Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add C++ files for CTC decoder bindings #2079

Closed
wants to merge 1 commit into from

Conversation

carolineechen
Copy link
Contributor

part of #2072 -- splitting up the PR for easier review

Add C++ files for binding CTC decoder functionality for Python

Note: the code here will not be compiled until the build process is changed

#include <torchaudio/csrc/decoder/bindings/_dictionary.cpp>

PYBIND11_MODULE(_torchaudio_decoder, m) {
#ifdef BUILD_CTC_DECODER
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think we can remove this directive since we are creating a library file separate from libtorchaudio.

@@ -0,0 +1,19 @@
include(ExternalProject)
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We no longer need any of the *.cmake files.

@@ -0,0 +1,111 @@
/*
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think _decoder.cpp, _dictionary.cpp and pybind.cpp can be combined and placed directly at torchaudio/csrc/decoder/*. it looks strange that pybind.cpp incldues two other cpp files.

@facebook-github-bot
Copy link
Contributor

@carolineechen has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

@mthrok
Copy link
Collaborator

mthrok commented Dec 17, 2021

note: style check is failing, so let's follow up on that one as well.

@facebook-github-bot
Copy link
Contributor

@carolineechen has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

xiaohui-zhang pushed a commit to xiaohui-zhang/audio that referenced this pull request May 4, 2022
Summary:
part of pytorch#2072 -- splitting up the PR for easier review

Add C++ files for binding CTC decoder functionality for Python

Note: the code here will not be compiled until the build process is changed

Pull Request resolved: pytorch#2079

Reviewed By: mthrok

Differential Revision: D33196286

Pulled By: carolineechen

fbshipit-source-id: 9fe4a8635b60ebfb594918bab00f5c3dccf96bd2
mthrok pushed a commit to mthrok/audio that referenced this pull request Dec 13, 2022
* Create torchserve_with_ipex_2.rst

* create torchserve-ipex-images-2

* add torchserve-ipex-images-2 png

* add png

* update wording

* update wording

* update wording

* update wording

* add tutorial to matrix and left nav

* Delete placeholder

* link github

* tutorial -> blog

Co-authored-by: Svetlana Karslioglu <svekars@fb.com>

* tutorial -> blog

Co-authored-by: Svetlana Karslioglu <svekars@fb.com>

* grammar fix

Co-authored-by: Svetlana Karslioglu <svekars@fb.com>

* grammar fix

Co-authored-by: Svetlana Karslioglu <svekars@fb.com>

* grammar fix

Co-authored-by: Svetlana Karslioglu <svekars@fb.com>

* blog -> tutorial

Co-authored-by: Svetlana Karslioglu <svekars@fb.com>

* un-tuned -> untuned, submetircs -> sub-metrics

* blog -> tutorial, we'll -> we will

* with torch.autograd.profiler.emit_itt()

* grammar fix

Co-authored-by: Svetlana Karslioglu <svekars@fb.com>

* grammar fix

Co-authored-by: Svetlana Karslioglu <svekars@fb.com>

* we'll -> we will

Co-authored-by: Svetlana Karslioglu <svekars@fb.com>

* we'll -> we will

Co-authored-by: Svetlana Karslioglu <svekars@fb.com>

* we'll -> we will

Co-authored-by: Svetlana Karslioglu <svekars@fb.com>

* we've -> we have

Co-authored-by: Svetlana Karslioglu <svekars@fb.com>

* we'll -> we will

Co-authored-by: Svetlana Karslioglu <svekars@fb.com>

* we'll ->  we will

Co-authored-by: Svetlana Karslioglu <svekars@fb.com>

* 2 -> two

Co-authored-by: Svetlana Karslioglu <svekars@fb.com>

* we'll -> we will

Co-authored-by: Svetlana Karslioglu <svekars@fb.com>

* e.g., -> for example, refer to -> see

Co-authored-by: Svetlana Karslioglu <svekars@fb.com>

* etc -> and more

* we'll -> we will

Co-authored-by: Svetlana Karslioglu <svekars@fb.com>

* we'll -> we will

Co-authored-by: Svetlana Karslioglu <svekars@fb.com>

* we'll we will

Co-authored-by: Svetlana Karslioglu <svekars@fb.com>

* un-tuned -> untuned

Co-authored-by: Svetlana Karslioglu <svekars@fb.com>

* take-aways -> conclusion

Co-authored-by: Svetlana Karslioglu <svekars@fb.com>

* blog -> tutorial, we've -> we have

Co-authored-by: Svetlana Karslioglu <svekars@fb.com>

* fix linking

Co-authored-by: Svetlana Karslioglu <svekars@fb.com>

* fix png sizes

* my lin <url>__

* (1) add content under each heading (2) fix heading syntax

* update

* blog -> tutorial

Co-authored-by: Svetlana Karslioglu <svekars@fb.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants