within addons.
Sorry for the very late reply.
I am not very familiar with that too. Could u provide a reference to the paper for it?
Also, for the addon package, we are targeting TF 2.0, which means 1.x is probably not supported.
Paper is here https://arxiv.org/abs/1211.3711. It's quite similar to CTC loss.
Sorry for the very late reply.
I am not very familiar with that too. Could u provide a reference to the paper for it?
Also, for the addon package, we are targeting TF 2.0, which means 1.x is probably not supported.
Paper is here https://arxiv.org/abs/1211.3711
This issue is pretty old, but since it is still open does that mean I could work on an implementation? I work on ASR and would benefit from an implementation with TensorFlow ops. From what I can tell, everyone is still using the warp-transducer version, and the build process adds additional complexity to projects.
Sure, any contribution is welcome.
@will-rice I have an implementation of RNNT (link to the repository) using TensorFlow ops. We can work on this together, if you are interested?
@iamjanvijay sounds good!
@iamjanvijay do you want me to just port your ops to the addons loss format and tag you in the PR?
@will-rice Yes. That can be a good way to start then we can do iterations over it. What do you suggest?
@will-rice Yes. That can be a good way to start then we can do iterations over it. What do you suggest?
that works. I'll put it together and then tag you.
TensorFlow Addons is transitioning to a minimal maintenance and release mode. New features will not be added to this repository. For more information, please see our public messaging on this decision: TensorFlow Addons Wind Down
Please consider sending feature requests / contributions to other repositories in the TF community with a similar charters to TFA: Keras Keras-CV Keras-NLP
您好,我已经收到您的来信,会尽快处理。