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.

Sign up for GitHub

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

Jump to bottom

Add audio data provider and preprocessor for speech recognition datasets. #2226

Closed
xinghai-sun opened this issue May 22, 2017 · 1 comment · Fixed by PaddlePaddle/models#55
Closed

Add audio data provider and preprocessor for speech recognition datasets. #2226

xinghai-sun opened this issue May 22, 2017 · 1 comment · Fixed by PaddlePaddle/models#55
Assignees
@xinghai-sun
Projects
Deep Speech 2

Comments

@xinghai-sun
Copy link
Contributor

  • Prepare one or more public English speech recognition data sets (e.g. LibriSpeech), and respective baselines.
  • Convert all audio file formats to .wav format.
  • Add a file manifest generator for each dataset, and add a merger if there exist more than one datasets. Make this interface unified across different datasets.
  • Add spectrogram feature extractor, power normalizer etc.
  • Add transcription text parser (tokenization, dictionary generation etc).
  • Add batch data reader with SortaGrad.
  • Refer to the DS2 design doc and update it when necessary.
  • Please pull your codes and docs into PaddlePaddle/models.
@xinghai-sun xinghai-sun self-assigned this May 22, 2017
@xinghai-sun xinghai-sun mentioned this issue May 22, 2017
Closed
@xinghai-sun xinghai-sun added this to Feature Requests in Deep Speech 2 May 22, 2017
@xinghai-sun xinghai-sun moved this from Feature Requests to Developing in Deep Speech 2 May 22, 2017
This was referenced May 22, 2017
Closed
Merged
@xinghai-sun xinghai-sun moved this from Developing to Under Reviews in Deep Speech 2 May 24, 2017
@xinghai-sun
Copy link
Contributor Author

Pull Request PaddlePaddle/models#55

@xinghai-sun xinghai-sun moved this from Under Reviews to Done in Deep Speech 2 Jun 2, 2017
heavengate pushed a commit to heavengate/Paddle that referenced this issue Aug 16, 2021
@nemonameless
[dygraph] Add gnfpn and gnhead (PaddlePaddle#2226)
4cd1291 
* add gn head fpn, test=dygraph

* add gn for cascade

* update gn readme, test=dygraph
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@xinghai-sun xinghai-sun

Labels
None yet
Projects
Deep Speech 2
  
Done
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Add audio data provider and a simplified DeepSpeech2 model configuration. xinghai-sun/models
1 participant
@xinghai-sun